CN107784024A - Build the method and device of party's portrait - Google Patents

Build the method and device of party's portrait Download PDF

Info

Publication number
CN107784024A
CN107784024A CN201610792049.4A CN201610792049A CN107784024A CN 107784024 A CN107784024 A CN 107784024A CN 201610792049 A CN201610792049 A CN 201610792049A CN 107784024 A CN107784024 A CN 107784024A
Authority
CN
China
Prior art keywords
paragraph
party
judicial
target
grammatical
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.)
Granted
Application number
CN201610792049.4A
Other languages
Chinese (zh)
Other versions
CN107784024B (en
Inventor
贾炜
石鹏
刘激扬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Gridsum Technology Co Ltd
Original Assignee
Beijing Gridsum Technology Co Ltd
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 Beijing Gridsum Technology Co Ltd filed Critical Beijing Gridsum Technology Co Ltd
Priority to CN201610792049.4A priority Critical patent/CN107784024B/en
Publication of CN107784024A publication Critical patent/CN107784024A/en
Application granted granted Critical
Publication of CN107784024B publication Critical patent/CN107784024B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/34Browsing; Visualisation therefor
    • G06F16/345Summarisation for human users
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Machine Translation (AREA)

Abstract

The invention discloses a kind of method and device for building party's portrait.Wherein, this method includes:Target party is searched from the judicial domain body built in advance, wherein, the structured data comprising Ontological concept and the attribute for describing Ontological concept, Ontological concept include party in judicial domain body;After target party is found, the structured data for being used to describe the attribute of the target party in the structured data of user's input is chosen or received from the structured data of the attribute for describing Ontological concept;According to selection or reception the structured data for being used to describe the attribute of target party, party's portrait of structure target party.The present invention solves the technical problem that can not build party's portrait in correlation technique automatically.

Description

Build the method and device of party's portrait
Technical field
The present invention relates to data processing field, in particular to a kind of method and device for building party's portrait.
Background technology
The relevant information of many parties is usually contained in a judicial document, these relevant informations are to analyzing party Feature, structure party's portrait have very big value.
Correlation technique is main to be taken passages using manual type from judicial document pair in the party in analyzing judicial document The party's information answered, these information are classified, normalized and statistical disposition.Wherein, message digest and classifying rules be all Determined by concrete application demand, the message digest and classifying rules of different application have different emphasis.
However, because above-mentioned technical proposal is mainly by what is manually realized, efficiency is low, and accuracy rate is poor, it is difficult in a short time The analysis work of a large amount of judicial documents is completed, and manually obtains data and has that standard differs, more or less, reuses and compares The defects of difficult.
Although additionally provided in correlation technique a kind of effective structure domestic consumer portrait (such as log in/browse electric business website User portrait) technical scheme, but the program is realized by the specified dimension of statistical framework data.And Judicial document is as text data, and text data is unstructured data, thus existing structure domestic consumer portrait is automatic Construction method cannot be directly used to build party's portrait.
In view of the above-mentioned problems, not yet propose effective solution at present.
The content of the invention
The embodiments of the invention provide a kind of method and device for building party's portrait, at least to solve in correlation technique The technical problem of party's portrait can not be built automatically.
One side according to embodiments of the present invention, there is provided a kind of method for building party's portrait, including:From advance Target party is searched in the judicial domain body of structure, wherein, Ontological concept is included in above-mentioned judicial domain body and is used for The structured data of the attribute of Ontological concept is described, above-mentioned Ontological concept includes party;After above-mentioned target party is found, The use in the structured data of user's input is chosen or received from the said structure data of the attribute for describing Ontological concept In the structured data for the attribute for describing above-mentioned target party;Work as thing for describing above-mentioned target according to selection or reception The structured data of the attribute of people, build party's portrait of above-mentioned target party.
Further, according to it is selection or reception be used for describe above-mentioned target party attribute structured data, Building party's portrait of above-mentioned target party includes:In the case where above-mentioned target party is individual party, according to That chooses is used to describe the part or all of structured data of the attribute of above-mentioned target party, builds working as above-mentioned individual party Thing people draws a portrait;In the case where above-mentioned target party is colony party, thing is worked as describing above-mentioned target according to selection The part or all of structured data of the attribute of people, build party's portrait of above-mentioned colony party.
Further, above-mentioned judicial domain body is built by following steps:According to above-mentioned Ontological concept and for describing The above-mentioned attribute of Ontological concept, it is determined that selectively becoming corresponding to the grammatical Feature Words and Feature Words of judicial document for parsing Amount;The selective variable according to corresponding to the Feature Words and Feature Words of determination, builds the above-mentioned syntax;Using the above-mentioned syntax of structure, Parsing needs the judicial document parsed, obtains judicial document analysis result;Above-mentioned judicial document analysis result is filled into above-mentioned In judicial domain body.
Further, after selective variable corresponding to the Feature Words and Feature Words according to determination, the above-mentioned syntax of structure, The above method also includes:Obtain the style of writing feature of judicial document;According to the style of writing feature of above-mentioned grammatical and above-mentioned judicial document, structure Grammatical paragraph feature templates and grammatical paragraph position feature template are built, corresponding template characteristic and the syntax are included in each template Subset, wherein, using the above-mentioned syntax of structure, parsing needs the judicial document parsed, and obtaining judicial document analysis result includes: Use the above-mentioned grammatical paragraph feature templates of structure, or above-mentioned grammatical paragraph feature templates and above-mentioned grammatical paragraph position feature Template, the judicial document of above-mentioned needs parsing is parsed paragraph by paragraph, obtains judicial document analysis result.
Further, using above-mentioned grammatical paragraph feature templates and above-mentioned grammatical paragraph position feature template, paragraph by paragraph parsing The judicial document of above-mentioned needs parsing, obtaining judicial document analysis result includes:Carried from the judicial document of above-mentioned needs parsing The target paragraph taken;For grammatical paragraph feature templates corresponding to the matching of above-mentioned target paragraph;If the match is successful, using matching Grammatical paragraph feature templates, parse above-mentioned target paragraph, obtain corresponding analysis result, and jump to next target paragraph Process of analysis;If it fails to match, for above-mentioned target paragraph matching corresponding to grammatical paragraph position feature template, if matching into Work(, then using the grammatical paragraph position feature template matched, above-mentioned target paragraph is parsed, obtains corresponding analysis result, and Jump to the process of analysis of next target paragraph.
Further, during above-mentioned target paragraph is parsed, the above method also includes:If corresponding analysis result is Sky, then at least record the sequence number of the judicial document of above-mentioned needs parsing and above-mentioned target paragraph;Record result is filled into State in judicial domain body.
Further, in the above-mentioned syntax using structure, parsing needs the judicial document parsed, obtains judicial document parsing As a result after, the above method also includes:According to above-mentioned judicial document analysis result, the incidence relation between all parties is built; Count the Numeric Attributes of each party;After the completion of incidence relation structure between all parties, each party is counted Incidence relation each dimension statistical value;By the incidence relation between above-mentioned all parties, the numerical value of above-mentioned each party The statistical value of each dimension of type attribute and the incidence relation of above-mentioned each party is filled into above-mentioned judicial domain body.
Another aspect according to embodiments of the present invention, a kind of device for building party's portrait is additionally provided, including:Search Unit, for searching target party from the judicial domain body built in advance, wherein, included in above-mentioned judicial domain body The structured data of Ontological concept and the attribute for describing Ontological concept, above-mentioned Ontological concept include party;Processing unit, use In after above-mentioned target party is found, choose or connect from the said structure data of the attribute for describing Ontological concept Receive the structured data for being used to describe the attribute of above-mentioned target party in the structured data of user's input;First construction unit, For according to selection or reception the structured data for being used to describe the attribute of above-mentioned target party, building above-mentioned target and working as Party's portrait of thing people.
Further, above-mentioned first construction unit includes:First structure module, for being individual in above-mentioned target party In the case of party, according to the part or all of structured data for being used to describe the attribute of above-mentioned target party of selection, structure Build party's portrait of above-mentioned individual party;Second structure module, for being colony party's in above-mentioned target party In the case of, according to the part or all of structured data for being used to describe the attribute of above-mentioned target party of selection, build above-mentioned group Party's portrait of body party.
Further, said apparatus also includes:Determining unit, for after judicial domain body is obtained, according to above-mentioned Ontological concept and the above-mentioned attribute for describing Ontological concept, it is determined that grammatical Feature Words and feature for parsing judicial document Selective variable corresponding to word;Second construction unit, for selective variable corresponding to the Feature Words and Feature Words according to determination, Build the above-mentioned syntax;Resolution unit, for the above-mentioned syntax using structure, parsing needs the judicial document parsed, obtains the administration of justice Document analysis result;First fills unit, for above-mentioned judicial document analysis result to be filled into above-mentioned judicial domain body.
Further, said apparatus also includes:Acquiring unit, for choosing corresponding to the Feature Words and Feature Words according to determination Selecting property variable, after building the above-mentioned syntax, obtain the style of writing feature of judicial document;3rd construction unit, for according to above-mentioned text The style of writing feature of method and above-mentioned judicial document, build grammatical paragraph feature templates and grammatical paragraph position feature template, Mei Gemo All comprising corresponding template characteristic and grammatical subset in plate, wherein, above-mentioned resolution unit is additionally operable to:Use the above-mentioned syntax of structure Paragraph feature templates, or above-mentioned grammatical paragraph feature templates and above-mentioned grammatical paragraph position feature template, are parsed above-mentioned paragraph by paragraph The judicial document parsed is needed, obtains judicial document analysis result.
Further, above-mentioned resolution unit includes:Extraction module, for being extracted in the judicial document that is parsed from above-mentioned needs Target paragraph;Matching module, for for above-mentioned target paragraph matching corresponding to grammatical paragraph feature templates;First parsing mould Block, it is used for:If the match is successful, using the grammatical paragraph feature templates matched, above-mentioned target paragraph is parsed, is obtained corresponding Analysis result, and jump to the process of analysis of next target paragraph;Second parsing module, is used for:If it fails to match, to be upper Grammatical paragraph position feature template corresponding to stating target paragraph matching, if the match is successful, uses the grammatical paragraph position matched Feature templates are put, parse above-mentioned target paragraph, obtain corresponding analysis result, and jump to the resolution flow of next target paragraph Journey.
Further, said apparatus also includes:Recording unit, for during above-mentioned target paragraph is parsed, if right The analysis result answered is sky, then at least records the sequence number of the judicial document of above-mentioned needs parsing and above-mentioned target paragraph;Second Fills unit, for record result to be filled into above-mentioned judicial domain body.
Further, said apparatus also includes:4th construction unit, for being needed in the above-mentioned syntax using structure, parsing The judicial document to be parsed, after obtaining judicial document analysis result, according to above-mentioned judicial document analysis result, structure respectively works as thing Incidence relation between people;First statistic unit, for counting the Numeric Attributes of each party;Second statistic unit, use After the completion of the incidence relation structure between all parties, the statistics of each dimension of the incidence relation of each party is counted Value;3rd fills unit, for by the Numeric Attributes of the incidence relation between above-mentioned all parties, above-mentioned each party with And the statistical value of each dimension of the incidence relation of above-mentioned each party is filled into above-mentioned judicial domain body.
In embodiments of the present invention, by the way of being drawn a portrait based on judicial domain ontological construction party, by from advance Target party is searched in the judicial domain body of structure, wherein, comprising Ontological concept and for describing in judicial domain body The structured data of the attribute of Ontological concept, Ontological concept include party;After target party is found, from for describing this In the structured data of the attribute of body concept choose or receive user input structured data in be used for target party is described Attribute structured data;According to selection or reception the structured data for being used to describe the attribute of target party, structure Party's portrait of target party, has reached the dependency structure number of the attribute by selecting the party in judicial domain body The purpose of the portrait of the party is built according to this, it is achieved thereby that the technique effect of structure party portrait, and then solve automatically The technical problem of party's portrait can not be built in correlation technique automatically.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, forms the part of the application, this hair Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow chart of the method for optional structure party portrait according to embodiments of the present invention;
Fig. 2 is a kind of schematic diagram of the device of optional structure party portrait according to embodiments of the present invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people The every other embodiment that member is obtained under the premise of creative work is not made, it should all belong to the model that the present invention protects Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, " Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use Data can exchange in the appropriate case, so as to embodiments of the invention described herein can with except illustrating herein or Order beyond those of description is implemented.In addition, term " comprising " and " having " and their any deformation, it is intended that cover Cover it is non-exclusive include, be not necessarily limited to for example, containing the process of series of steps or unit, method, system, product or equipment Those steps or unit clearly listed, but may include not list clearly or for these processes, method, product Or the intrinsic other steps of equipment or unit.
Embodiment 1
According to embodiments of the present invention, there is provided it is a kind of build party portrait embodiment of the method, it is necessary to explanation, The step of flow of accompanying drawing illustrates can perform in the computer system of such as one group computer executable instructions, also, , in some cases, can be with different from shown in order execution herein although showing logical order in flow charts The step of going out or describing.
Fig. 1 is a kind of flow chart of the method for optional structure party portrait according to embodiments of the present invention, such as Fig. 1 institutes Show, this method comprises the following steps:
Step S102, target party is searched from the judicial domain body built in advance, wherein, in judicial domain body Comprising Ontological concept and the attribute for describing Ontological concept structured data, Ontological concept includes party;
Step S104, after target party is found, selected from the structured data of the attribute for describing Ontological concept Take or receive the structured data for being used to describe the attribute of target party in the structured data of user's input;
Step S106, according to selection or reception the structured data for being used to describe the attribute of target party, structure Party's portrait of target party.
It should be noted that according to the professional standard such as China's laws and regulations and people's court's Information System configuration technical specification (abbreviation method mark) can build the judicial domain body centered on judicial party.Wherein, judicial domain body includes body The structured data of concept and the attribute for describing Ontological concept.Herein, the Ontological concept of core is except including in judicial document Outside the party being related to, can also include case, applicable law, case by, accept the concepts such as law court, time, and judicial text The other information being related in book can be as the attribute of these concepts.During implementation, method mark and law related data can be used The type and value of specification Ontological concept and the attribute for describing Ontological concept, reach with the main concept in judicial document and Express consistent purpose.For example, judicial domain body can be database, Ontological concept can be " case ", describe body The structured data of the attribute of concept " case " can be the type of case, e.g., criminal case, civil case etc..Led in the administration of justice In the body of domain, the structured data of attribute of the Ontological concept with describing Ontological concept is corresponding to be stored.
Based on technical scheme provided by the invention, when user needs to build the party of certain party (i.e. target party) During portrait, first target party can be found out from all Ontological concepts of judicial domain body;Finding the target After party, then choose from all structured datas for the attribute for describing Ontological concept oneself needs be used for the mesh is described Mark the part or all of structured data of the attribute of party;Finally according to the part or all of structured data of selection, the mesh is built Mark party's portrait of party.In addition, in actual mechanical process, user is when building party's portrait, it is also possible to can be defeated Enter judicial domain body originally without Ontological concept and its association attributes, now, on the one hand, system start build party draw As after, can the need user and structured data of Ontological concept that judicial domain body just had originally and its association attributes exports To user interface, and presented by way of figure/form;On the other hand, system can also export user's request but judicial neck Domain body originally without Ontological concept and its association attributes list.
Due to judicial domain body saved based on judicial document extraction it is many can accurately describe party and The structured data of association attributes, thus can be accurately and accurately based on judicial document structure party using above-mentioned technical proposal Portrait.
By the embodiment of the present invention, by the way of being drawn a portrait based on judicial domain ontological construction party, reach and passed through The dependency structure data of the attribute of the party in judicial domain body are selected to build the purpose of the portrait of the party, so as to The technique effect of automatic structure party portrait is realized, and then solves and can not build party's portrait in correlation technique automatically Technical problem.
Alternatively, according to selection or reception the structured data for being used to describe the attribute of target party, mesh is built Party's portrait of mark party includes:
S2, in the case where target party is individual party, according to the category for being used to describe target party of selection Property part or all of structured data, build individual party party portrait;
S4, in the case where target party is colony party, according to the category for being used to describe target party of selection Property part or all of structured data, building group party party portrait.
Because colony party includes multiple individual parties with incidence relation, therefore building group party's When party draws a portrait, except needing in building group party in addition to each individual, it is also necessary to build the pass between these individuals Connection relation.
It should be noted that the embodiment of the present invention, which is one kind, utilizes domain body and machine learning techniques, computer is realized It is automatically based upon the method for judicial document structure party's portrait.Certain man-machine interaction is needed in building process, such as by user Input and the various demands of adjustment structure party's portrait, it is other to work what is be automatically performed by computer.The present invention can efficiently, It is accurately finished the processing and analysis of a large amount of judicial documents, structure party's portrait;And the sum of user's adjustment can be timely responded to Newly-increased demand, the difference of party's portrait is shown from result data, meets the needs of user constantly excavates fresh information.This Invention is simultaneously suitable for structure party's individual portrait and colony's portrait.
Alternatively, judicial domain body is built by following steps:
S6, according to Ontological concept and the attribute for describing Ontological concept, it is determined that for parsing the grammatical of judicial document Selective variable corresponding to Feature Words and Feature Words;
S8, the selective variable according to corresponding to the Feature Words and Feature Words of determination, the structure syntax;
S10, using the syntax of structure, parsing needs the judicial document parsed, obtains judicial document analysis result;
S12, judicial document analysis result is filled into judicial domain body.
That is, when implementing, in order to enrich, expand existing judicial domain body, judicial domain body can be used, specifically The Ontological concept in judicial domain body and the attribute for describing Ontological concept can be used, structure computer can solve automatically The syntax of judicial document are analysed, wherein, the syntax of judicial document are the frame mode of language, include composition and Bianization the ﹐ phrases of word With the tissue of sentence.And using the syntax of structure, the parsing judicial document that more newly-increased needs parse, and then by judicial document Analysis result is filled into judicial domain body, pair for the corresponding Ontological concept that can be specifically filled into judicial domain body Answer in attribute.Wherein, the syntax are based on context-free grammar.When parsing document using the syntax, mainly with judgement document In parsed based on single sentence (hereinafter referred to as simple sentence), the correlation required for structure party's portrait is obtained from simple sentence Information.The term of the grammatical Feature Words and selective variable both is from judicial domain body.
It should be noted that after parsing judicial document every time, system can be independent to each judicial document analysis result Preserve, while the data of all accumulations can also be uniformly saved together.For unified preserving type, due to all The judicial document analysis result that the secondary judicial document of parsing obtains will be merged so that result set is constantly accumulated, for structure The structured data for building party's portrait (including individual party portrait and all parties portrait) is enriched constantly, increased, so as to Fine and comprehensive party's portrait can be formed.Specifically, when building party's portrait, user can select as needed Select this, the data of former each time, or even all time data accumulation results.Meanwhile technical solution of the present invention can also utilize The various data of party's portrait are built, document is parsed with the continuous strengthening system of the method for machine learning and structure party draws a portrait Ability.
Alternatively, after selective variable corresponding to the Feature Words and Feature Words according to determination, the structure syntax, on Stating method also includes:
S14, obtain the style of writing feature of judicial document;
S16, according to the style of writing feature of grammatical and judicial document, build grammatical paragraph feature templates and grammatical paragraph position is special Template is levied, corresponding template characteristic and grammatical subset are included in each template,
Accordingly, using the syntax of structure, parsing needs the judicial document parsed, obtains judicial document analysis result bag Include:
S18, use the grammatical paragraph feature templates of structure, or grammatical paragraph feature templates and grammatical paragraph position feature Template, paragraph by paragraph parsing need the judicial document parsed, obtain judicial document analysis result.
Usually, judicial document, which can all include, appeals paragraph, judgement paragraph, true paragraph and law court to think paragraph, and Every kind of paragraph can all have the exclusive style of writing feature of oneself.Different paragraphs often has different style of writing features, for example, appealing section Falling is plaintiff describes to prosecute the paragraph of defendant why, is case " reason paragraph ";Judgement paragraph is according to after law legal principle The paragraph made decisions, it is case " result paragraph ";True paragraph is the description paragraph of generation thing between former defendant, is case " the objective description paragraph " of part;Law court thinks that paragraph is the paragraph that judge does reason according to prosecution content, the fact, evidence, is case " reason things out paragraph " of part.
Thus according to the style of writing feature of judicial document and and style of writing of the description with different characteristic used in grammatical, structure Grammatical paragraph feature templates and grammatical paragraph position feature template are built, each template includes template characteristic and corresponding syntax Collect two parts.In use, the two templates will guide computer software on fixed paragraph and paragraph position using most suitably used Grammatical subset so that the syntax parse the performance of judicial document and the degree of accuracy all greatly improves.
Alternatively, need what is parsed using grammatical paragraph feature templates and grammatical paragraph position feature template, paragraph by paragraph parsing Judicial document, obtaining judicial document analysis result includes:
S20, the target paragraph extracted from the judicial document for needing to parse;
S22, for grammatical paragraph feature templates corresponding to target paragraph matching;
S24, if the match is successful, using the grammatical paragraph feature templates matched, target paragraph is parsed, is obtained corresponding Analysis result, and jump to the process of analysis of next target paragraph;
S26, if it fails to match, for target paragraph matching corresponding to grammatical paragraph position feature template, if the match is successful, Then using the grammatical paragraph position feature template matched, target paragraph is parsed, obtains corresponding analysis result, and jump to down The process of analysis of one target paragraph.
That is, when implementing, each paragraph of the judicial document of needs parsing is first set to match grammatical paragraph feature templates, if The match is successful, then calls the grammatical paragraph feature templates matched, and the paragraph is parsed with the grammatical subset in the template, and will solution The information separated out is filled into the corresponding attribute in judicial domain body.If it fails to match, then makes current paragraph matching text Method paragraph position feature template, now if the match is successful, then the paragraph is parsed using the grammatical subset of the template, and will parsing Information out is filled into the corresponding attribute in judicial domain body, now if it fails to match, then into next paragraph Process of analysis, untill having handled whole paragraphs of the paperwork.
Further, after all judicial documents are parsed, system can also belong to according to the party parsed Property, the incidence relation between party is built, and counts the Numeric Attributes of each party, be i.e. property value, based on this To count the Numeric Attributes of party colony.After the completion of party's incidence relation structure, each party's dependency relation is counted Each dimension statistical value, count each dimension statistical value of the relation of party colony based on this, and by these Property value, relation and statistical value are all stored in database.
Further, it is possible to show party's individual portrait using all data in user interface and above-mentioned database Drawn a portrait with colony.When the attribute that user selects specific individual, colony to gather in interface, system can pass through OLAP technologies Party's individual and the specific dimension data and aggregated data of colony is presented.
It should be noted that in above-mentioned various matchings, including but not limited to template matches and synonym can be used to arrange The method of table matching is matched.
Alternatively, during target paragraph is parsed, the above method also includes:
S28, if corresponding analysis result is sky, at least record needs the sequence number and target phase of the judicial document parsed Fall;Record result is filled into judicial domain body.
That is, in resolving, if grammatical paragraph feature templates or the success of grammatical paragraph position feature template matches, , then can be by the Noumenon property set of document sequence number, sentence and be likely to require filling but the information parsed is sky All remember among daily record.So, when user clicks on oneself selection but barren attribute, system can be with the shape of list Corresponding judicial document and specific paragraph, sentence therein etc. is presented in formula.
Further, for can be to these paragraphs and/or sentence either with or without the paragraph and/or sentence that the match is successful, system Son carries out data mining, merges identical paragraph and/or sentence, and attempt with the other attribute datas obtained to these sections Fall and/or sentence is matched, count the Ontological concept and association attributes that may be included in these paragraphs and/or sentence.Separately Outside, the automatic study that Frequent episodes method carries out the syntax can also be used but be not limited to, so that system developer and guardian are set Meter writes the new syntax.
Alternatively, need the judicial document that parses in the syntax using structure, parsing, obtain judicial document analysis result it Afterwards, the above method also includes:
S30, according to judicial document analysis result, build the incidence relation between all parties;
S32, count the Numeric Attributes of each party;
S34, after the completion of the incidence relation between all parties is built, count each dimension of the incidence relation of each party The statistical value of degree;
S36, by the pass of the incidence relation between all parties, the Numeric Attributes of each party and each party The statistical value of each dimension of connection relation is filled into judicial domain body.
Embodiment 2
According to embodiments of the present invention, there is provided a kind of device embodiment for building party's portrait.
Fig. 2 is a kind of schematic diagram of the device of optional structure party portrait according to embodiments of the present invention, such as Fig. 2 institutes Show, the device includes:Searching unit 202, for searching target party from the judicial domain body built in advance, wherein, Structured data comprising Ontological concept and the attribute for describing Ontological concept in judicial domain body, Ontological concept include working as thing People;Processing unit 204, for after target party is found, from the structured data of the attribute for describing Ontological concept Choose or receive the structured data for being used to describe the attribute of target party in the structured data of user's input;First structure Unit 206, for being worked as according to selection or reception the structured data for being used to describe the attribute of target party, structure target Party's portrait of thing people.
It should be noted that according to the professional standard such as China's laws and regulations and people's court's Information System configuration technical specification (abbreviation method mark) can build the judicial domain body centered on judicial party.Wherein, judicial domain body includes body The structured data of concept and the attribute for describing Ontological concept.Herein, the Ontological concept of core is except including in judicial document Outside the party being related to, can also include case, applicable law, case by, accept the concepts such as law court, time, and judicial text The other information being related in book can be as the attribute of these concepts.During implementation, method mark and law related data can be used The type and value of specification Ontological concept and the attribute for describing Ontological concept, reach with the main concept in judicial document and Express consistent purpose.For example, judicial domain body can be database, Ontological concept can be " case ", describe body The structured data of the attribute of concept " case " can be the type of case, e.g., criminal case, civil case etc..Led in the administration of justice In the body of domain, the structured data of attribute of the Ontological concept with describing Ontological concept is corresponding to be stored.
Based on technical scheme provided by the invention, when user needs to build the party of certain party (i.e. target party) During portrait, first target party can be found out from all Ontological concepts of judicial domain body;Finding the target After party, then choose from all structured datas for the attribute for describing Ontological concept oneself needs be used for the mesh is described Mark the part or all of structured data of the attribute of party;Finally according to the part or all of structured data of selection, the mesh is built Mark party's portrait of party.In addition, in actual mechanical process, user is when building party's portrait, it is also possible to can be defeated Enter judicial domain body originally without Ontological concept and its association attributes, now, on the one hand, system start build party draw As after, can the need user and structured data of Ontological concept that judicial domain body just had originally and its association attributes exports To user interface, and presented by way of figure/form;On the other hand, system can also export user's request but judicial neck Domain body originally without Ontological concept and its association attributes list.
Due to judicial domain body saved based on judicial document extraction it is many can accurately describe party and The structured data of association attributes, thus can be accurately and accurately based on judicial document structure party using above-mentioned technical proposal Portrait.
By the embodiment of the present invention, by the way of being drawn a portrait based on judicial domain ontological construction party, reach and passed through The dependency structure data of the attribute of the party in judicial domain body are selected to build the purpose of the portrait of the party, so as to The technique effect of automatic structure party portrait is realized, and then solves and can not build party's portrait in correlation technique automatically Technical problem.
Alternatively, above-mentioned first construction unit includes:First structure module, for being individual party in target party In the case of, according to the part or all of structured data for being used to describe the attribute of target party of selection, structure individual works as thing Party's portrait of people;Second structure module, in the case of being colony party in target party, according to the use of selection In the part or all of structured data of the attribute of description target party, party's portrait of building group party.
Alternatively, said apparatus also includes:Determining unit, it is general according to body for after judicial domain body is obtained Considering the attribute for describing Ontological concept, it is determined that for parsing choosing corresponding to the grammatical Feature Words and Feature Words of judicial document Selecting property variable;Second construction unit, for selective variable corresponding to the Feature Words and Feature Words according to determination, the structure syntax; Resolution unit, for the syntax using structure, parsing needs the judicial document parsed, obtains judicial document analysis result;First Fills unit, for judicial document analysis result to be filled into judicial domain body.
Alternatively, said apparatus also includes:Acquiring unit, for selection corresponding to the Feature Words and Feature Words according to determination Property variable, after the structure syntax, obtain the style of writing feature of judicial document;3rd construction unit, for according to the syntax and administration of justice text The style of writing feature of book, grammatical paragraph feature templates and grammatical paragraph position feature template are built, are included in each template corresponding Template characteristic and grammatical subset, wherein, resolution unit is additionally operable to:Use the grammatical paragraph feature templates of structure, or the syntax Paragraph feature templates and grammatical paragraph position feature template, paragraph by paragraph parsing need the judicial document parsed, obtain judicial document solution Analyse result.
Alternatively, above-mentioned resolution unit includes:Extraction module, for the target extracted from the judicial document for needing to parse Paragraph;Matching module, for grammatical paragraph feature templates corresponding to being matched for target paragraph;First parsing module, is used for:If With success, then using the grammatical paragraph feature templates matched, target paragraph is parsed, obtains corresponding analysis result, and redirect To the process of analysis of next target paragraph;Second parsing module, is used for:If it fails to match, matched for target paragraph corresponding Grammatical paragraph position feature template, if the match is successful, use the grammatical paragraph position feature template matched, parse target Paragraph, corresponding analysis result is obtained, and jump to the process of analysis of next target paragraph.
Alternatively, said apparatus also includes:Recording unit, for during target paragraph is parsed, if corresponding solution Result is analysed as sky, then at least record needs the sequence number and target paragraph of the judicial document parsed;Second fills unit, for inciting somebody to action Record result is filled into judicial domain body.
Alternatively, said apparatus also includes:4th construction unit, for needing to parse in the syntax using structure, parsing Judicial document, after obtaining judicial document analysis result, according to judicial document analysis result, build the pass between all parties Connection relation;First statistic unit, for counting the Numeric Attributes of each party;Second statistic unit, for respectively working as thing After the completion of incidence relation structure between people, the statistical value of each dimension of the incidence relation of each party is counted;3rd filling Unit, for by the association of the incidence relation between all parties, the Numeric Attributes of each party and each party The statistical value of each dimension of relation is filled into judicial domain body.
It should be noted that device section Example and corresponding method section Example are same or like;Device part The operation principle of each functional unit/module in embodiment, the function of realizing and the technique effect that reaches respectively with it is corresponding Corresponding step in method section Example is same or like, will not be repeated here.
The device of above-mentioned structure party portrait includes processor and memory, above-mentioned searching unit, processing unit and the One construction unit etc. stores in memory as program unit, by the said procedure of computing device storage in memory Unit.
Kernel is included in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can set one Or more, parse content of text by adjusting kernel parameter.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/ Or the form such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM), memory includes at least one deposit Store up chip.
Present invention also provides a kind of embodiment of computer program product, when being performed on data processing equipment, fits In the program code for performing initialization there are as below methods step:Target is searched from the judicial domain body built in advance and works as thing People, wherein, the structured data comprising Ontological concept and the attribute for describing Ontological concept, Ontological concept in judicial domain body Including party;After target party is found, from the structured data of the attribute for describing Ontological concept choose or Receive the structured data for being used to describe the attribute of target party in the structured data of user's input;According to selection or connect That receives is used to describe the structured data of the attribute of target party, party's portrait of structure target party.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not have in some embodiment The part of detailed description, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed technology contents, others can be passed through Mode is realized.Wherein, device embodiment described above is only schematical, such as the division of the unit, Ke Yiwei A kind of division of logic function, can there is an other dividing mode when actually realizing, for example, multiple units or component can combine or Person is desirably integrated into another system, or some features can be ignored, or does not perform.Another, shown or discussed is mutual Between coupling or direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some interfaces, unit or module Connect, can be electrical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple On unit.Some or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially The part to be contributed in other words to prior art or all or part of the technical scheme can be in the form of software products Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer Equipment (can be personal computer, server or network equipment etc.) perform each embodiment methods described of the present invention whole or Part steps.And foregoing storage medium includes:USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes Medium.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should It is considered as protection scope of the present invention.

Claims (10)

  1. A kind of 1. method for building party's portrait, it is characterised in that including:
    Target party is searched from the judicial domain body built in advance, wherein, body is included in the judicial domain body The structured data of concept and the attribute for describing Ontological concept, the Ontological concept include party;
    After the target party is found, from the structured data of the attribute for describing Ontological concept choose or Receive the structured data for being used to describe the attribute of the target party in the structured data of user's input;
    According to selection or reception the structured data for being used to describe the attribute of the target party, build the target and work as Party's portrait of thing people.
  2. 2. according to the method for claim 1, it is characterised in that build the judicial domain body by following steps:
    According to the Ontological concept and the attribute for describing Ontological concept, it is determined that for parsing the grammatical of judicial document Selective variable corresponding to Feature Words and Feature Words;
    The selective variable according to corresponding to the Feature Words and Feature Words of determination, builds the syntax;
    Using the syntax of structure, parsing needs the judicial document parsed, obtains judicial document analysis result;
    The judicial document analysis result is filled into the judicial domain body.
  3. 3. according to the method for claim 2, it is characterised in that in selection corresponding to the Feature Words and Feature Words according to determination Property variable, build it is described the syntax after, methods described also includes:
    Obtain the style of writing feature of judicial document;
    According to the style of writing feature of described grammatical and described judicial document, build grammatical paragraph feature templates and grammatical paragraph position is special Template is levied, corresponding template characteristic and grammatical subset are included in each template,
    Wherein, using the syntax of structure, parsing needs the judicial document parsed, and obtaining judicial document analysis result includes:
    Use the grammatical paragraph feature templates of structure, or the grammatical paragraph feature templates and the grammatical paragraph position Feature templates, the judicial document for needing to parse is parsed paragraph by paragraph, obtains judicial document analysis result.
  4. 4. according to the method for claim 3, it is characterised in that use the grammatical paragraph feature templates and the grammatical section Dropping place puts feature templates, parses the judicial document for needing to parse paragraph by paragraph, obtaining judicial document analysis result includes:
    The target paragraph extracted from the judicial document for needing to parse;
    For grammatical paragraph feature templates corresponding to target paragraph matching;
    If the match is successful, using the grammatical paragraph feature templates matched, the target paragraph is parsed, obtains corresponding parsing As a result, and the process of analysis of next target paragraph is jumped to;
    If it fails to match, for grammatical paragraph position feature template corresponding to target paragraph matching, if the match is successful, make With the grammatical paragraph position feature template matched, the target paragraph is parsed, obtains corresponding analysis result, and jump to down The process of analysis of one target paragraph.
  5. 5. according to the method for claim 4, it is characterised in that during the target paragraph is parsed, methods described Also include:
    If corresponding analysis result is sky, the sequence number of the judicial document for needing to parse and the target phase are at least recorded Fall;
    Record result is filled into the judicial domain body.
  6. 6. according to the method for claim 2, it is characterised in that in the syntax using structure, parsing needs what is parsed Judicial document, after obtaining judicial document analysis result, methods described also includes:
    According to the judicial document analysis result, the incidence relation between all parties is built;
    Count the Numeric Attributes of each party;
    After the completion of incidence relation structure between all parties, the statistics of each dimension of the incidence relation of each party is counted Value;
    By the incidence relation between all parties, the Numeric Attributes of each party and each party The statistical value of each dimension of incidence relation be filled into the judicial domain body.
  7. A kind of 7. device for building party's portrait, it is characterised in that including:
    Searching unit, for searching target party from the judicial domain body built in advance, wherein, the judicial domain sheet The structured data comprising Ontological concept and the attribute for describing Ontological concept, the Ontological concept include party in body;
    Processing unit, for after the target party is found, from the structure of the attribute for describing Ontological concept The structure number for being used to describe the attribute of the target party in the structured data of user's input is chosen or received in data According to;
    First construction unit, for according to selection or reception the structure number for being used to describe the attribute of the target party According to the party for building the target party draws a portrait.
  8. 8. device according to claim 7, it is characterised in that described device also includes:
    Determining unit, for after judicial domain body is obtained, according to the Ontological concept and for describing Ontological concept The attribute, it is determined that for parsing selective variable corresponding to the grammatical Feature Words and Feature Words of judicial document;
    Second construction unit, for selective variable corresponding to the Feature Words and Feature Words according to determination, build the syntax;
    Resolution unit, for the syntax using structure, parsing needs the judicial document parsed, obtains judicial document parsing knot Fruit;
    First fills unit, for the judicial document analysis result to be filled into the judicial domain body.
  9. 9. device according to claim 8, it is characterised in that described device also includes:
    Acquiring unit, for selective variable corresponding to the Feature Words and Feature Words according to determination, after building the syntax, obtain Take the style of writing feature of judicial document;
    3rd construction unit, for the style of writing feature according to described grammatical and described judicial document, build grammatical paragraph character modules Plate and grammatical paragraph position feature template, comprising corresponding template characteristic and grammatical subset in each template,
    Wherein, the resolution unit is additionally operable to:It is special using the grammatical paragraph feature templates of structure, or the grammatical paragraph Template and the grammatical paragraph position feature template are levied, the judicial document for needing to parse is parsed paragraph by paragraph, obtains judicial document Analysis result.
  10. 10. device according to claim 9, it is characterised in that the resolution unit includes:
    Extraction module, for the target paragraph extracted from the judicial document for needing to parse;
    Matching module, for for the target paragraph matching corresponding to grammatical paragraph feature templates;
    First parsing module, is used for:If the match is successful, using the grammatical paragraph feature templates matched, the target is parsed Paragraph, corresponding analysis result is obtained, and jump to the process of analysis of next target paragraph;
    Second parsing module, is used for:If it fails to match, for grammatical paragraph position feature mould corresponding to target paragraph matching Plate, if the match is successful, using the grammatical paragraph position feature template matched, the target paragraph is parsed, obtained corresponding Analysis result, and jump to the process of analysis of next target paragraph.
CN201610792049.4A 2016-08-31 2016-08-31 Construct the method and device of party's portrait Active CN107784024B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610792049.4A CN107784024B (en) 2016-08-31 2016-08-31 Construct the method and device of party's portrait

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610792049.4A CN107784024B (en) 2016-08-31 2016-08-31 Construct the method and device of party's portrait

Publications (2)

Publication Number Publication Date
CN107784024A true CN107784024A (en) 2018-03-09
CN107784024B CN107784024B (en) 2019-04-09

Family

ID=61451372

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610792049.4A Active CN107784024B (en) 2016-08-31 2016-08-31 Construct the method and device of party's portrait

Country Status (1)

Country Link
CN (1) CN107784024B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110968662A (en) * 2018-09-27 2020-04-07 北京国双科技有限公司 Judicial data processing method and device, storage medium and processor
CN111311177A (en) * 2020-01-20 2020-06-19 北京合信力科技有限公司 Method and device for maintaining timeliness of litigation cases
CN112581326A (en) * 2019-09-30 2021-03-30 北京国双科技有限公司 Method, device, storage medium and equipment for discriminating false litigation

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008171A (en) * 2014-06-03 2014-08-27 中国科学院计算技术研究所 Legal database establishing method and legal retrieving service method
WO2015006044A2 (en) * 2013-07-11 2015-01-15 Neura, Inc. Data consolidation mechanisms for internet of things integration platform
CN104408093A (en) * 2014-11-14 2015-03-11 中国科学院计算技术研究所 News event element extracting method and device
US20160182516A1 (en) * 2014-12-19 2016-06-23 Bank Of America Corporation Presenting authorized data to a target system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015006044A2 (en) * 2013-07-11 2015-01-15 Neura, Inc. Data consolidation mechanisms for internet of things integration platform
CN104008171A (en) * 2014-06-03 2014-08-27 中国科学院计算技术研究所 Legal database establishing method and legal retrieving service method
CN104408093A (en) * 2014-11-14 2015-03-11 中国科学院计算技术研究所 News event element extracting method and device
US20160182516A1 (en) * 2014-12-19 2016-06-23 Bank Of America Corporation Presenting authorized data to a target system

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110968662A (en) * 2018-09-27 2020-04-07 北京国双科技有限公司 Judicial data processing method and device, storage medium and processor
CN112581326A (en) * 2019-09-30 2021-03-30 北京国双科技有限公司 Method, device, storage medium and equipment for discriminating false litigation
WO2021063072A1 (en) * 2019-09-30 2021-04-08 北京国双科技有限公司 Method and apparatus for identifying false litigation, and storage medium and device
CN111311177A (en) * 2020-01-20 2020-06-19 北京合信力科技有限公司 Method and device for maintaining timeliness of litigation cases

Also Published As

Publication number Publication date
CN107784024B (en) 2019-04-09

Similar Documents

Publication Publication Date Title
CN108052583B (en) E-commerce ontology construction method
CN103885934B (en) Method for automatically extracting key phrases of patent documents
US10565233B2 (en) Suffix tree similarity measure for document clustering
KR101536520B1 (en) Method and server for extracting topic and evaluating compatibility of the extracted topic
CN109299271B (en) Training sample generation method, text data method, public opinion event classification method and related equipment
CN110377900A (en) Checking method, device, computer equipment and the storage medium of Web content publication
CN104077407B (en) A kind of intelligent data search system and method
CN110334178A (en) Data retrieval method, device, equipment and readable storage medium storing program for executing
CN109726274A (en) Problem generation method, device and storage medium
CN108345686A (en) A kind of data analysing method and system based on search engine technique
CN113312474A (en) Similar case intelligent retrieval system of legal documents based on deep learning
CN106570013A (en) Method and device for processing page access data
CN109446376A (en) Method and system for classifying voice through word segmentation
CN109299277A (en) The analysis of public opinion method, server and computer readable storage medium
CN107943792A (en) A kind of statement analytical method, device and terminal device, storage medium
CN110297880A (en) Recommended method, device, equipment and the storage medium of corpus product
CN110134844A (en) Subdivision field public sentiment monitoring method, device, computer equipment and storage medium
CN109522396B (en) Knowledge processing method and system for national defense science and technology field
CN107784024B (en) Construct the method and device of party's portrait
CN109992665A (en) A kind of classification method based on the extension of problem target signature
KR101803150B1 (en) Important precedents extraction and sorting method using Big Data
CN108153781A (en) The method and apparatus for extracting the keyword of business scope
CN106934049B (en) News question selection analysis method and device
CN109558531A (en) News information method for pushing, device and computer equipment
CN113688623A (en) Aspect level emotion analysis method based on deep learning

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
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: Method and device for creating portrait of party

Effective date of registration: 20190531

Granted publication date: 20190409

Pledgee: Shenzhen Black Horse World Investment Consulting Co.,Ltd.

Pledgor: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd.

Registration number: 2019990000503

PE01 Entry into force of the registration of the contract for pledge of patent right
CP02 Change in the address of a patent holder

Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing

Patentee after: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd.

Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A

Patentee before: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd.

PP01 Preservation of patent right

Effective date of registration: 20240604

Granted publication date: 20190409

PP01 Preservation of patent right