CN110633458A - Method and device for generating referee document - Google Patents
Method and device for generating referee document Download PDFInfo
- Publication number
- CN110633458A CN110633458A CN201810664228.9A CN201810664228A CN110633458A CN 110633458 A CN110633458 A CN 110633458A CN 201810664228 A CN201810664228 A CN 201810664228A CN 110633458 A CN110633458 A CN 110633458A
- Authority
- CN
- China
- Prior art keywords
- document
- text
- elements
- generating
- case
- 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 72
- 230000014509 gene expression Effects 0.000 claims description 58
- 238000000605 extraction Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 15
- 238000007635 classification algorithm Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000015654 memory Effects 0.000 description 22
- 238000012545 processing Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000013145 classification model Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 238000002372 labelling Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- 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
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Technology Law (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a generation method and a generation device of a referee document. Wherein, the method comprises the following steps: acquiring a case original text of a referee document to be generated; extracting element features of elements from the case original text; generating a text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following components: elements, and relationships between elements; and generating the referee document at least according to the text part. The method and the device solve the technical problem that the referee document cannot be automatically generated in the related technology.
Description
Technical Field
The present application relates to the field of computers, and in particular, to a method and an apparatus for generating a referee document.
Background
With the rapid development of the internet technology, the intelligent device brings convenience to people in daily life and work, for example, in a court business scene, legal staff in the court can extract important information in a referee document through an intelligent system such as an internet court, so that the legal staff can perform statistical analysis on the case or the case of the type.
An existing intelligent system such as an internet court is generally used as an auxiliary work of a lawful worker, for example, information is extracted from a referee document through a technology such as semantic analysis, or a relationship between legal elements is constructed through a manual processing mode, and a referee result is generated according to the relationship between the legal elements. In addition, in the process of generating the referee document, legal staff are required to manually mark or search related data, time and labor are consumed, and the working efficiency of the legal staff is reduced. In addition, in the prior art, the judgment result of the referee document needs to be manually extracted by legal staff, and the content of the referee document, especially the content of the referee document of a complex case, is generally more, so that the problem of inaccurate extraction content is easy to occur in the scheme of manually extracting the judgment result.
Aiming at the problem that the referee document cannot be automatically generated in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a generation method and a generation device of a referee document, which at least solve the technical problem that the referee document cannot be automatically generated in the related art.
According to an aspect of the embodiments of the present invention, there is provided a method for generating a referee document, including: acquiring a case original text of a referee document to be generated; extracting element features of elements from the case original text; generating a text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following components: elements, and relationships between elements; and generating the referee document at least according to the text part.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for generating a referee document, including: the acquiring module is used for acquiring case original texts of the official documents to be generated; the extraction module is used for extracting element features of elements from the case original text; the first generation module is used for generating the text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises: elements, and relationships between elements; and the second generation module is used for generating the referee document at least according to the text part.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium storing a computer program, wherein the program realizes the generation method of the referee document when executed by a processor.
In the embodiment of the invention, a mode of generating the referee document by using a knowledge graph is adopted, the case original text of the referee document to be generated is obtained, the element characteristics of elements are extracted from the case original text, then the text part of the referee document is generated according to the knowledge graph and the element characteristics, and the referee document is generated at least according to the text part, wherein the knowledge graph comprises the following components: elements, and relationships between elements.
In the above process, the elements required for generating the official document can be determined according to the element characteristics, and after the elements required for generating the official document are obtained, the text part of the official document can be generated according to the knowledge graph. In the process of generating the text part of the referee document, legal staff is not required to participate, so that the workload of the legal staff is reduced. In addition, because the text part is the core part of the referee document and comprises the reasoning and explaining part of the judgment result, in the prior art, the part is finished manually, and in the scheme provided by the application, the text part can be generated according to the element characteristics and the knowledge graph of the case original document, so that the purpose of automatically generating the referee document is achieved, and the technical effect of improving the working efficiency of legal staff is realized.
Therefore, the technical problem that the referee document cannot be automatically generated in the related technology can be solved by the scheme provided by the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a computer terminal for implementing a method for generating a referee document according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for generating a referee document according to an embodiment of the present application;
FIG. 3 is a schematic illustration of an alternative knowledge-graph according to embodiments of the present application;
FIG. 4 is a schematic illustration of an alternative referee document according to an embodiment of the present application;
FIG. 5 is a schematic illustration of an alternative referee document according to an embodiment of the present application;
FIG. 6 is a schematic diagram of an alternative tagging element according to an embodiment of the application;
FIG. 7 is a block diagram of an alternative method for generating a referee document according to an embodiment of the present application;
FIG. 8 is a schematic structural diagram of an apparatus for generating official documents according to an embodiment of the present application; and
fig. 9 is a block diagram of a computer terminal according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. 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 application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
First, some terms or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:
the Knowledge graph, also called scientific Knowledge graph, is a structured semantic Knowledge base, which is used to describe concepts and their interrelations in the physical world in symbolic form, and its basic constituent units are "entity-relationship-entity" triplets, and entities and their related attribute-value pairs, which are connected with each other through the relationships between the entities to form a mesh Knowledge structure.
Example 1
There is also provided, in accordance with an embodiment of the present application, an embodiment of a method for producing a referent document, to be noted that the steps illustrated in the flowchart of the drawings may be carried out in a computer system such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be carried out in an order different than here.
The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Fig. 1 shows a hardware configuration block diagram of a computer terminal (or mobile device) for implementing the referee document generation method. As shown in fig. 1, computer terminal a (or mobile device a) may include one or more (shown as 102a, 102b, … …, 102 n) processors 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), memory 104 for storing data, and a transmission module 106 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the electronic device. For example, computer terminal A may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
It should be noted that the one or more processors 102 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Furthermore, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer terminal a (or mobile device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).
The memory 104 can be used for storing software programs and modules of application software, such as program instructions/data storage devices corresponding to the method for generating a referee document in the embodiment of the present application, and the processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for generating a referee document of an application program is realized. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the computer terminal a through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal a. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 106 can be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer terminal a (or mobile device).
Under the operating environment, the application also provides intelligent equipment for generating the referee document, and the intelligent equipment can execute the generation method of the referee document provided by the application. Fig. 2 shows a flowchart of a method for generating a referee document, and as shown in fig. 2, the method for generating a referee document may include the following steps:
step S202, acquiring case original texts of the official documents to be generated.
It should be noted that the content of the referee document may include, but is not limited to, information of parties (including original information and information of a subject), trial process, original appeal, subject answer, subject finding, subject thinking, and referee result. Wherein different parts of the case original document generate different parts of the umpire document, for example, the original appeal document generates the original appeal part of the umpire document, and the defendant-answer document generates the defendant-answer part.
In an alternative scheme, for different parts of the referee document, the manner of acquiring corresponding parts of the case text may be different, for example, for the parts of the information of the parties, the trial process, the referee result, etc., because the formats of the components are fixed, when acquiring the information of the parts from the case text, the manual writing module may be used in combination with the filling of the key entity information, for example, for the information part of the parties, the legal staff may input the information of the names, sexes, identification numbers, addresses, etc., of the original and the advertised names, sexes, identification numbers, addresses, etc., by using an input device (for example, a mouse, a keyboard) or a voice, etc.
In another alternative, the intelligent device for generating the referee document may convert the message in the paper or picture format into information in the text format by using an OCR (Optical Character Recognition) technology, and the intelligent device acquires the original document of the case from the converted information.
In step S204, the element feature of the element is extracted from the case text.
In step S204, the element in the case text is a sentence or a word playing a key role in the case text or the sentence, and the element feature of the element is a value corresponding to the element, for example, the element feature may be in a numerical form or a boolean form. In addition, different elements correspond to different extraction modes, for example, digital element features such as transaction amount and transaction quantity can be extracted from case original texts (such as original appellation documents, defendant and answer documents, evidence documents and the like) by adopting a direct extraction mode; for boolean type feature characteristics, such as whether goods are received, whether the original price is false, etc., the label can be extracted from the original text of the case.
It should be noted that, the above description only introduces the element features of the number type and the element features of the boolean type, and other element features have corresponding extraction methods, which are not described herein again.
Step S206, generating the text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following steps: elements, and relationships between elements.
It should be noted that, in step S206, the text part of the official document may include the home opinion part in the official document. In addition, the relationships of the knowledge-graph are stored in the form of triples, i.e., in the form of "element-relationship-element", where elements in the knowledge-graph in this application include legal knowledge elements, e.g., whether fraud is being constructed. Alternatively, fig. 3 shows a schematic diagram of an alternative knowledge-graph, in fig. 3, each node may represent an element (e.g., "number of prosecutions in the chinese judge document network"), a criterion (e.g., "whether or not there are 3 or more prosecutions in the chinese judge document network") or a logic gate (e.g., "or 001"), and the node on the left is the input of the node on the right, e.g., the node "number of prosecutions in the chinese judge document network" is the input node of the node "whether or not there are 3 or more prosecutions in the chinese judge document network".
Further, it is also necessary to create a knowledge graph before generating the body part of the official document based on the knowledge graph and the feature of the element. The construction method of the knowledge graph includes, but is not limited to, manual construction and automatic algorithm construction. In addition, in order to improve the accuracy of generating the text part of the official document, different knowledge maps need to be constructed for different types of cases, for example, a knowledge map required for generating the official document of a criminal case is different from a knowledge map required for generating the official document of a civil case.
And step S208, generating a referee document at least according to the text part.
After the text part is generated, other parts of the generated official document are combined in step S208, so that an official document, such as the official documents shown in fig. 4 and 5, can be generated. The combination of the parts of the referee document may be, but not limited to, template combination, and for example, the document template including the information of the party, the request for prosecution, the recognition of the notice, the confirmation of evidence, the recognition of fact, the recognition of the own court, and the judgment of the own court is generated, then the contents corresponding to the parts are acquired, and the contents corresponding to the parts are put into the corresponding modules in the document template, thereby generating the referee document shown in fig. 4 and 5.
It should be noted that different types of cases require different document templates corresponding to knowledge patterns.
Based on the schemes defined in the above steps S202 to S208, it can be known that, by using a mode of generating a referee document by using a knowledge graph, a case original text of the referee document to be generated is acquired, and element features of elements are extracted from the case original text, then, a text portion of the referee document is generated according to the knowledge graph and the element features, and the referee document is generated at least according to the text portion, wherein the knowledge graph includes: elements, and relationships between elements.
In the above process, the elements required for generating the official document can be determined according to the element characteristics, and after the elements required for generating the official document are obtained, the text part of the official document can be generated according to the knowledge graph. In the process of generating the text part of the referee document, legal staff is not required to participate, so that the workload of the legal staff is reduced. In addition, because the text part is the core part of the referee document and comprises the reasoning and explaining part of the judgment result, in the prior art, the part is finished manually, and in the scheme provided by the application, the text part can be generated according to the element characteristics and the knowledge graph of the case original document, so that the purpose of automatically generating the referee document is achieved, and the technical effect of improving the working efficiency of legal staff is realized.
Therefore, the technical problem that the referee document cannot be automatically generated in the related technology can be solved by the scheme provided by the application.
It should be noted that, after acquiring the case original text of the official document to be generated, the intelligent device may extract the feature characteristics of the elements from the case original text by at least one of the following:
the first method is as follows: the method includes extracting element features of entity elements from the text expression of the case text, wherein the entity elements are elements of which the element features are directly expressed in the text expression of the case text, such as transaction amount, transaction quantity and the like directly extracted from the case text, and the manner of extracting the element features from the text can include but is not limited to a template matching extraction manner and a machine learning model extraction manner. Further, machine learning models include, but are not limited to, Conditional Random Fields (CRF) models, two-way LSTM (Long Short-Term Memory) models, and the like.
The second method comprises the following steps: extracting label elements from the text expression of the case original text, and classifying the label elements to obtain element characteristics of the label elements, wherein the element characteristics of the label elements are expressed in the case original text by adopting a preset classification algorithm. In this manner, the tag elements may be boolean type tag elements, such as whether a good was received, whether a false original price, whether a false discount, etc. After the label elements are obtained, the intelligent device trains each label element to obtain a classifier, so that each sentence in a corresponding part (for example, an original complaint document) in the case original text is judged by the classifier to determine whether each sentence in the part is matched with the corresponding element feature. In addition, in the second mode, the classifier may be, but is not limited to, a Support Vector Machine (SVM) classifier.
Further, after extracting the element features from the case original text, the intelligent device may generate the text part of the referee document according to the knowledge graph and the element features, wherein the method for generating the text part of the referee document may include:
at step S2060, the dispute focus of the case is identified.
In an alternative arrangement, the intelligent device may identify the dispute focus of the case by identifying the selection instructions issued by the plaintiff and the defendant. Specifically, in the intelligent device for generating the referee document, the original complaint and the told answer are both completed through the internet, the original report can select the problem to be disputed in the knowledge map on the intelligent device, for example, selecting 'original report is not to be abused', the told selects whether to accept the original report according to the dispute problem selected by the original report, if the told selects 'original report', the opinions of the original report and the told are not consistent, and 'whether the original report is to be abused' is the dispute focus of the case.
Step S2062, generating a path from the basic element of the case to the dispute focus according to the element characteristics and the relationship between the elements in the knowledge graph.
The knowledge graph includes the trial logic of the case, and the dispute focus and the basic elements, such as purchase amount and history data (e.g., original claim documents in the law), extracted from information such as original claim documents, followed-by response documents, and evidence documents, are all nodes in the knowledge graph. The base element is the starting point of the path, which can also be understood as a dispute-free node without a preceding node.
Step S2064, generating the text part of the referee document according to the path.
Specifically, after a path with a basic element as a starting point and a dispute focus as a key point is determined, the intelligent device determines child nodes and inference nodes included in the path, then traverses the nodes on the path, and describes the nodes to obtain a text part of the referee document. The sub-nodes comprise nodes of direct words in case original text for expressing feature characteristics, and the reasoning nodes comprise nodes which can cause the dispute focus to be out of place.
It should be noted that different description forms are adopted for different nodes, wherein when a node comprises a child node, the child node is described by using the element characteristics expressed by the case original text; and describing the reasoning nodes according to element templates under the condition that the nodes comprise the reasoning nodes, wherein the element templates comprise: the common words of the referee document and the position of the entity corresponding to the feature. Specifically, a mode of traversing the knowledge graph is adopted, and the nodes on the path are accessed from the child nodes until the nodes are detected to be inference nodes. And under the condition that the nodes comprise the reasoning nodes, generating the description of the reasoning nodes by using the element module, transmitting the description to the next node, detecting whether the next node is the reasoning node or not, and further performing corresponding description according to the types of the nodes. After access to all the dispute focus points in the case is completed, the text part of the referee document is generated based on the description under each path.
Furthermore, it should be noted that before describing the inference node according to the element template, the element template can be obtained by:
step S3060, obtaining multiple expressions of the judgment key points in a predetermined number of judgment documents;
step S3062, training the multiple expressions by adopting a machine training model to obtain public expression parts of the multiple expressions;
step S3064, a factor template is generated by using the common expression part as a common expression and combining the position of the entity corresponding to the factor feature.
Optionally, before the element template is obtained, the elements in the referee document need to be labeled, for example, entity extraction is performed on the determination points in the referee document. As shown in fig. 6, different elements are labeled with different styles of display frames. Note that the style of labeling the elements is not limited to labeling in the form of display frames of different styles, and may be labeled in different colors. In addition, elements to be labeled are included in the knowledge map, and mainly include legal terms, entity information (e.g., original information, notice information, etc.), and points of discriminant (e.g., "no material/additive is added in a limited amount" in fig. 6).
For example, the multiple expressions of the determination points in the predetermined number of referee documents include: the expression one: zhang III requires 30 Yuan of return money of Li IV; the expression II: the second requirement of wang is Zhao Wu returned money of 40 yuan; the expression three: xiao Yi requires a refund of 50 Yuan from Bai Liu, and so on. And training the multiple expressions by adopting a machine training model to obtain a public expression part of the multiple expressions: claim refund, the common expression part is the above-mentioned common expression. Wherein, the first is the position corresponding to the original entity, and the second is the position corresponding to the reported entity, therefore, the position of the entity corresponding to the common expression part combined with the element feature generates the element template: the original report requires the refund.
Therefore, after reading the element features (original name and advertised name) of the element from the case original text, the element features are combined with the element template to express the inference node.
It should be noted that the entity information needs to extract specific problems from the case text, the determination key points and the legal terms need to screen corresponding sentences from the case text, then perform tag processing on the sentences, and finally obtain the determination key points and the legal terms according to the processed tags.
In an alternative embodiment, after labeling elements in a large number of referee documents, the intelligent device obtains multiple expressions of each judgment point in a statistical manner, performs entity identification for each label (NER, method is not limited), then replaces entities (such as name of person, name of shop, amount of money, name of place, name of legal provision, and the like) in sentences with labels, and extracts multiple groups of common substrings and frequency of occurrence from the large number of expressions by using a longest common substring algorithm, and uses the common substring with the highest frequency as an element template of the judgment point.
It should be noted that, in the above process, the way of performing Entity identification on the tag may be, but is not limited to, NER (name and Entity Recognizer) method.
Further, after generating the text part of the official document, the intelligent device generates the official document at least according to the text part, and the specific method may include:
step S30, extracting an original appeal part and a defended answer part from the original appeal document and the defended answer document respectively by adopting an abstraction method;
and step S32, combining the original appeal part and the answered part according to the text part to generate a referee document.
In the scenarios defined in steps S30 to S32, the contents of the original essay document and the noticed-and-answered document are relatively specific, and therefore, the contents of the original essay document and the noticed-and-answered document are particularly important for cases with complex cases. The corresponding original appeal part and the corresponding defendant answer part in the referee document are the extraction of the contents of the original appeal document and the defendant answer document, so the referee document generated by combining the original appeal part and the defendant answer part contains the main contents of referee on the case according to the text part.
In an alternative scheme, the intelligent device firstly constructs an automatic abstract labeling data set, wherein the original instruction is called an example, the original input of the labeling data set is a prosecution book, and the output is the original instruction part of a referee document of a corresponding case. And then, the intelligent equipment trains the labeled data set to obtain an abstract extraction model. The abstract extraction model can adopt an extraction abstract method to respectively extract an original appeal part from an original appeal document and an informed answer part from an informed answer document, and can be but is not limited to a traditional classification model, a sequence model, a depth model, a two-classification model and the like.
Optionally, the extracting the original appeal part from the original appeal document and the extracting the defended answer part from the defended answer document respectively by using a method of extracting abstract includes:
step S302, an appeal abstract is extracted from the original appeal document and is used as an original appeal part, wherein the appeal abstract comprises the following steps: whole or clauses in the original appeal document;
step S304, extracting an answer abstract from the defended answer document, and taking the answer abstract as a defended answer part, wherein the answer abstract comprises the following steps: the quilt answer distinguishes the whole sentence or clause in the document.
Specifically, the intelligent device extracts the abstract in a binary classification model mode. When the input of the binary classification model is the original claim document, the binary classification model extracts the claim abstract according to the position of the element feature in the paragraph, whether the legal knowledge element is contained, the length of the sentence in which the element feature is contained, the number of contained entities, whether the amount of money is contained and the like. In the case that the input of the binary model is the noticed and answered document, the processing method of the binary model is similar to that of the original appeal document, and the detailed description is omitted here.
It should be noted that the two-classification model can output different abstract contents according to different case routes, and therefore the abstract extraction model can be trained according to different case routes to obtain different models.
In addition, the method of extracting the abstract is adopted to extract the key whole sentence or clause from the original text of the case to form the abstract, so that not only can key information be kept, but also the fluency of the abstract can be ensured, and the abstract is convenient to read and understand.
It should be noted that the official document also includes a home finding section, wherein the home finding section is divided into a non-dispute fact section and a dispute fact section. Since the composition of the non-dispute fact part is relatively fixed, the non-dispute fact part can be generated by adopting a templating method; the dispute fact part is similar to the text part, and the corresponding legal provision part is not required to be displayed only for the dispute fact part, so that the dispute fact part can be generated by adopting the same method as the text part.
Finally, fig. 7 shows a frame schematic diagram of the method for generating a referee document provided by the present application, and as can be seen from fig. 7, the method for generating a referee document mainly comprises the following six modules, wherein the knowledge graph construction module is used for constructing a knowledge graph; the element marking module is used for marking the knowledge elements in the referee document and providing data for the abstract extraction module; the abstract extraction module is used for describing the judged main points; the entity extraction module is used for extracting legal knowledge elements from the case original text; the key point identification module is used for identifying the dispute focus and the reasoning key point; and the referee document generation module is used for acquiring the description corresponding to the reasoning main point from the abstract extraction module, transmitting the description until all dispute focuses are accessed, and generating a text part.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method for generating the official document according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method of the embodiments of the present application.
Example 2
According to an embodiment of the present application, there is also provided an apparatus for generating a referee document for implementing the method for generating a referee document, as shown in fig. 8, the apparatus 80 including: an acquisition module 801, an extraction module 803, a first generation module 805, and a second generation module 807.
The acquiring module 801 is used for acquiring case original texts of referee documents to be generated; an extracting module 803, configured to extract element features of elements from the case original text; a first generating module 805, configured to generate a text part of the referee document according to a knowledge graph and the feature of the element, where the knowledge graph includes: elements, and relationships between elements; a second generating module 807 for generating the referee document based at least on the body part.
The feature of the element extracted from the case original text includes at least one of the following: extracting element characteristics of entity elements from the character expression of the case original text, wherein the entity elements are elements of which the element characteristics are directly expressed in the character expression of the case original text; extracting label elements from the text expression of the case original text, and classifying the label elements to obtain element characteristics of the label elements, wherein the element characteristics of the label elements are expressed in the case original text by adopting a preset classification algorithm.
Here, it should be further noted that the acquiring module 801, the extracting module 803, the first generating module 805, and the second generating module 807 correspond to steps S202 to S208 in embodiment 1, and the four modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as a part of the apparatus may be operated in the computer terminal a provided in the first embodiment.
In an alternative, the first generating module comprises: the device comprises an identification module, a third generation module and a fourth generation module. The identification module is used for identifying the dispute focus of the case; the third generation module is used for generating a path from the basic element of the case to a dispute focus according to the element characteristics and the relationship among the elements in the knowledge graph; and the fourth generation module is used for generating the text part of the referee document according to the path.
Here, it should be noted that the above-mentioned identification module, third generation module and fourth generation module correspond to steps S2060 to S2064 in embodiment 1, and the three modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure of the above-mentioned embodiment one. It should be noted that the modules described above as a part of the apparatus may be operated in the computer terminal a provided in the first embodiment.
In an optional aspect, the fourth generating module includes: the device comprises a determining module and a traversing module. The determination module is used for determining child nodes and inference nodes included in the path, wherein the child nodes include nodes with direct characters expressing feature characteristics in case original text, and the inference nodes include nodes which can cause the dispute focus to be not established; and the traversal module is used for traversing the nodes on the path, describing the nodes and obtaining the text part of the referee document.
In an alternative, the traversing module comprises: the device comprises a first processing module and a second processing module. The first processing module is used for describing the element characteristics of the child nodes expressed by the case original text under the condition that the nodes comprise the child nodes; and the second processing module is used for describing the reasoning nodes according to the element template under the condition that the nodes comprise the reasoning nodes, wherein the element template comprises: the common words of the referee document and the position of the entity corresponding to the feature.
In an alternative scheme, before describing the inference node according to the element template, the generation device of the referee document acquires the element template through the following modules: the device comprises a first acquisition module, a training module and a third processing module. The first acquisition module is used for acquiring various expressions of the judgment key points in a predetermined number of referee documents; the training module is used for training the multiple expressions by adopting a machine training model to obtain public expression parts of the multiple expressions; and the third processing module is used for taking the public expression part as a common expression and generating an element template by combining the position of the entity corresponding to the element feature.
Here, it should be noted that the first acquiring module, the training module, and the third processing module correspond to steps S3060 to S3064 in embodiment 1, and the three modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as a part of the apparatus may be operated in the computer terminal a provided in the first embodiment.
In an optional aspect, the second generating module includes: the device comprises a first extraction module and a fifth generation module. The first extraction module is used for extracting an original appeal part from an original appeal document and extracting a defended answer part from a defended answer document by adopting an extraction type abstract method; and the fifth generation module is used for generating the referee document by combining the original appeal part and the told-answer part according to the text part.
Here, it should be noted that the first extraction module and the fifth generation module correspond to steps S30 to S32 in embodiment 1, and the two modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as a part of the apparatus may be operated in the computer terminal a provided in the first embodiment.
In an alternative, the first extraction module comprises: a second extraction module and a third extraction module. The second extraction module is used for extracting the appeal abstract from the original appeal document and taking the appeal abstract as an original appeal part, wherein the appeal abstract comprises: whole or clauses in the original appeal document; the third extraction module is used for extracting the answer abstract from the defended answer document and taking the answer abstract as a defended answer part, wherein the answer abstract comprises: the quilt answer distinguishes the whole sentence or clause in the document.
Here, it should be noted that the second extraction module and the third extraction module correspond to steps S302 to S304 in embodiment 1, and the two modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure of the first embodiment. It should be noted that the modules described above as a part of the apparatus may be operated in the computer terminal a provided in the first embodiment.
Example 3
The embodiment of the application can provide a computer terminal, and the computer terminal can be any one computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced with a terminal device such as a mobile terminal.
Optionally, in this embodiment, the computer terminal may be located in at least one network device of a plurality of network devices of a computer network.
In this embodiment, the computer terminal may execute the program code of the following steps in the method for generating the official document of the application program: acquiring a case original text of a referee document to be generated; extracting element features of elements from the case original text; generating a text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following components: elements, and relationships between elements; and generating the referee document at least according to the text part.
Optionally, fig. 9 is a block diagram of a computer terminal according to an embodiment of the present application. As shown in fig. 9, the computer terminal 90 may include: one or more processors 902 (only one shown), a memory 904, and a transmitting device 906.
The memory may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for generating a referee document in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the method for generating a referee document described above is implemented. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, which may be connected to the terminal 90 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The processor can call the information and application program stored in the memory through the transmission device to execute the following steps: acquiring a case original text of a referee document to be generated; extracting element features of elements from the case original text; generating a text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following components: elements, and relationships between elements; and generating the referee document at least according to the text part. The element feature extracted from the case original text comprises at least one of the following features: extracting element characteristics of entity elements from the character expression of the case original text, wherein the entity elements are elements of which the element characteristics are directly expressed in the character expression of the case original text; extracting label elements from the text expression of the case original text, and classifying the label elements to obtain element characteristics of the label elements, wherein the element characteristics of the label elements are expressed in the case original text by adopting a preset classification algorithm.
Optionally, the processor may further execute the program code of the following steps: identifying a dispute focus of the case; generating a path from the basic elements of the case to a dispute focus according to the element characteristics and the relationship among the elements in the knowledge graph; and generating the text part of the referee document according to the path.
Optionally, the processor may further execute the program code of the following steps: determining child nodes and reasoning nodes which are included in the path, wherein the child nodes include nodes which express element characteristics by direct characters in case text, and the reasoning nodes include nodes which can cause the dispute focus to be not established; and traversing the nodes on the path, and describing the nodes to obtain the text part of the referee document.
Optionally, the processor may further execute the program code of the following steps: under the condition that the node comprises a child node, describing the feature characteristics of the child node expressed by the case original text; and describing the reasoning nodes according to element templates under the condition that the nodes comprise the reasoning nodes, wherein the element templates comprise: the common words of the referee document and the position of the entity corresponding to the feature.
Optionally, the processor may further execute the program code of the following steps: acquiring various expressions of the judgment key points in a predetermined number of judgment documents; training the multiple expressions by adopting a machine training model to obtain a public expression part of the multiple expressions; and taking the public expression part as a common expression, and generating an element template by combining the positions of the entities corresponding to the element characteristics.
Optionally, the processor may further execute the program code of the following steps: extracting an original appeal part and a defended answer part from an defended answer document respectively by adopting an extraction type abstract method; and generating a referee document by combining the original appeal part and the reported answer part according to the text part.
Optionally, the processor may further execute the program code of the following steps: extracting the appeal abstract from the original appeal document, and taking the appeal abstract as an original appeal part, wherein the appeal abstract comprises: whole or clauses in the original appeal document; extracting an answer abstract from the defended answer document and taking the answer abstract as a defended answer part, wherein the answer abstract comprises the following steps: the quilt answer distinguishes the whole sentence or clause in the document.
It can be understood by those skilled in the art that the structure shown in fig. 9 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 9 is a diagram illustrating a structure of the electronic device. For example, the computer terminal 90 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 9, or have a different configuration than shown in FIG. 9.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
Example 4
Embodiments of the present application also provide a storage medium. Optionally, in this embodiment, the storage medium may be configured to store the program code executed by the method for generating a referee document provided in the first embodiment.
Optionally, in this embodiment, the storage medium may be located in any one of computer terminals in a computer terminal group in a computer network, or in any one of mobile terminals in a mobile terminal group.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring a case original text of a referee document to be generated; extracting element features of elements from the case original text; generating a text part of the referee document according to the knowledge graph and the element characteristics, wherein the knowledge graph comprises the following components: elements, and relationships between elements; and generating the referee document at least according to the text part. Extracting the element features from the case original text comprises at least one of the following steps: extracting element characteristics of entity elements from the character expression of the case original text, wherein the entity elements are elements of which the element characteristics are directly expressed in the character expression of the case original text; extracting label elements from the text expression of the case original text, and classifying the label elements to obtain element characteristics of the label elements, wherein the element characteristics of the label elements are expressed in the case original text by adopting a preset classification algorithm.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: identifying a dispute focus of the case; generating a path from the basic elements of the case to a dispute focus according to the element characteristics and the relationship among the elements in the knowledge graph; and generating the text part of the referee document according to the path.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: determining child nodes and reasoning nodes which are included in the path, wherein the child nodes include nodes which express element characteristics by direct characters in case text, and the reasoning nodes include nodes which can cause the dispute focus to be not established; and traversing the nodes on the path, and describing the nodes to obtain the text part of the referee document.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: under the condition that the node comprises a child node, describing the feature characteristics of the child node expressed by the case original text; and describing the reasoning nodes according to element templates under the condition that the nodes comprise the reasoning nodes, wherein the element templates comprise: the common words of the referee document and the position of the entity corresponding to the feature.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring various expressions of the judgment key points in a predetermined number of judgment documents; training the multiple expressions by adopting a machine training model to obtain a public expression part of the multiple expressions; and taking the public expression part as a common expression, and generating an element template by combining the positions of the entities corresponding to the element characteristics.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: extracting an original appeal part and a defended answer part from an defended answer document respectively by adopting an extraction type abstract method; and generating a referee document by combining the original appeal part and the reported answer part according to the text part.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: extracting the appeal abstract from the original appeal document, and taking the appeal abstract as an original appeal part, wherein the appeal abstract comprises: whole or clauses in the original appeal document; extracting an answer abstract from the defended answer document and taking the answer abstract as a defended answer part, wherein the answer abstract comprises the following steps: the quilt answer distinguishes the whole sentence or clause in the document.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in 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 application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (10)
1. A method for generating a referee document, comprising:
acquiring a case original text of a referee document to be generated;
extracting element features of elements from the case original text;
generating a text part of the referee document according to a knowledge graph and the element characteristics, wherein the knowledge graph comprises: elements, and relationships between elements;
and generating the referee document at least according to the text part.
2. The method of claim 1, wherein generating the body part of the official document based on the knowledge-graph and the element features comprises:
identifying a dispute focus of the case;
generating a path from the basic element of the case to the dispute focus according to the element characteristics and the relationship between the elements in the knowledge graph;
and generating the text part of the referee document according to the path.
3. The method of claim 2, wherein generating the body part of the official document according to the path comprises:
determining child nodes and inference nodes included in the path, wherein the child nodes include nodes of direct word expression element features in the case text, and the inference nodes include nodes which can cause the dispute focus to be out of place;
and traversing the nodes on the path, and describing the nodes to obtain the text part of the referee document.
4. The method of claim 3, wherein traversing nodes on the path to describe the nodes to obtain the body part of the official document comprises:
under the condition that the node comprises a child node, describing the element characteristics of the child node expressed by the case original text;
describing the inference node according to an element template in the case that the node includes the inference node, wherein the element template includes: the common words of the referee document and the position of the entity corresponding to the feature.
5. The method of claim 4, prior to describing the inference node according to an element template, further comprising: acquiring the element template by the following method:
acquiring various expressions of the judgment key points in a predetermined number of judgment documents;
training the multiple expressions by adopting a machine training model to obtain a common expression part of the multiple expressions;
and taking the public expression part as the common expression, and generating the element template by combining the positions of the entities corresponding to the element characteristics.
6. The method according to claim 1, wherein the feature characteristics of the extracted elements from the case text comprise at least one of:
extracting element features of entity elements from the text expression of the case original text, wherein the entity elements are elements of which the element features are directly expressed in the text expression of the case original text;
extracting label elements from the text expression of the case original text, and classifying the label elements to obtain element features of the label elements, wherein the element features of the label elements are expressed in the case original text by adopting a preset classification algorithm.
7. The method of claim 1, wherein generating the official document based on at least the body part comprises:
extracting an original appeal part and a defended answer part from an defended answer document respectively by adopting an extraction type abstract method;
and generating the referee document by combining the original appeal part and the reported answer part according to the text part.
8. The method of claim 7, wherein extracting the prosecution portion from the prosecution document and the defended response portion from the defended response document respectively using a abstract method comprises:
extracting an appeal abstract from the original appeal document, and taking the appeal abstract as the original appeal part, wherein the appeal abstract comprises: the whole sentence or the clause in the original appeal document;
extracting an answer abstract from the said defended answer document and using the said answer abstract as the said defended answer part, wherein the said answer abstract includes: the said quilt answer debates the whole or sub-sentence in the document.
9. An apparatus for generating a referee document, comprising:
the acquiring module is used for acquiring case original texts of the official documents to be generated;
the extraction module is used for extracting element features of elements from the case original text;
a first generation module, configured to generate a text part of the referee document according to a knowledge graph and the element features, where the knowledge graph includes: elements, and relationships between elements;
and the second generation module is used for generating the referee document at least according to the text part.
10. A storage medium, characterized in that it stores a computer program, wherein the computer program realizes the generation method of a referee document according to any one of claims 1 to 8 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810664228.9A CN110633458A (en) | 2018-06-25 | 2018-06-25 | Method and device for generating referee document |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810664228.9A CN110633458A (en) | 2018-06-25 | 2018-06-25 | Method and device for generating referee document |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110633458A true CN110633458A (en) | 2019-12-31 |
Family
ID=68968706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810664228.9A Pending CN110633458A (en) | 2018-06-25 | 2018-06-25 | Method and device for generating referee document |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110633458A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781254A (en) * | 2020-01-02 | 2020-02-11 | 四川大学 | Automatic case knowledge graph construction method, system, equipment and medium |
| CN110781650A (en) * | 2020-01-02 | 2020-02-11 | 四川大学 | Method and system for automatically generating referee document based on deep learning |
| CN111694931A (en) * | 2020-06-11 | 2020-09-22 | 北京百度网讯科技有限公司 | Element acquisition method and device |
| CN111753538A (en) * | 2020-06-12 | 2020-10-09 | 鼎富智能科技有限公司 | Method and device for extracting document elements of divorce dispute referee |
| CN111753025A (en) * | 2020-06-24 | 2020-10-09 | 南方科技大学 | Automatic case information acquisition method, device, equipment and storage medium |
| CN112950414A (en) * | 2021-02-25 | 2021-06-11 | 华东师范大学 | Legal text representation method based on decoupling legal elements |
| CN113222251A (en) * | 2021-05-13 | 2021-08-06 | 太极计算机股份有限公司 | Case dispute focus-based auxiliary judgment result prediction method and system |
| CN113254651A (en) * | 2021-06-28 | 2021-08-13 | 人民法院信息技术服务中心 | Method and device for analyzing referee document, computer equipment and storage medium |
| TWI757767B (en) * | 2020-06-16 | 2022-03-11 | 國立政治大學 | Method for generating abstract of written judgment automatically |
| CN116127977A (en) * | 2023-02-08 | 2023-05-16 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
| CN116484010A (en) * | 2023-03-15 | 2023-07-25 | 北京擎盾信息科技有限公司 | Knowledge graph construction method and device, storage medium and electronic device |
| CN117273008A (en) * | 2023-08-30 | 2023-12-22 | 北京华夏电通科技股份有限公司 | Referee document generation method and device and electronic equipment |
| CN117763156A (en) * | 2023-11-24 | 2024-03-26 | 上海歆广数据科技有限公司 | Dynamic holographic individual case management system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030236679A1 (en) * | 2002-04-23 | 2003-12-25 | Galves Fred A. | On-line dispute resolution for e-commerce disputes |
| CN106815203A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | A kind of amount of money analysis method and device in judgement document |
| CN106886572A (en) * | 2017-01-18 | 2017-06-23 | 中国人民解放军信息工程大学 | Knowledge mapping relationship type estimation method and its device based on Markov Logic Networks |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
-
2018
- 2018-06-25 CN CN201810664228.9A patent/CN110633458A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030236679A1 (en) * | 2002-04-23 | 2003-12-25 | Galves Fred A. | On-line dispute resolution for e-commerce disputes |
| CN106815203A (en) * | 2015-12-01 | 2017-06-09 | 北京国双科技有限公司 | A kind of amount of money analysis method and device in judgement document |
| CN106886572A (en) * | 2017-01-18 | 2017-06-23 | 中国人民解放军信息工程大学 | Knowledge mapping relationship type estimation method and its device based on Markov Logic Networks |
| CN108038091A (en) * | 2017-10-30 | 2018-05-15 | 上海思贤信息技术股份有限公司 | A kind of similar calculating of judgement document's case based on figure and search method and system |
| CN108009299A (en) * | 2017-12-28 | 2018-05-08 | 北京市律典通科技有限公司 | Law tries method and device for business processing |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781650A (en) * | 2020-01-02 | 2020-02-11 | 四川大学 | Method and system for automatically generating referee document based on deep learning |
| CN110781650B (en) * | 2020-01-02 | 2020-04-14 | 四川大学 | Method and system for automatically generating referee document based on deep learning |
| CN110781254A (en) * | 2020-01-02 | 2020-02-11 | 四川大学 | Automatic case knowledge graph construction method, system, equipment and medium |
| CN111694931A (en) * | 2020-06-11 | 2020-09-22 | 北京百度网讯科技有限公司 | Element acquisition method and device |
| CN111753538A (en) * | 2020-06-12 | 2020-10-09 | 鼎富智能科技有限公司 | Method and device for extracting document elements of divorce dispute referee |
| TWI757767B (en) * | 2020-06-16 | 2022-03-11 | 國立政治大學 | Method for generating abstract of written judgment automatically |
| CN111753025A (en) * | 2020-06-24 | 2020-10-09 | 南方科技大学 | Automatic case information acquisition method, device, equipment and storage medium |
| CN111753025B (en) * | 2020-06-24 | 2024-06-14 | 南方科技大学 | Automatic case information acquisition method, device, equipment and storage medium |
| CN112950414B (en) * | 2021-02-25 | 2023-04-18 | 华东师范大学 | Legal text representation method based on decoupling legal elements |
| CN112950414A (en) * | 2021-02-25 | 2021-06-11 | 华东师范大学 | Legal text representation method based on decoupling legal elements |
| CN113222251A (en) * | 2021-05-13 | 2021-08-06 | 太极计算机股份有限公司 | Case dispute focus-based auxiliary judgment result prediction method and system |
| CN113254651A (en) * | 2021-06-28 | 2021-08-13 | 人民法院信息技术服务中心 | Method and device for analyzing referee document, computer equipment and storage medium |
| CN116127977A (en) * | 2023-02-08 | 2023-05-16 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
| CN116127977B (en) * | 2023-02-08 | 2023-10-03 | 中国司法大数据研究院有限公司 | Casualties extraction method for referee document |
| CN116484010A (en) * | 2023-03-15 | 2023-07-25 | 北京擎盾信息科技有限公司 | Knowledge graph construction method and device, storage medium and electronic device |
| CN116484010B (en) * | 2023-03-15 | 2024-01-16 | 北京擎盾信息科技有限公司 | Knowledge graph construction method and device, storage medium and electronic device |
| CN117273008A (en) * | 2023-08-30 | 2023-12-22 | 北京华夏电通科技股份有限公司 | Referee document generation method and device and electronic equipment |
| CN117273008B (en) * | 2023-08-30 | 2024-06-04 | 北京华夏电通科技股份有限公司 | Referee document generation method and device and electronic equipment |
| CN117763156A (en) * | 2023-11-24 | 2024-03-26 | 上海歆广数据科技有限公司 | Dynamic holographic individual case management system |
| CN117763156B (en) * | 2023-11-24 | 2024-05-07 | 上海歆广数据科技有限公司 | Dynamic holographic individual case management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110633458A (en) | Method and device for generating referee document | |
| CN108319888B (en) | Video type identification method and device and computer terminal | |
| CN109086420B (en) | Method, device and storage medium for selecting reading material | |
| CN108920675A (en) | A kind of method, apparatus of information processing, computer storage medium and terminal | |
| CN114170468B (en) | Text recognition method, storage medium and computer terminal | |
| CN110858353B (en) | Method and system for obtaining case judge result | |
| CN110717312B (en) | Text labeling method and device | |
| KR101127646B1 (en) | A study book using readable identification code and method for feedback study | |
| CN111274813B (en) | Language sequence labeling method, device storage medium and computer equipment | |
| CN110647504B (en) | Method and device for searching judicial documents | |
| CN112527963B (en) | Dictionary-based multi-label emotion classification method and device, equipment and storage medium | |
| CN114564938A (en) | Document parsing method and device, storage medium and processor | |
| CN110147358B (en) | Construction method and construction system of automatic question-answering knowledge base | |
| CN116071769A (en) | Table identification method, apparatus, nonvolatile storage medium and computer device | |
| CN114385776A (en) | Information positioning method, storage medium and device | |
| CN115861606A (en) | Method and device for classifying long-tail distribution documents and storage medium | |
| CN113377980A (en) | Information labeling method and device, electronic equipment and storage medium | |
| CN111723164B (en) | Address information processing method and device | |
| CN110956034B (en) | Word acquisition method and device and commodity search method | |
| CN113779934A (en) | Multi-modal information extraction method, device, equipment and computer-readable storage medium | |
| CN113011182A (en) | Method, device and storage medium for labeling target object | |
| CN110728138A (en) | News text recognition method and device and storage medium | |
| CN109710852A (en) | It is a kind of for determining the method and apparatus of the label information of financial information | |
| CN114565444A (en) | Object classification method, storage medium and computer terminal | |
| CN115719255A (en) | Method, device and storage medium for generating file |
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: 20191231 |