WO2018224028A1 - 获取裁判文书焦点的方法和装置 - Google Patents

获取裁判文书焦点的方法和装置 Download PDF

Info

Publication number
WO2018224028A1
WO2018224028A1 PCT/CN2018/090354 CN2018090354W WO2018224028A1 WO 2018224028 A1 WO2018224028 A1 WO 2018224028A1 CN 2018090354 W CN2018090354 W CN 2018090354W WO 2018224028 A1 WO2018224028 A1 WO 2018224028A1
Authority
WO
WIPO (PCT)
Prior art keywords
focus
document
rule engine
referee document
preset
Prior art date
Application number
PCT/CN2018/090354
Other languages
English (en)
French (fr)
Inventor
舒怡
周冰洁
杨天泰
贾炜
陈飞
Original Assignee
北京国双科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京国双科技有限公司 filed Critical 北京国双科技有限公司
Publication of WO2018224028A1 publication Critical patent/WO2018224028A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor

Definitions

  • the present invention relates to the field of data processing, and in particular to a method and apparatus for acquiring focus of a referee.
  • the methods for obtaining the judgment documents generally have the following two types: 1) according to the degree of standardization of the judgment documents, the legal experts summarize the regular expressions of the basic dimensions such as the case, the case number, the trial court, the parties, and the applicable law. Then, the machine extracts such data according to the given rule; 2) the legal expert marks the judgment document, then puts the document into the judgment document library, and the machine matches the keyword through the string matching. Joint laws and regulations, typical cases, judgment documents, etc.
  • the first method can read the data in the judgment documents, it is limited to the basic types of data that are regularly ruled and have a single expression, such as the case, the case number, the trial court, etc., and it is impossible to recognize that the legal practitioners really care.
  • the embodiment of the invention provides a method and a device for acquiring the focus of the refereeing document, so as to at least solve the focus of obtaining the refereeing document by using the artificially labeled keyword in the prior art, and the focus of the obtained refereeing document is subjective, resulting in acquisition.
  • a method including: acquiring a preset focus rule engine, wherein a focus rule engine is constructed according to a first referee document that has determined focus; and obtaining, by a focus rule engine, a target referee document Focus.
  • an apparatus for acquiring a focus of a refereeing document including: a first acquiring module, configured to acquire a preset focus rule engine, wherein the focus rule engine is based on the determined focus A referee document is constructed; the second obtaining module is configured to obtain a focus belonging to the target refereeing document by the focus rule engine.
  • a storage medium comprising a stored program, wherein the device in which the storage medium is located controls the method of acquiring the focus of the referee document when the program is running.
  • a processor configured to execute a program, wherein the method of acquiring the focus of the refereeing document is performed while the program is running.
  • the focus rule engine is constructed according to the first referee document that has determined the focus, and the focus of the target referee document is acquired by the focus rule engine.
  • the above solution obtains the focus rule engine from the first referee document with the determined focus, and then determines the focus of the target referee document to be determined by the focus rule engine, and solves the focus of obtaining the referee document by the artificial mark keyword in the prior art.
  • the focus of the obtained refereeing documents is subjective, resulting in a technical problem of low focus accuracy of the obtained refereeing documents, and improving the technical effect of determining the efficiency of the focus of the refereeing documents.
  • FIG. 1 is a flow chart of a method of acquiring a focus of a refereeing document according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of an alternative method of acquiring a focus of a refereeing document according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of an apparatus for acquiring a focus of a refereeing document according to an embodiment of the present invention.
  • Judgment documents used to record the process and results of the court hearings, is the carrier of the outcome of the litigation activities, and the only evidence that the people's courts determine and assign the rights and obligations of the parties.
  • Focus the focus of controversy, simply the core of the dispute, the contradictory confrontation point, the problem of disputes between the parties in the case, the form is the point of judgment by the judge and confirmed by the parties, is to lead the case trial, dispute resolution
  • the main line and the hub are also a prominent sign that reflects the extent to which the judge is familiar with the case and grasps the ability of the law to connect with the case.
  • an embodiment of a method of obtaining a focus of a refereeing document is provided, and it is noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer executable instructions, and Although the logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than the ones described herein.
  • FIG. 1 is a flow chart of a method for acquiring a focus of a refereeing document according to an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:
  • Step S102 Acquire a preset focus rule engine, wherein the focus rule engine is constructed according to the first referee document that has determined the focus.
  • the first referee document with the determined focus can be obtained from the preset document library. Since the first referee document has determined the focus, the first referee document of the determined focus can be obtained directly. The focus of a referee's paperwork.
  • step S104 the focus of the target judgment document is acquired by the focus rule engine.
  • the above-mentioned target judgment document is a judgment document to be determined.
  • the target referee document can be input to the focus rule engine described above, and the focus rule engine can output the focus of the target referee document.
  • the focus rule engine can also be updated according to a preset period to maintain the timeliness of the focus rule engine.
  • the above embodiment of the present application constructs a focus rule engine according to the first referee document that has determined the focus, and acquires the focus of the target referee document by the focus rule engine.
  • the above solution obtains the focus rule engine from the first referee document with the determined focus, and then determines the focus of the target referee document to be determined by the focus rule engine, and solves the focus of obtaining the referee document by the artificial mark keyword in the prior art.
  • the focus of the obtained refereeing documents is subjective, resulting in a technical problem of low focus accuracy of the obtained refereeing documents, and improving the technical effect of determining the efficiency of the focus of the refereeing documents.
  • the focus rule engine is constructed according to the first referee document that has determined the focus, including:
  • Step S1021 Acquire a first referee document corresponding to the preset domain.
  • the above preset field is the field of the focused focus rule engine.
  • the focus rule engine when the focus rule engine is constructed as an example of trademark infringement, the first referee document used to construct the focus rule engine should belong to the field of trademark infringement.
  • an instrument entitled "Disruption of trademark rights disputes" can be extracted from the document library as the first judgment document in the field.
  • Step S1023 Acquire focus information corresponding to the focus in the first referee document.
  • the above focus information may include a paragraph in which the focus appears, a specific line position in the paragraph where the focus is located, and a sentence pattern in which the focus appears.
  • Step S1025 Construct a rule engine corresponding to the preset domain according to the focus information in the first referee document and the focus information corresponding to the focus in the first referee document.
  • the focus rule engine may be obtained by learning the first referee document, for example, the focus of the first referee document and the first referee document may be input to a preset initialized focus.
  • the focus rule engine is trained until any one of the first referee documents is input to the focus rule engine, and the focus rule engine can output the same focus as the determined focus result.
  • the foregoing embodiment of the present application constructs a focus rule engine corresponding to the domain according to the first referee document of a certain domain, so that the result of the focus rule engine finding the focus is more accurate.
  • the method in order to facilitate learning and training in the process of constructing the focus rule engine, and conveniently outputting the result in the use process of the focus rule engine, the method may be The focus content is displayed, so after obtaining the first referee document corresponding to the preset field, the above method may further include the following steps:
  • step S1027 the focus of the first referee document corresponding to the preset domain is extracted, and the focus library corresponding to the preset domain is formed.
  • step S1029 the focus in the focus library is classified according to a preset dimension.
  • the preset dimension may be a focus class corresponding to the preset domain.
  • the trademark infringement field is still taken as an example.
  • the above-mentioned preset dimensions may be the five focus categories obtained by combing the judge's thinking mode: (1) trademark type; (2) behavior pattern (3) Defense; (4) Tort liability; (5) Other focus.
  • trademark type well-known trademark, commodity trademark, service trademark, certification trademark, collective trademark, three-dimensional trademark, sound trademark, three-dimensional trademark, geographical indication
  • Behavior patterns trademark counterfeiting/counterfeiting, sales of goods that infringe the exclusive right of registered trademarks, trademark-assisted infringements, corporate name violations of others' registered trademarks, domain name infringement of others' registered trademarks, infringement of well-known trademarks, other infringements
  • Defense prior rights and reasonable use, whether there are legal sources/legitimate channels, whether the registered trademarks are not actually used, trademark co-owners/shared trademarks
  • Tort liability stop infringement/stop sales/destruction (5)
  • Other focus Whether the subject is suitable, whether it exceeds the statute of limitations, whether it constitutes trademark use, administrative punishment/criminal judgment, or whether it constitutes unfair competition.
  • the steps of the above classification are not limited to one or more times, and in the case that a certain case type has multiple branches or multiple deformation modes, the classification may be continued on one or more classifications. Classification until it is possible to categorize the focus of the case directly.
  • Step S1031 encoding according to the category to which the focus in the focus library belongs, and obtaining an identifier corresponding to each focus.
  • the above-mentioned five categories of focus categories (1) trademark types, (2) behavior patterns, (3) defense reasons, and (4) tort liability and (5)
  • the other focus codes are respectively A, B, C, D, and E.
  • the focus corresponding to the focus class can be used to represent the focus.
  • the above five categories of focus can be further classified, with class A focus
  • trademark types include: well-known trademarks, commodity trademarks, service trademarks, certification trademarks, collective trademarks, three-dimensional trademarks
  • sound trademarks, three-dimensional logos and geographical indications, and sub-categories of category A focus can also be coded, for example, well-known trademarks, commodity trademarks, service trademarks, certification trademarks, collective trademarks, three-dimensional trademarks, sound trademarks, Three-dimensional logo trademarks and geographical indications can be encoded as A1, A2, A3, A4, A5, A6, A7, A8, and A9, respectively.
  • Other focus classes can also continue to be categorized and coded according to the above rules.
  • the coding mode in the foregoing embodiment is only used as an example, and the identification manner in which the correspondence between the focus and the identifier can be established can be used in the above solution.
  • acquiring the first referee document corresponding to the preset domain including:
  • step S1021a a plurality of second referee documents are acquired.
  • the above second judgment instrument may be all the documents in the library.
  • Step S1021b determining the field to which the second referee document belongs according to the case of the second referee document.
  • step S1021c the second referee document belonging to the preset field is used as the first referee document corresponding to the preset field.
  • the above solution of the present application determines the field of the judgment document according to the case in the judgment document, and does not need to manually determine each judgment document in order, which greatly improves the efficiency of obtaining the first judgment document in the preset field.
  • the focus information includes: a focus position and a focus attribute
  • the focus of the target judgment document is obtained by the focus rule engine, including:
  • step S1041 each focus position is sequentially searched for in the target judgment document.
  • the above focus position may include a paragraph in which the focus is located, and a line position in the paragraph, and further, may include a specific character position in the line position.
  • the focus attribute may include a sentence pattern in which the focus appears, a keyword used to represent the focus, and the like.
  • step S1043 if the attribute of the content corresponding to the focus position is the same as the focus attribute corresponding to the focus indicated by the focus position, it is determined that the content corresponding to the focus position in the target referee document is the focus.
  • the focus position corresponding to the focus A1 is the first line of the [0028] paragraph in the first referee document, and its attribute is after the phrase "explained and found".
  • the focus rule engine After inputting the target referee document to the focus rule engine, the focus rule engine searches for the [0028] paragraph in the target judgment document, and if the phrase "argumented for trial" is found, it is confirmed that the target judgment document has A1 focus.
  • the method further includes: forming a focus sequence according to the identifier corresponding to all the focus points in the target referee document;
  • the identifiers corresponding to each focus may be sorted according to the order in which the focus appears, thereby obtaining a focus sequence; outputting the focus sequence, and outputting the focus of the target referee document according to the focus content corresponding to each focus in the focus sequence. content.
  • the focus In the process of generating the focus identifier, the focus is in one-to-one correspondence with the focus content. Therefore, after the focus content of the target judgment document is acquired, the focus content of the target judgment document can be determined according to the correspondence relationship between the focus and the focus sequence.
  • each focus in the focus sequence represents a very specific focus type of the preset field.
  • the referee document processed by the focus rule engine can directly read out the focus sequence, and obtain the corresponding focus content according to each focus code in the focus sequence.
  • FIG. 2 is a schematic diagram of an optional method for acquiring the focus of a refereeing document according to an embodiment of the present application. As shown in FIG. 2, the example in FIG. 2 is described in two steps.
  • Step 1 Obtain a focus library from the referee library, and generate a focus rule engine according to the focus information corresponding to each focus in the focus library.
  • the foregoing referee document library is a library of referee documents composed of the first referee document that has determined the focus, and the step is a preparatory work at the initial stage, and is not a focus fixing step of obtaining the target referee document each time through the focus rule engine;
  • Step two the step includes: a, inputting a target referee document to the focus rule engine; b, the focus rule engine outputs a focus sequence of the target referee document.
  • This step is the focus step of obtaining the target referee document each time through the focus rule engine.
  • FIG. 3 is a schematic diagram of an apparatus for acquiring a focus of a refereeing document according to an embodiment of the present invention. As shown in FIG. 3, the apparatus includes:
  • the first obtaining module 30 is configured to acquire a preset focus rule engine, wherein the focus rule engine is constructed according to the first referee document that has determined the focus.
  • the first referee document with the determined focus can be obtained from the preset document library. Since the first referee document has determined the focus, the first referee document of the determined focus can be obtained directly. The focus of a referee's paperwork.
  • the second obtaining module 32 is configured to acquire a focus belonging to the target referee document by the focus rule engine.
  • the above-mentioned target judgment document is a judgment document to be determined.
  • the target referee document can be input to the focus rule engine described above, and the focus rule engine can output the focus of the target referee document.
  • the focus rule engine can also be updated according to a preset period to maintain the timeliness of the focus rule engine.
  • the first embodiment of the present application uses the first acquisition module to construct a focus rule engine according to the first referee document that has determined the focus, and uses the second acquisition module to acquire the focus of the target referee document through the focus rule engine.
  • the above solution obtains the focus rule engine from the first referee document with the determined focus, and then determines the focus of the target referee document to be determined by the focus rule engine, and solves the focus of obtaining the referee document by the artificial mark keyword in the prior art.
  • the focus of the obtained refereeing documents is subjective, resulting in a technical problem of low focus accuracy of the obtained refereeing documents, and improving the technical effect of determining the efficiency of the focus of the refereeing documents.
  • the foregoing first obtaining module 30 and the second obtaining module 32 may be run in a computer terminal as part of the device, and the functions implemented by the foregoing module may be performed by a processor in the computer terminal, and the computer terminal may also be It is a smart phone (such as Android phone, iOS phone, etc.), tablet computer, applause computer, and mobile Internet devices (MID), PAD and other terminal devices.
  • the apparatus further includes: a building module, configured to construct a focus rule engine according to the first referee document that has determined the focus before acquiring the preset focus rule engine.
  • the building module includes:
  • the first obtaining submodule is configured to acquire a first referee document corresponding to the preset domain.
  • the second obtaining submodule is configured to acquire focus information corresponding to a focus in the first referee document.
  • the construction submodule is configured to construct a focus rule engine corresponding to the preset domain according to the focus information in the first referee document and the focus information corresponding to the focus in the first referee document.
  • the device further includes:
  • the extracting module is configured to extract the focus of the first refereeing document library corresponding to the preset domain after acquiring the refereeing document library corresponding to the preset domain, and constitute a focus library corresponding to the preset domain.
  • a classification module set to classify the focus in the focus library according to a preset dimension.
  • the encoding module is set to encode according to the category to which the focus in the focus library belongs, and obtain an identifier corresponding to each focus.
  • the focus information includes: a focus position and a focus attribute
  • the second obtaining module includes:
  • the determining sub-module is configured to determine that the content corresponding to the focus position in the target referee document is the focus if the attribute of the content corresponding to the focus position is the same as the focus attribute corresponding to the focus indicated by the focus position.
  • the device further includes:
  • a building module configured to form a focus sequence according to the identifier corresponding to all the focus points in the target refereeing document after acquiring the focus belonging to the target refereeing document by the focus rule engine;
  • the output module is configured to output a focus sequence, and output the focus content of the target referee document according to the focus content corresponding to each focus in the focus sequence.
  • the various functional units provided by the embodiments of the present application may be operated in a mobile terminal, a computer terminal, or the like, or may be stored as part of a storage medium.
  • embodiments of the present invention may provide a computer terminal, which may be any computer terminal device in a group of computer terminals.
  • a computer terminal may also be replaced with a terminal device such as a mobile terminal.
  • the computer terminal may be located in at least one network device of the plurality of network devices of the computer network.
  • the computer terminal may execute the program code of the following steps in the method for acquiring the focus of the referee: acquiring a preset focus rule engine, wherein the focus rule engine is constructed according to the first referee document that has determined the focus;
  • the rules engine captures the focus of the target refereeing instrument.
  • the computer terminal can include: one or more processors, memory, and transmission means.
  • the memory can be used to store the software program and the module, such as the method for acquiring the focus of the referee and the program instruction/module corresponding to the device in the embodiment of the present invention, and the processor executes the software program and the module stored in the memory, thereby executing each A functional application and data processing, that is, the method of obtaining the focus of the refereeing instrument described above.
  • the memory may include a 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.
  • the memory can further include memory remotely located relative to the processor, which can be connected to the terminal over 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 above transmission device is for receiving or transmitting data via a network.
  • Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device is a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory is used to store preset action conditions and information of the preset rights user, and an application.
  • the processor can call the memory stored information and the application by the transmitting device to execute the program code of the method steps of each of the alternative or preferred embodiments of the above method embodiments.
  • the computer terminal can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, an applause computer, and a mobile Internet device (MID), a PAD, and the like.
  • a smart phone such as an Android phone, an iOS phone, etc.
  • a tablet computer such as an iPad, Samsung Galaxy Tab, Samsung Galaxy Tab, etc.
  • MID mobile Internet device
  • PAD PAD
  • the embodiment of the present application provides a storage medium on which a program is stored, and when the program is executed by the processor, the method for acquiring the focus of the referee is implemented.
  • the foregoing storage medium may be located in any one of the computer terminal groups in the computer network, or in any one of the mobile terminal groups.
  • the storage medium is configured to store program code for performing the step of: acquiring a preset focus rule engine, wherein the focus rule engine is constructed according to the first referee document that has determined the focus;
  • the focus rule engine captures the focus of the target refereeing instrument.
  • the storage medium may also be set as program code of various preferred or optional method steps provided by the method of obtaining the focus of the referee.
  • the embodiment of the invention provides a processor for running a program, wherein the method for acquiring the focus of the refereeing document is executed when the program is running.
  • the embodiment of the present invention provides a device, which includes a processor, a memory, and a program stored on the memory and operable on the processor.
  • the processor executes the program, the following steps are performed: acquiring a preset focus rule engine, where The focus rule engine is constructed according to the first referee document that has determined the focus; the focus of the target referee document is obtained by the focus rule engine.
  • the devices in this document can be servers, PCs, PADs, mobile phones, and the like.
  • the device for acquiring the focus of the refereeing document comprises a processor and a memory, wherein the first acquiring module and the second obtaining module are stored in the memory as a program unit, and the processor executes the program unit stored in the memory to implement a corresponding function.
  • the processor contains a kernel, and the kernel removes the corresponding program unit from the memory.
  • the kernel can be set to one or more.
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one Memory chip.
  • RAM random access memory
  • ROM read only memory
  • flash RAM flash memory
  • the present application also provides an embodiment of a computer program product, when executed on a data processing device, adapted to perform program code initialization with the following method steps: acquiring a preset focus rule engine, wherein the focus rule engine is based on Determining the focus of the first referee document construction; obtaining the focus of the target referee document through the focus rule engine.
  • the computer program When executed on the data processing device, the computer program is further adapted to perform a process of initializing the following method steps: acquiring a first referee file corresponding to the preset field; acquiring focus information corresponding to the focus in the first referee document; Focus information in a referee document and focus information corresponding to the focus construct a focus rule engine corresponding to the preset field.
  • the computer program When executed on the data processing device, the computer program is further adapted to perform a process of initializing the method steps of: extracting a focus of the first referee document corresponding to the preset domain, and forming a focus library corresponding to the preset domain; The focus is classified according to the preset dimensions; the encoding is performed according to the category to which the focus in the focus library belongs, and the identifier corresponding to each focus is obtained.
  • the computer program When executed on a data processing device, the computer program is further adapted to perform a process of initializing the method steps: the focus information includes: a focus position and a focus attribute, and each focus position is sequentially searched in the target referee document; if the focus position corresponds The attribute of the content is the same as the focus attribute corresponding to the focus indicated by the focus position, and then the content corresponding to the focus position in the target referee document is determined to be the focus.
  • the computer program When executed on a data processing device, the computer program is further adapted to perform a process of initializing a method of constructing a focus sequence according to the identifiers corresponding to all the focus points in the target referee document; outputting the focus sequence, and according to each of the focus sequences The focus content corresponding to the focus, and the focus content of the target judgment document is output.
  • the disclosed technical contents may be implemented in other manners.
  • the device embodiments described above are only schematic.
  • the division of the unit may be a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the 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 standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本发明公开了一种获取裁判文书焦点的方法和装置。其中，该方法包括：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。本发明解决了现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题。

Description

获取裁判文书焦点的方法和装置 技术领域
本发明涉及数据处理领域，具体而言，涉及一种获取裁判文书焦点的方法和装置。
背景技术
在现有技术中，获取裁判文书的方法通常有如下两种：1)根据裁判文书的规范化程度，由法律专家总结出案由、案号、审理法院、当事人、适用法条等基础维度的正则表达式，然后，机器按照该给定规则提取此类数据；2)由法律专家对裁判文书进行关键词标记，然后将该文书放入裁判文书库，机器通过字符串匹配，找到与该关键词相关联的法律法规、典型案例、裁判文书等。
第一种方法虽然能够读取出裁判文书中的数据，但是限于有规律可循的、表述方式较为单一的基础类数据，如案由、案号、审理法院等，无法识别出法律从业人员真正关心的裁判文书的焦点。
第二种方法虽然是对裁判文书的争议焦点进行关键词匹配，但是存在以下几个缺陷：1)需要法律专家对每一篇裁判文书均进行入库前关键词标记，只要出现一篇新的文书，即需要标记一次关键词；2)由于每个人专业水平、素养的不一致，对同一篇裁判文书可能标记出完全不同的关键词，主观性较强；3)依靠每篇文书2-3个关键词的标记，并不能精确判断文书的焦点。
针对现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的问题，目前尚未提出有效的解决方案。
发明内容
本发明实施例提供了一种获取裁判文书焦点的方法和装置，以至少解决现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题。
根据本发明实施例的一个方面，提供了一种方法，包括：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。
根据本发明实施例的另一方面，还提供了一种获取裁判文书焦点的装置，包括： 第一获取模块，设置为获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；第二获取模块，设置为通过焦点规则引擎获取属于目标裁判文书的焦点。
根据本发明实施例的另一方面，还提供了一种存储介质，包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述获取裁判文书焦点的方法。
根据本发明实施例的另一方面，还提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述获取裁判文书焦点的方法。
在本发明实施例中，根据已确定焦点的第一裁判文书构建焦点规则引擎，通过焦点规则引擎获取属于目标裁判文书的焦点。上述方案由已确定焦点的第一裁判文书得到焦点规则引擎，再通过焦点规则引擎来确定待确定焦点的目标裁判文书的焦点，解决了现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题，并且提高了确定裁判文书的焦点的效率的技术效果。
附图说明
此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1是根据本发明实施例的获取裁判文书焦点的方法的流程图；
图2是根据本申请实施例的一种可选的获取裁判文书焦点的方法的原理示意图；以及
图3是根据本发明实施例的获取裁判文书焦点的装置的示意图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。
需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这 样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
下面，对实施例中出现的词汇进行解释，以便对实施例的理解。
裁判文书：用于记载法院审理案件的过程和结果，是诉讼活动结果的载体，也是人民法院确定和分配当事人义务权利的唯一凭证。
焦点：即争议焦点，简单地说就是纠纷的核心，矛盾的交锋点，案件双方当事人争执的问题所在，在形式上是由法官归纳、并经当事人确认的争点，是引领案件审理、纠纷解决的主线和枢纽，也是体现法官熟悉案情的程度，把握法律与案件联系的能力的一个突出标志。
实施例1
根据本发明实施例，提供了一种获取裁判文书焦点的方法实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
图1是根据本发明实施例的获取裁判文书焦点的方法的流程图，如图1所示，该方法包括如下步骤：
步骤S102，获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建。
具体的，上述已确定焦点的第一裁判文书可以从预设的文书库中获取，由于第一裁判文书已确定焦点，因此在获取已确定焦点的第一裁判文书的同时，还能够直接得到第一裁判文书的焦点。
步骤S104，通过焦点规则引擎获取属于目标裁判文书的焦点。
具体的，上述目标裁判文书为待确定焦点的裁判文书。在一种可选的实施例中，可以将目标裁判文书输入至上述焦点规则引擎，焦点规则引擎则能够输出目标裁判文书的焦点。
此处需要说明的是，还可以按照预设的周期对焦点规则引擎进行更新，以保持焦点规则引擎的时效性。
由上可知，本申请上述实施例根据已确定焦点的第一裁判文书构建焦点规则引擎，通过焦点规则引擎获取属于目标裁判文书的焦点。上述方案由已确定焦点的第一裁判文书得到焦点规则引擎，再通过焦点规则引擎来确定待确定焦点的目标裁判文书的焦点，解决了现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题，并且提高了确定裁判文书的焦点的效率的技术效果。
可选的，根据本申请上述实施例，步骤S102，根据已确定焦点的第一裁判文书构建焦点规则引擎，包括：
步骤S1021，获取预设领域对应的第一裁判文书。
具体的，上述预设领域为构建的焦点规则引擎的领域。例如，当构建的焦点规则引擎为商标侵权领域为例，用于构建该焦点规则引擎的第一裁判文书应该属于商标侵权领域。在一种可选的实施例中，以商标侵权领域为例，可以在文书库中提取出案由为“侵害商标权纠纷”的文书作为该领域的第一裁判文书。
步骤S1023，获取第一裁判文书中的焦点对应的焦点信息。
具体的，上述焦点信息可以包括焦点出现的段落、焦点所在段落中所处的具体行位置以及焦点出现的句式等。
步骤S1025，根据第一裁判文书中的焦点和第一裁判文书中的焦点对应的焦点信息构建预设领域对应的规则引擎。
在一种可选的实施例中，可以通过对第一裁判文书进行学习来得到焦点规则引擎，例如，可以将第一裁判文书以及第一裁判文书的焦点输入至预设的经过初始化后的焦点规则引擎中，对焦点规则引擎进行训练，直至输入任意一个第一裁判文书至焦点规则引擎，焦点规则引擎都能够输出与已确定焦点结果相同的焦点。
由上可知，本申请上述实施例根据某一领域的第一裁判文书构建该领域对应的焦点规则引擎，从而使得焦点规则引擎查找焦点的结果更准确。
可选的，根据本申请上述实施例，为了在构建焦点规则引擎的过程中能够方便的学习并进行训练，且在焦点规则引擎的使用过程中方便的进行结果的输出，可以通过标识的方式来表示焦点内容，因此在获取预设领域对应的第一裁判文书之后，上述方法还可以包括如下步骤：
步骤S1027，提取预设领域对应的第一裁判文书的焦点，构成预设领域对应的焦点库。
步骤S1029，将焦点库中的焦点根据预设的维度进行分类。
具体的，上述预设维度可以为预设的领域对应的焦点类。在一种可选的实施例中，仍以商标侵权领域为例，上述预设的维度可以是经过对法官的思维模式进行梳理得到的五大焦点类：(1)商标类型；(2)行为模式；(3)抗辩理由；(4)侵权责任；(5)其他焦点。
进一步地，还可以对上述类型继续进行分类，例如：(1)商标类型：驰名商标、商品商标、服务商标、证明商标、集体商标、立体商标、声音商标、三维标志商标、地理标志；(2)行为模式：商标假冒/仿冒行为、销售侵犯注册商标专用权的商品、商标辅助侵权行为、企业字号侵害他人注册商标的行为、域名侵害他人注册商标的行为、侵犯驰名商标的行为、其他侵权行为；(3)抗辩理由：在先权利及合理使用、是否具有合法来源/合法渠道、注册商标是否未实际使用、商标共有权人/共有商标；(4)侵权责任：停止侵权/停止销售/销毁、赔偿损失、消除影响；(5)其他焦点：主体是否适格、是否超过诉讼时效、是否构成商标性使用、经行政处罚/经刑事判决、是否构成不正当竞争。
此处需要说明的是，上述分类的步骤不限于是一次或多次，在某个案件类型具有多种分支，或多种变形方式的情况下，可以在一次或多次分类的基础上继续进行分类，直至能够具体到直接对案件的焦点进行分类。
步骤S1031，根据焦点库中的焦点所属的类别进行编码，得到每个焦点对应的标识。
在一种可选的实施例中，仍以上述商标侵权领域为例，可以将上述五大类焦点类(1)商标类型、(2)行为模式、(3)抗辩理由、(4)侵权责任和(5)其他焦点分别编码为A、B、C、D和E，当焦点属于上述任意一类时，可以用焦点类对应的编码代表该焦点。
在另一种可选的实施例中，可以对上述五大类焦点继续进行了分类，以A类焦点(1)商标类型包括：驰名商标、商品商标、服务商标、证明商标、集体商标、立体商标、声音商标、三维标志商标和地理标志为例，还可以再将A类焦点下的子类进行编码，例如，驰名商标、商品商标、服务商标、证明商标、集体商标、立体商标、声音商标、三维标志商标和地理标志可以分别编码为A1、A2、A3、A4、A5、A6、A7、A8和A9。其他焦点类也可以继续进行分类，按照上述规则进行编码。
此处需要说明的是，上述实施例中的编码方式仅用于示例，实际上能够建立起焦点与标识的对应关系的标识方式均能够用于上述方案中。
可选的，根据本申请上述实施例，获取预设领域对应的第一裁判文书，包括：
步骤S1021a，获取多个第二裁判文书。具体的，上述第二裁判文书可以为文书库中的所有文书。
步骤S1021b，根据第二裁判文书的案由确定第二裁判文书所属的领域。
步骤S1021c，将属于预设领域的第二裁判文书作为预设领域对应的第一裁判文书。
由上可知，本申请上述方案根据裁判文书中的案由确定裁判文书的领域，无需人为的依次对每个裁判文书进行确定，极大的提高了获取预设领域的第一裁判文书的效率。
可选的，根据本申请上述实施例，焦点信息包括：焦点位置和焦点属性，通过焦点规则引擎获取属于目标裁判文书的焦点，包括：
步骤S1041，在目标裁判文书中依次查找每个焦点位置。
具体的，上述焦点位置可以包括焦点所在的段落，以及在段落中的行位置，进一步地，还可以包括在行位置中具体的字符位置。焦点属性可以包括焦点出现的句式、用于表征焦点的关键词等。
步骤S1043，如果焦点位置对应的内容的属性与焦点位置所指示的焦点对应的焦点属性相同，则确定目标裁判文书中焦点位置对应的内容为焦点。
在一种可选的实施例中，焦点A1对应的焦点位置为第一裁判文书中的第[0028]段第一行，其属性为出现在“经审理查明”这一句式之后。在向焦点规则引擎输入目标裁判文书之后，焦点规则引擎在目标裁判文书中第[0028]段进行查找，如果查找到“经审理查明”这一句式，则确认该目标裁判文书具有A1这一焦点。
可选的，根据本申请上述实施例，在通过所述焦点规则引擎获取属于目标裁判文书的焦点之后，方法还包括：根据目标裁判文书中所有的焦点对应的标识构成焦点序列；在一种可选的实施例中，可以将每个焦点对应的标识按照焦点出现的顺序进行排序，从而得到焦点序列；输出焦点序列，并根据焦点序列中每个焦点对应的焦点内容，输出目标裁判文书的焦点内容。
在生成焦点标识的过程中，焦点与焦点内容一一对应，因此在获取到目标裁判文书的焦点内容后，能够根据焦点与焦点序列中标识的对应关系确定目标裁判文书的焦点内容。
此处需要说明的是，由于焦点标识对应的是焦点库中的预设焦点类的子焦点，所以，焦点序列中每个焦点都代表着预设领域的一种非常具体的焦点类型。仍以商标侵权领域为例，如商品商标领域，被告实施了销售侵犯原告商标专用权商品的行为，法 院重点对是否构成近似商标、是否具有合法来源等争议点进行释法说理的案件类型。所以通过焦点规则引擎处理过的裁判文书能直接读取出焦点序列，并根据焦点序列中每个焦点码得到对应的焦点内容。
图2是根据本申请实施例的一种可选的获取裁判文书焦点的方法的原理示意图，结合图2所示，下面分为两个步骤对图2中的示例进行描述。
步骤一：从裁判文书库中获取焦点库，根据焦点库中每个焦点对应的焦点信息，生成焦点规则引擎。具体的，上述裁判文书库为已确定焦点的第一裁判文书构成的裁判文书库，该步骤为在最初始阶段的准备工作，不为每次通过焦点规则引擎获取目标裁判文书的焦点固定步骤；
步骤二，该步骤包括：a，向焦点规则引擎输入目标裁判文书；b，焦点规则引擎输出目标裁判文书的焦点序列。该步骤为每次通过焦点规则引擎获取目标裁判文书的焦点步骤。
实施例2
根据本发明实施例，提供了一种获取裁判文书焦点的装置实施例，图3是根据本发明实施例的获取裁判文书焦点的装置的示意图，如图3所示，该装置包括：
第一获取模块30，设置为获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建。
具体的，上述已确定焦点的第一裁判文书可以从预设的文书库中获取，由于第一裁判文书已确定焦点，因此在获取已确定焦点的第一裁判文书的同时，还能够直接得到第一裁判文书的焦点。
第二获取模块32，设置为通过焦点规则引擎获取属于目标裁判文书的焦点。
具体的，上述目标裁判文书为待确定焦点的裁判文书。在一种可选的实施例中，可以将目标裁判文书输入至上述焦点规则引擎，焦点规则引擎则能够输出目标裁判文书的焦点。
此处需要说明的是，还可以按照预设的周期对焦点规则引擎进行更新，以保持焦点规则引擎的时效性。
由上可知，本申请上述实施例采用第一获取模块根据已确定焦点的第一裁判文书构建焦点规则引擎，采用第二获取模块通过焦点规则引擎获取属于目标裁判文书的焦点。上述方案由已确定焦点的第一裁判文书得到焦点规则引擎，再通过焦点规则引擎来确定待确定焦点的目标裁判文书的焦点，解决了现有技术中通过人为标记关键词来 获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题，并且提高了确定裁判文书的焦点的效率的技术效果。
此处需要说明的是，上述第一获取模块30和第二获取模块32可以作为装置的一部分运行在计算机终端中，可以通过计算机终端中的处理器来执行上述模块实现的功能，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选的，根据本申请上述实施例，装置还包括：构建模块，设置为在获取预设的焦点规则引擎之前，根据已确定焦点的第一裁判文书构建焦点规则引擎。
可选的，根据本申请上述实施例，构建模块包括：
第一获取子模块，设置为获取预设领域对应的第一裁判文书。
第二获取子模块，设置为获取第一裁判文书中的焦点对应的焦点信息。
构建子模块，设置为根据第一裁判文书中的焦点和第一裁判文书中的焦点对应的焦点信息构建预设领域对应的焦点规则引擎。
可选的，根据本申请上述实施例，装置还包括：
提取模块，设置为在获取预设领域对应的裁判文书库之后，提取预设领域对应的第一裁判文书库的焦点，构成预设领域对应的焦点库。
分类模块，设置为将焦点库中的焦点根据预设的维度进行分类。
编码模块，设置为根据焦点库中的焦点所属的类别进行编码，得到每个焦点对应的标识。
可选的，根据本申请上述实施例，焦点信息包括：焦点位置和焦点属性，第二获取模块包括：
查找子模块，设置为在目标裁判文书中依次查找每个焦点位置；
确定子模块，设置为如果焦点位置对应的内容的属性与焦点位置所指示的焦点对应的焦点属性相同，则确定目标裁判文书中焦点位置对应的内容为焦点。
可选的，根据本申请上述实施例，装置还包括：
构建模块，设置为在通过焦点规则引擎获取属于目标裁判文书的焦点之后，根据目标裁判文书中所有的焦点对应的标识构成焦点序列；
输出模块，设置为输出焦点序列，并根据焦点序列中每个焦点对应的焦点内容， 输出目标裁判文书的焦点内容。
本申请实施例所提供的各个功能单元可以在移动终端、计算机终端或者类似的运算装置中运行，也可以作为存储介质的一部分进行存储。
由此，本发明的实施例可以提供一种计算机终端，该计算机终端可以是计算机终端群中的任意一个计算机终端设备。可选地，在本实施例中，上述计算机终端也可以替换为移动终端等终端设备。
可选地，在本实施例中，上述计算机终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
在本实施例中，上述计算机终端可以执行获取裁判文书焦点的方法中以下步骤的程序代码：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。
可选地，该计算机终端可以包括：一个或多个处理器、存储器、以及传输装置。
其中，存储器可用于存储软件程序以及模块，如本发明实施例中的获取裁判文书焦点的方法及装置对应的程序指令/模块，处理器通过运行存储在存储器内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的获取裁判文书焦点的方法。存储器可包括高速随机存储器，还可以包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器可进一步包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置用于经由一个网络接收或者发送数据。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，具体地，存储器用于存储预设动作条件和预设权限用户的信息、以及应用程序。
处理器可以通过传输装置调用存储器存储的信息及应用程序，以执行上述方法实施例中的各个可选或优选实施例的方法步骤的程序代码。
本领域普通技术人员可以理解，计算机终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本申请实施例提供了一种存储介质，其上存储有程序，该程序被处理器执行时实现所述获取裁判文书焦点的方法。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。
可选地，在本实施例中，存储介质还可以被设置为获取裁判文书焦点的方法提供的各种优选地或可选的方法步骤的程序代码。
本发明实施例提供了一种处理器，所述处理器用于运行程序，其中，所述程序运行时执行所述获取裁判文书焦点的方法。
本发明实施例提供了一种设备，设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序，处理器执行程序时实现以下步骤：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。本文中的设备可以是服务器、PC、PAD、手机等。
如上参照附图以示例的方式描述了根据本发明的获取裁判文书焦点的方法及装置。但是，本领域技术人员应当理解，对于上述本发明所提出的获取裁判文书焦点的方法及装置，还可以在不脱离本发明内容的基础上做出各种改进。因此，本发明的保护范围应当由所附的权利要求书的内容确定。
所述获取裁判文书焦点的装置包括处理器和存储器，上述第一获取模块和第二获取模块等均作为程序单元存储在存储器中，由处理器执行存储在存储器中的上述程序单元实现相应功能。
处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来解决现有技术中通过人为标记关键词来获取裁判文书的焦点，获取的裁判文书的焦点主观性较强，导致获取的裁判文书的焦点准确度低的技术问题。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本申请还提供了一种计算机程序产品的实施例，当在数据处理设备上执行时，适于执行初始化有如下方法步骤的程序代码：获取预设的焦点规则引擎，其中，焦点规则引擎根据已确定焦点的第一裁判文书构建；通过焦点规则引擎获取属于目标裁判文书的焦点。
当在数据处理设备上执行时，上述计算机程序还适于执行初始化有如下方法步骤的程序：获取预设领域对应的第一裁判文书；获取第一裁判文书中的焦点对应的焦点信息；根据第一裁判文书中的焦点和焦点对应的焦点信息构建预设领域对应的焦点规则引擎。
当在数据处理设备上执行时，上述计算机程序还适于执行初始化有如下方法步骤的程序：提取预设领域对应的第一裁判文书的焦点，构成预设领域对应的焦点库；将焦点库中的焦点根据预设的维度进行分类；根据焦点库中的焦点所属的类别进行编码，得到每个焦点对应的标识。
当在数据处理设备上执行时，上述计算机程序还适于执行初始化有如下方法步骤的程序：焦点信息包括：焦点位置和焦点属性，在目标裁判文书中依次查找每个焦点位置；如果焦点位置对应的内容的属性与焦点位置所指示的焦点对应的焦点属性相同，则确定目标裁判文书中焦点位置对应的内容为焦点。
当在数据处理设备上执行时，上述计算机程序还适于执行初始化有如下方法步骤的程序：根据目标裁判文书中所有的焦点对应的标识构成焦点序列；输出焦点序列，并根据焦点序列中每个焦点对应的焦点内容，输出目标裁判文书的焦点内容。
上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。
在本发明的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有 详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的技术内容，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，可以为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (15)

  1. 一种获取裁判文书焦点的方法，包括：
    获取预设的焦点规则引擎，其中，所述焦点规则引擎根据已确定焦点的第一裁判文书构建；
    通过所述焦点规则引擎获取属于目标裁判文书的焦点。
  2. 根据权利要求1所述的方法，其中，在获取预设的焦点规则引擎之前，所述方法还包括：根据已确定焦点的第一裁判文书构建焦点规则引擎。
  3. 根据权利要求2所述的方法，其中，根据已确定焦点的第一裁判文书构建焦点规则引擎的步骤包括：
    获取预设领域对应的第一裁判文书；
    获取所述第一裁判文书中的焦点对应的焦点信息；
    根据所述第一裁判文书中的焦点和所述焦点对应的焦点信息构建所述预设领域对应的焦点规则引擎。
  4. 根据权利要求2所述的方法，其中，在获取预设领域对应的第一裁判文书之后，所述方法还包括：
    提取所述预设领域对应的第一裁判文书的焦点，构成所述预设领域对应的焦点库；
    将所述焦点库中的焦点根据预设的维度进行分类；
    根据所述焦点库中的焦点所属的类别进行编码，得到每个焦点对应的标识。
  5. 根据权利要求3或4所述的方法，其中，所述焦点信息包括：焦点位置和焦点属性。
  6. 根据权利要求5所述的方法，其中，通过所述焦点规则引擎获取属于目标裁判文书的焦点，包括：
    在所述目标裁判文书中依次查找每个焦点位置；
    如果所述焦点位置对应的内容的属性与所述焦点位置所指示的焦点对应的焦点属性相同，则确定所述目标裁判文书中所述焦点位置对应的内容为焦点。
  7. 根据权利要求6所述的方法，其中，在通过所述焦点规则引擎获取属于目标裁判文书的焦点之后，所述方法还包括：
    根据所述目标裁判文书中所有的焦点对应的标识构成焦点序列；
    输出所述焦点序列，并根据所述焦点序列中每个焦点对应的焦点内容，输出所述目标裁判文书的焦点内容。
  8. 一种获取裁判文书焦点的装置，包括：
    第一获取模块，设置为获取预设的焦点规则引擎，其中，所述焦点规则引擎根据已确定焦点的第一裁判文书构建；
    第二获取模块，设置为通过所述焦点规则引擎获取属于目标裁判文书的焦点。
  9. 根据权利要求8所述的装置，其中，所述装置还包括：构建模块，设置为在获取预设的焦点规则引擎之前，根据已确定焦点的第一裁判文书构建焦点规则引擎。
  10. 根据权利要求9所述的装置，其中，所述构建模块包括：
    第一获取子模块，设置为获取预设领域对应的第一裁判文书；
    第二获取子模块，设置为获取所述第一裁判文书中的焦点对应的焦点信息；
    构建子模块，设置为根据所述第一裁判文书中的焦点和所述第一裁判文书中的焦点对应的焦点信息构建所述预设领域对应的焦点规则引擎。
  11. 根据权利要求10所述的装置，其中，所述装置还包括：
    提取模块，设置为在获取预设领域对应的裁判文书库之后，提取所述预设领域对应的第一裁判文书库的焦点，构成所述预设领域对应的焦点库；
    分类模块，设置为将所述焦点库中的焦点根据预设的维度进行分类；
    编码模块，设置为根据所述焦点库中的焦点所属的类别进行编码，得到每个焦点对应的标识。
  12. 根据权利要求10或11所述的装置，其中，所述焦点信息包括：焦点位置和焦点属性。
  13. 根据权利要求12所述的装置，其中，所述第二获取模块包括：
    查找子模块，设置为在所述目标裁判文书中依次查找每个焦点位置；
    确定子模块，设置为如果所述焦点位置对应的内容的属性与所述焦点位置所指示的焦点对应的焦点属性相同，则确定所述目标裁判文书中所述焦点位置对应的内容为焦点。
  14. 一种存储介质，其中，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行权利要求1至7中任意一项所述的获取裁判文书焦点的方法。
  15. 一种处理器，其中，所述处理器用于运行程序，其中，所述程序运行时执行权利要求1至7中任意一项所述的获取裁判文书焦点的方法。
PCT/CN2018/090354 2017-06-09 2018-06-08 获取裁判文书焦点的方法和装置 WO2018224028A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710433361.9 2017-06-09
CN201710433361.9A CN109033105B (zh) 2017-06-09 2017-06-09 获取裁判文书焦点的方法和装置

Publications (1)

Publication Number Publication Date
WO2018224028A1 true WO2018224028A1 (zh) 2018-12-13

Family

ID=64566401

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/090354 WO2018224028A1 (zh) 2017-06-09 2018-06-08 获取裁判文书焦点的方法和装置

Country Status (2)

Country Link
CN (1) CN109033105B (zh)
WO (1) WO2018224028A1 (zh)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110516203A (zh) * 2019-08-28 2019-11-29 北京市律典通科技有限公司 争议焦点分析方法、装置、电子设备及计算机可存储介质
CN110765760A (zh) * 2019-09-03 2020-02-07 平安科技（深圳）有限公司 一种法律案件分配方法、装置、存储介质和服务器
CN110889502A (zh) * 2019-10-15 2020-03-17 东南大学 一种基于深度学习的争议焦点生成方法
CN111401047A (zh) * 2018-12-29 2020-07-10 北京国双科技有限公司 法律文书的争议焦点生成方法、装置及计算机设备
CN111507095A (zh) * 2019-01-29 2020-08-07 阿里巴巴集团控股有限公司 裁判文书的生成方法、装置、存储介质和处理器
CN111563374A (zh) * 2020-03-23 2020-08-21 北京交通大学 一种基于司法裁判文书的人员社交关系抽取方法
CN111753537A (zh) * 2020-06-12 2020-10-09 鼎富智能科技有限公司 离婚纠纷裁判文书标签提取方法及装置
CN111753538A (zh) * 2020-06-12 2020-10-09 鼎富智能科技有限公司 离婚纠纷裁判文书要素提取方法及装置
CN111783472A (zh) * 2020-06-30 2020-10-16 鼎富智能科技有限公司 一种判决书内容提取方法及相关装置
CN112541005A (zh) * 2019-09-23 2021-03-23 北京国双科技有限公司 编号的生成方法、装置及电子设备
CN112579763A (zh) * 2019-09-30 2021-03-30 北京国双科技有限公司 一种文书的推送方法及装置
CN112579746A (zh) * 2019-09-29 2021-03-30 京东数字科技控股有限公司 获取文本对应的行为信息的方法和装置
CN114092119A (zh) * 2021-11-29 2022-02-25 北京金堤科技有限公司 供应关系获取方法、装置、存储介质及电子设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109992664B (zh) * 2019-03-12 2023-04-18 平安科技（深圳）有限公司 争议焦点的标注分类方法、装置、计算机设备和存储介质
CN112580338A (zh) * 2019-09-27 2021-03-30 北京国双科技有限公司 确定争议焦点的方法和装置、存储介质和设备
CN111967437A (zh) * 2020-09-03 2020-11-20 平安国际智慧城市科技股份有限公司 文本识别方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080005094A1 (en) * 2006-07-01 2008-01-03 Kevin Cunnane Method and system for finding the focus of a document
CN104054075A (zh) * 2011-12-06 2014-09-17 派赛普申合伙公司 文本挖掘、分析和输出系统
CN105988978A (zh) * 2015-03-04 2016-10-05 科大讯飞股份有限公司 确定文本焦点的方法及系统
CN106326420A (zh) * 2015-08-24 2017-01-11 Tcl集团股份有限公司 一种用于移动终端的推荐方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105426748B (zh) * 2014-09-18 2019-09-13 腾讯科技（深圳）有限公司 一种规则文件的更新方法和设备
US20160103823A1 (en) * 2014-10-10 2016-04-14 The Trustees Of Columbia University In The City Of New York Machine Learning Extraction of Free-Form Textual Rules and Provisions From Legal Documents
CN106502996A (zh) * 2016-12-13 2017-03-15 深圳爱拼信息科技有限公司 一种基于语义匹配的裁判文书检索方法和服务器

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080005094A1 (en) * 2006-07-01 2008-01-03 Kevin Cunnane Method and system for finding the focus of a document
CN104054075A (zh) * 2011-12-06 2014-09-17 派赛普申合伙公司 文本挖掘、分析和输出系统
CN105988978A (zh) * 2015-03-04 2016-10-05 科大讯飞股份有限公司 确定文本焦点的方法及系统
CN106326420A (zh) * 2015-08-24 2017-01-11 Tcl集团股份有限公司 一种用于移动终端的推荐方法及装置

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111401047A (zh) * 2018-12-29 2020-07-10 北京国双科技有限公司 法律文书的争议焦点生成方法、装置及计算机设备
CN111507095B (zh) * 2019-01-29 2023-05-02 阿里云计算有限公司 裁判文书的生成方法、装置、存储介质和处理器
CN111507095A (zh) * 2019-01-29 2020-08-07 阿里巴巴集团控股有限公司 裁判文书的生成方法、装置、存储介质和处理器
CN110516203A (zh) * 2019-08-28 2019-11-29 北京市律典通科技有限公司 争议焦点分析方法、装置、电子设备及计算机可存储介质
CN110516203B (zh) * 2019-08-28 2023-08-04 北京市律典通科技有限公司 争议焦点分析方法、装置、电子设备及计算机可存储介质
CN110765760B (zh) * 2019-09-03 2023-01-06 平安科技（深圳）有限公司 一种法律案件分配方法、装置、存储介质和服务器
CN110765760A (zh) * 2019-09-03 2020-02-07 平安科技（深圳）有限公司 一种法律案件分配方法、装置、存储介质和服务器
CN112541005A (zh) * 2019-09-23 2021-03-23 北京国双科技有限公司 编号的生成方法、装置及电子设备
CN112579746A (zh) * 2019-09-29 2021-03-30 京东数字科技控股有限公司 获取文本对应的行为信息的方法和装置
CN112579763A (zh) * 2019-09-30 2021-03-30 北京国双科技有限公司 一种文书的推送方法及装置
CN110889502A (zh) * 2019-10-15 2020-03-17 东南大学 一种基于深度学习的争议焦点生成方法
CN110889502B (zh) * 2019-10-15 2024-02-06 东南大学 一种基于深度学习的争议焦点生成方法
CN111563374A (zh) * 2020-03-23 2020-08-21 北京交通大学 一种基于司法裁判文书的人员社交关系抽取方法
CN111563374B (zh) * 2020-03-23 2022-08-19 北京交通大学 一种基于司法裁判文书的人员社交关系抽取方法
CN111753537A (zh) * 2020-06-12 2020-10-09 鼎富智能科技有限公司 离婚纠纷裁判文书标签提取方法及装置
CN111753538A (zh) * 2020-06-12 2020-10-09 鼎富智能科技有限公司 离婚纠纷裁判文书要素提取方法及装置
CN111783472A (zh) * 2020-06-30 2020-10-16 鼎富智能科技有限公司 一种判决书内容提取方法及相关装置
CN114092119A (zh) * 2021-11-29 2022-02-25 北京金堤科技有限公司 供应关系获取方法、装置、存储介质及电子设备

Also Published As

Publication number Publication date
CN109033105A (zh) 2018-12-18
CN109033105B (zh) 2022-03-01

Similar Documents

Publication Publication Date Title
WO2018224028A1 (zh) 获取裁判文书焦点的方法和装置
CN110147726B (zh) 业务质检方法和装置、存储介质及电子装置
CN110348214B (zh) 对恶意代码检测的方法及系统
CN108768986B (zh) 一种加密流量分类方法及服务器、计算机可读存储介质
TW201909112A (zh) 圖像特徵獲取
CN109815976A (zh) 一种证件信息识别方法、装置及设备
JP2018503158A (ja) ソーシャルプラットフォームに基づくデータマイニング方法及び装置
CN103164698B (zh) 文本指纹库生成方法及装置、文本指纹匹配方法及装置
KR101627398B1 (ko) 내용기반의 검색엔진을 이용한 개인 콘텐츠 저작권 관리 시스템 및 방법
CN105718502A (zh) 用于高效特征匹配的方法和设备
CN113032528B (zh) 案件分析方法、装置、设备及存储介质
Chen et al. Automatic mobile application traffic identification by convolutional neural networks
CN106844544A (zh) 一种合同条款风险识别方法及系统
CN107368592B (zh) 一种用于网络安全报告的文本特征模型建模方法及装置
CN110858353B (zh) 获取案件裁判结果的方法和系统
CN109714356A (zh) 一种异常域名的识别方法、装置及电子设备
MX2011009461A (es) Metodo y dispositivo para extraer un circulo de relaciones caracteristico de una red.
WO2020063524A1 (zh) 一种法律文书的确定方法及系统
CN110995681B (zh) 用户识别方法、装置、电子设备及存储介质
CN108154031A (zh) 伪装应用程序的识别方法、装置、存储介质和电子装置
CN104615621B (zh) 搜索中的相关性处理方法和系统
CN108664501B (zh) 广告审核方法、装置及服务器
CN111899741A (zh) 音频关键词加密方法、装置、存储介质及电子装置
CN111144546A (zh) 评分方法、装置、电子设备及存储介质
CN110020134A (zh) 一种知识服务信息的推送方法、系统、存储介质和处理器

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18813949

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18813949

Country of ref document: EP

Kind code of ref document: A1