CN107704572A - The creation angle method for digging and device of people entities - Google Patents
The creation angle method for digging and device of people entities Download PDFInfo
- Publication number
- CN107704572A CN107704572A CN201710914887.9A CN201710914887A CN107704572A CN 107704572 A CN107704572 A CN 107704572A CN 201710914887 A CN201710914887 A CN 201710914887A CN 107704572 A CN107704572 A CN 107704572A
- Authority
- CN
- China
- Prior art keywords
- keyword
- network
- word
- personage
- people entities
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The invention provides the creation angle method for digging and device of a kind of people entities, wherein, this method includes:First, article metadata is obtained from network data source, and parses the people entities word included in article metadata and the keyword related to people entities word.Then, personage's keyword network is built as network node by the use of people entities word and keyword, and label is added to the network node in personage's keyword network.And then using same label as corporations' partitioning standards, corporations' division, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation are carried out to the network node in personage's keyword network.The embodiment of the present invention can not only provide more novel writing angle for creator, can also widen the creation thought of creator, help creator to create the article of more diversification.
Description
Technical field
The present invention relates to technical field of internet application, more particularly to a kind of creation angle method for digging of people entities
And device.
Background technology
With the development of social informatization, while information emerges in multitude, requirement of the people for information also increasingly swashs
Increase.Bulk information is mainly presented in the form of intricate, fast changing information flow at present.Wherein, the presentation form of information flow
Mainly there are word, picture and video etc., it is more representational to have today's tops, everyday Netease's news, bulletin etc..
In addition, as personal user is used the depth of internet, arisen at the historic moment from media as emerging media.From matchmaker
Body is also known as " Civil Media " or " individual media ", is privatization, the disseminator of popular, generalization, autonomy-oriented, to modernize,
The means of electronization, normative and non-standard information new media is transmitted to not specific most of or specific single people
General name.The media of development from to(for) current information stream serves hugely impetus.And it is in different poses and with different expressions from media, the good and the bad is not
Together, the outstanding inspiration that from media audient can be allowed to be lived or contribute to success of career, allow it is found that living
Meaning and value.But most from media is some simple " network transplanting ", some trifles, even not are recorded
The content of health.For a long time, new meaning and innovative point are lacked gradually from the content of media.And for creator, creation
The main thought of one article is to surround one or more entities, from several angles, personal viewpoint and understanding in addition,
Finally arrange and form article.And field known to creator and thinking angle are limited, shape can not be created to all entities
Into complete framework.Can open-and-shut form if the angle that each entity is created can be polymerized to one, then creator
Just readily appreciate which aspect had been write, which aspect was not created also, and which aspect is that the comparison write is frequent
's.This creation for carrying out new angle for author has and obviously helped, and also has simultaneously for reader permanent sustainable
Read value.
But there is presently no a method that writing angle and thinking can be effectively provided for creator.Due to wound
It is a comparison abstract concept as angle, therefore possible creation angle how is found out from an article and how from big
It is to face huge challenge at present that the most important angle of entity is found out in the creation angle of amount.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State the creation angle method for digging and device of the people entities of problem.
According to an aspect of the present invention, a kind of creation angle method for digging of people entities is disclosed, including:
Article metadata is obtained from network data source, and parses the people entities included in the article metadata
Word and the keyword related to the people entities word;
Personage's keyword network is built as network node by the use of the people entities word and the keyword, to the people
Network node addition label in thing keyword network;
Using same label as corporations' partitioning standards, corporations are carried out to the network node in personage's keyword network and drawn
Point, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
Alternatively, it is described to build personage's keyword net as network node by the use of the people entities word and the keyword
Network, including:
Using the people entities word and keyword as network node, with the connection weight between people entities word and keyword
Connection weight between weight and/or different personage's entity words builds personage's keyword network for side, wherein, the connection weight table
Show the tight ness rating between network node.
Alternatively, the network node in personage's keyword network adds label, including:
Tagged people entities word and/or keyword and the net in personage's keyword network are added using preset
Network node is matched;
If the match is successful, by corresponding label added to the network node that the match is successful, and obtain and the net that the match is successful
Connection weight between network node reaches the network node of predetermined threshold value;
Reach the network node addition same label of predetermined threshold value to the connection weight got.
Alternatively, label is added to the network node in personage's keyword network, including:
Label is added to the network node in personage's keyword network based on Predistribution Algorithm.
Alternatively, the Predistribution Algorithm includes:Label propagation algorithm LPA.
Alternatively, the label includes at least one of:
The attribute information of the people entities word and/or the keyword;
The people information related to the people entities word and/or the keyword;
The event information related to the people entities word and/or the keyword.
Alternatively, it is described using the people entities word and keyword as network node, with people entities word and keyword
Between connection weight and/or different personage's entity words between connection weight for side build personage's keyword network before, also
Including:
Count the connection between connection weight and/or the different personage's entity words between the people entities word and keyword
Weight.
Alternatively, the connection weight between the statistics people entities word and keyword and/or different people entities
Connection weight between word, including:
The article title in the article metadata is extracted, people entities word and key are parsed from the article title
Word;
The co-occurrence word pair occurred in the article title is counted, the co-occurrence word is to the people to occur in same article title
The word pair that thing entity word forms from keyword, different personage's entity words;
The co-occurrence word is calculated to the corresponding weighted value in different articles, and to identical co-occurrence word in different articles
The summation of corresponding weighted value, using as in personage's keyword network with co-occurrence word to corresponding people entities word and keyword
Between connection weight and/or different personage's entity words between connection weight.
Alternatively, it is described to calculate the co-occurrence word to the corresponding weighted value in different articles, including:
Extract the article text in the article metadata;
The number occurred according to the co-occurrence word to the co-occurrence word included in the article text, calculates the co-occurrence
The weighted value of word pair, wherein, the co-occurrence word is personage's entity word and/or the keyword.
Alternatively, it is described to parse the people entities word and keyword included in the article metadata, including:
The article title in the article metadata is extracted, the article title of extraction is segmented;
High frequency words are filtered according to the word frequency after participle, and part-of-speech tagging is carried out to the word after filtering, wherein, by people's name
Word is labeled as people entities word, and other words related to the people entities word are labeled as keyword.
According to another aspect of the present invention, a kind of creation angle excavating gear of people entities is additionally provided, including:
Parsing module, suitable for obtaining article metadata from network data source, and parse in the article metadata
Comprising people entities word and the keyword related to the people entities word;
Module is built, suitable for building personage's keyword as network node by the use of the people entities word and the keyword
Network, label is added to the network node in personage's keyword network;
Module is excavated, suitable for using same label as corporations' partitioning standards, to the network in personage's keyword network
Node carries out corporations' division, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
Alternatively, the structure module is further adapted for:Using the people entities word and keyword as network node, with personage
The connection weight between connection weight and/or different personage's entity words between entity word and keyword builds personage's key for side
Word network, wherein, the connection weight represents the tight ness rating between network node.
Alternatively, the structure module is further adapted for:Tagged people entities word and/or keyword are added using preset
Matched with the network node in personage's keyword network;
If the match is successful, by corresponding label added to the network node that the match is successful, and obtain and the net that the match is successful
Connection weight between network node reaches the network node of predetermined threshold value;
Reach the network node addition same label of predetermined threshold value to the connection weight got.
Alternatively, the structure module is further adapted for:
Label is added to the network node in personage's keyword network based on Predistribution Algorithm.
Alternatively, the Predistribution Algorithm includes:Label propagation algorithm LPA.
Alternatively, the label includes at least one of:
The attribute information of the people entities word and/or the keyword;
The people information related to the people entities word and/or the keyword;
The event information related to the people entities word and/or the keyword.
Alternatively, described device also includes:Statistical module, suitable for it is described structure module with the people entities word and pass
Keyword is as network node, between the connection weight and/or different personage's entity words between people entities word and keyword
Connection weight is before side builds personage's keyword network, to count the connection weight between the people entities word and keyword
And/or the connection weight between different personage's entity words.
Alternatively, the statistical module is further adapted for:The article title in the article metadata is extracted, from the article mark
People entities word and keyword are parsed in topic;
The co-occurrence word pair occurred in the article title is counted, the co-occurrence word is to the people to occur in same article title
The word pair that thing entity word forms from keyword, different personage's entity words;
The co-occurrence word is calculated to the corresponding weighted value in different articles, and to identical co-occurrence word in different articles
The summation of corresponding weighted value, using as in personage's keyword network with co-occurrence word to corresponding people entities word and keyword
Between connection weight and/or different personage's entity words between connection weight.
Alternatively, the statistical module is further adapted for:Extract the article text in the article metadata;
The number occurred according to the co-occurrence word to the co-occurrence word included in the article text, calculates the co-occurrence
The weighted value of word pair, wherein, the co-occurrence word is personage's entity word and/or the keyword.
Alternatively, the parsing module is further adapted for:The article title in the article metadata is extracted, to the article of extraction
Title is segmented;
High frequency words are filtered according to the word frequency after participle, and part-of-speech tagging is carried out to the word after filtering, wherein, by people's name
Word is labeled as people entities word, and other words related to the people entities word are labeled as keyword.
In accordance with a further aspect of the present invention, a kind of computer program, including computer-readable code are additionally provided, when described
When computer-readable code is run on the computing device, cause the computing device described above based on corporations' division
Create angle method for digging.
In accordance with a further aspect of the present invention, a kind of computer-readable medium is additionally provided, wherein storing as described above
Computer program.
In embodiments of the present invention, first, article metadata is obtained from network data source, and parses article member number
The people entities word and the keyword related to people entities word included in.Then, made using people entities word and keyword
Personage's keyword network is built for network node, and label is added to the network node in personage's keyword network.Finally, with phase
With label as corporations' partitioning standards, corporations' division is carried out to the network node in personage's keyword network, by same corporations
Creation angle of the arbitrary network node as people entities word in this corporation.Thus, the embodiment of the present invention passes through to a large amount of nets
The people entities word and keyword that the excavation of network data is included with extracting in article metadata, closed using each word structure personage
After keyword network, corporations' division is carried out to the network node of the network, so as to be used as this corporation by the use of the word in same corporations
The creation angle of middle people entities word, the cluster of the creation angle of people entities word is realized, so that the creation angle of people entities word
Degree pools can open-and-shut form.The present invention program can not only provide more novel writing angle for creator, also
The creation thought of creator can be widened, helps creator to create the article of more diversification.
Further, creator is helped to carry out article creation using the scheme of the embodiment of the present invention, for the audient of article
Person also has permanent sustainable value.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
According to the accompanying drawings will be brighter to the detailed description of the specific embodiment of the invention, those skilled in the art
Above-mentioned and other purposes, the advantages and features of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings:
Fig. 1 shows the flow signal of the creation angle method for digging of people entities according to an embodiment of the invention
Figure;
Fig. 2 shows personage's keyword schematic network structure according to an embodiment of the invention;
Fig. 3 shows the flow signal of the creation angle method for digging of people entities in accordance with another embodiment of the present invention
Figure;
Fig. 4 shows the structural representation of the creation angle excavating gear of people entities according to an embodiment of the invention
Figure;
Fig. 5 shows the structural representation of the creation angle excavating gear of people entities in accordance with another embodiment of the present invention
Figure;
Fig. 6 shows the frame of the computing device of the creation angle method for digging for performing the people entities according to the present invention
Figure;And
Fig. 7 is shown for keeping or carrying realization according to the creation angle method for digging of the people entities of the present invention
The memory cell of program code.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
In order to solve the above technical problems, the embodiments of the invention provide a kind of creation angle method for digging of people entities.
Fig. 1 shows the schematic flow sheet of the creation angle method for digging of people entities according to an embodiment of the invention.Referring to figure
1, this method can at least include step S102 to step S106.
Step S102, article metadata is obtained from network data source, and parse the people included in article metadata
Thing entity word and the keyword related to people entities word.
In this step, network data source can be included from media, such as interesting history, phoenix news, Tengxun's news, today
Article that top news, Netease's news, everyday bulletin etc. or micro-blog information, wechat public number are delivered, blog articles etc.
Deng.The embodiment of the present invention does not do specific restriction to the source of network data.
Step S104, personage's keyword network is built as network node by the use of people entities word and keyword, and to people
Network node addition label in thing keyword network.
In this step, label include people entities word and/or keyword attribute information, with people entities word and/or
At least one of the related people information of keyword, event information related to people entities word and/or keyword etc..
Wherein, the attribute information of people entities word includes personal essential information, occupation, hobby etc..For example, " Zhuge Liang "
Attribute information include:Occupation is " military counsellor family " and " politician ", and hobby is " reading " etc..The attribute information of keyword includes
The affiliated type of keyword, the implication represented etc..For example, keyword includes for the attribute information of " The Romance of the Three Kingdoms ":Subject matter is to go through
Novel of history subject matter etc..
Step S106, using same label as corporations' partitioning standards, the network node in personage's keyword network is carried out
Corporations divide, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
The personage that the embodiment of the present invention is included by the excavation to a large amount of network datas with extracting in article metadata is real
Pronouns, general term for nouns, numerals and measure words and keyword, after using each word structure personage's keyword network, corporations' division is carried out to the node of the network, so as to
Creation angle by the use of the word in same corporations as people entities word in this corporation, realizes the creation angle of people entities word
Cluster, so that the creation angle collection of people entities word is into can open-and-shut form.The present invention program can not only be creation
Person provides more novel writing angle, can also widen the creation thought of creator, helps creator to create more polynary
The article of change.
Further, creator is helped to carry out article creation using the scheme of the embodiment of the present invention, for the audient of article
Person also has permanent sustainable value.
Step S102 is seen above, in an embodiment of the present invention, because the word in article title is the height to article
Summarize, therefore, the embodiment of the present invention parses people entities word and relative keyword from title.Specifically, extraction text
Article title in chapter metadata, the article title of extraction is segmented.Then according to the word frequency after participle to high frequency words mistake
Filter, and part-of-speech tagging is carried out to the word after filtering, wherein, personage's noun is labeled as people entities word, related to people entities word
Other words be labeled as keyword.
In this embodiment it is possible to using noun and verb as the keyword of candidate, then by word frequency by high frequency words mistake
Filter, for example the high frequency words such as have a meal, live will be filtered.And then using the noun after filtering and verb as keyword, personage
Noun is as people entities word.Certainly, the word of other parts of speech can also be used to implement as keyword, the present invention after participle
Example is not specifically limited to this.
Referring to table 1, the article title and Ge Wen being resolved to from the article in terms of several amusement, history are listed in table 1
People entities word that chapter title is included, the keyword related to people entities word.
Table 1
Step S104 is seen above, in an embodiment of the present invention, network is being used as by the use of people entities word and keyword
When node builds personage's keyword network, network node can be used as using people entities word and keyword, with people entities word and
The connection weight between connection weight and/or different personage's entity words between keyword builds personage's keyword network for side.
Wherein, connection weight represents the tight ness rating between network node.For example, connection weight is bigger, represent between two network nodes
Relation it is closer.
For example, Fig. 2 is to be closed using the people entities word and keyword parsed in table 1 as the personage that network node is built
Keyword network.Keyword " The Romance of the Three Kingdoms " in fig. 2 has been directly connected to 4 personage's entity words, that is, be respectively " Zhuge Liang ",
" Guan Yu ", " Liu is standby " and " Zhang Fei ", wherein the connection weight between " The Romance of the Three Kingdoms " and " Zhuge Liang " is up to 214, with "
Fly " connection weight minimum 69, it follows that the tight ness rating of " Zhuge Liang " and " The Romance of the Three Kingdoms " ratio " Zhang Fei " and " three states drill
The tight ness rating of justice " is larger.Certainly, the numerical value of the connection weight between each network node shown in Fig. 2 is only to illustrate
Property, the embodiment of the present invention is not specifically limited to this.
With continued reference to above step S104, in an embodiment of the present invention, to the network node in personage's keyword network
Adding tagged detailed process can be:
First, added using preset in tagged people entities word and/or keyword and personage's keyword network
Network node is matched.If the match is successful, corresponding label is added to the network node that the match is successful.Then, obtain
Reach the network node of predetermined threshold value with the connection weight between the network node that the match is successful.And then the connection to getting
Weight reaches the network node addition same label of predetermined threshold value.In the embodiment, predetermined threshold value can be set by user,
The embodiment of the present invention is not especially limited to predetermined threshold value.
Wherein, preset added tagged people entities word and/or keyword can be existing personage's knowledge mappings
The word included in network data.Personage's knowledge mapping is can be by the relation between the personage of encyclopaedia structure, such as man and wife, son
The important relationships such as female, brother.But the keyword included in personage's knowledge mapping is considerably less, it is therefore possible to use personage's knowledge
Collection of illustrative plates collection of illustrative plates removes to predict network node in the embodiment of the present invention in personage's keyword network as having added tagged source
Label.
In addition, network node (such as people entities word and keyword) can also using the surrounding network node that is completely embedded as
The label of itself.Each network node has individual probable value for the network node on periphery, exceedes certain threshold by select probability
Label of the network node of value as present networks node.For example, with reference to Fig. 2 content, according to each network being connected with " Zhang San "
Connection weight between node, because the connection weight of people entities word " Zhang San " and keyword " derailed " is of a relatively high.Therefore,
Can be by the label information of " derailed " as " Zhang San ".
In an alternative embodiment of the invention, when adding label to the network node in personage's keyword network, can be based on
Predistribution Algorithm adds label to the network node in personage's keyword network.Wherein, Predistribution Algorithm can include label propagation calculation
Method (Label propagation algorithm, LPA).Label propagation algorithm is a kind of semi-supervised learning method based on figure,
Its basic ideas is to be gone to predict the label information of unmarked node with the label information of marked node.Utilize the relation between sample
The complete graph model of opening relationships, in complete graph, node includes having marked and unlabeled data, and its side represents the tight of two nodes
Density, the label of node pass to other nodes by similarity.Referred herein to tight ness rating be connection weight in foregoing embodiments
Weight, in personage's keyword network, can be transferred to it according to the size of the value of the direct connection weight of network node by label
His network node.Label data is like a source, can be to being labeled without label data, and the similarity of node is got over
Greatly, the easier propagation of label.
For example, with reference to Fig. 2 and foregoing embodiments, the connection weight of people entities word " Zhang San " and people entities word " little Rong "
Also it is higher.Using label propagation algorithm, the label " derailed " of " Zhang San " can be passed to " little Rong ".Thus, connect before not
The contact also established between close keyword and people entities word.
Step S106 is seen above, in an embodiment of the present invention, using same label as corporations' partitioning standards, to Fig. 2
Network node in shown personage's keyword network carries out corporations' division, regard the arbitrary network node in same corporations as this society
The creation angle of people entities word in group.In the illustrated embodiment of table 2, each personage's entity word and its corresponding important angle represent
A corporations after division.
People entities word | Create angle |
Zhang San | Overstep the limit, little Rong, Li Si, divorce, stupid root |
Liu Bei | Straw sandals, Guan Yu, Zhang Fei |
Guan Yu | Liu Bei, force five passes and slay six captains, heat wine cuts Hua Xiong |
Chu Yuan-chang | Kill person who has rendered outstanding service, horse queen, Buddhist monk, beggar, Liu Baiwen |
Little Rong | Zhang San, Li Si, properties division, overstep the limit |
Table 2
In an embodiment of the present invention, creation angle can not only include the content of network node, can also be to net
The label of network node addition.For example, there are some to create angle, such as " divorce ", " stupid root ", " forcing five passes and slay six captains " in table 2
It is that these words can be to network section in preceding step in the people entities keyword network shown in the Fig. 2 not occurred
The label word added during point addition label.Due to the label and its close relation of network node itself, accordingly it is also possible to will
Important creation angle of the label of network node as people entities word in corporations.
Described above, network node can also be used as the label of itself using the surrounding network node being completely embedded.Therefore, draw
In the corporations divided, what some network nodes can't be single is divided into some specific corporation.For example, in table 2, it is crucial
In corporations where " Zhang San " and " little Rong " has been respectively divided each in word " derailed ".
The embodiment of the present invention additionally provides the creation angle method for digging of another people entities.Fig. 3 is shown according to this
Invent the schematic flow sheet of the creation angle method for digging of the people entities of another embodiment.Referring to Fig. 3, this method at least may be used
With including step S302 to step S310.
Step S302, article metadata is obtained from network data source, and parse the people included in article metadata
Thing entity word and the keyword related to people entities word.
In this step, people entities word can be noun, and keyword can be noun, verb etc..The embodiment of the present invention
The specific part of speech of people entities word and keyword is not limited.
Step S304, count between connection weight and/or the different personage's entity words between people entities word and keyword
Connection weight.
In this step, count connection weight between people entities word and keyword and/or different personage's entity words it
Between the process of connection weight can include:
First, the article title in article metadata is extracted, people entities word and keyword are parsed from article title.
Then, the co-occurrence word pair occurred in article title is counted.Wherein, co-occurrence word is to that can represent in same article title
The people entities word of appearance and crucial phrase into word pair, the word pair formed between different personage's entity words can also be represented.
Finally, co-occurrence word is calculated to the corresponding weighted value in different articles, and to identical co-occurrence word in different articles
In the summation of corresponding weighted value, using as in personage's keyword network with co-occurrence word to corresponding people entities word and keyword it
Between connection weight and/or different personage's entity words between connection weight.
In an embodiment of the present invention, co-occurrence word is calculated to during corresponding weighted value, can first be extracted in different articles
Article text in article metadata.Then the number occurred according to co-occurrence word to the co-occurrence word included in article text,
The weighted value of co-occurrence word pair is calculated, wherein, co-occurrence word is personage's entity word and/or keyword.
In order to more clearly embody the connection weight of the embodiment of the present invention, below with a specific embodiment to connection weight
The statistic processes of weight illustrates.
For example, the word for being segmented to obtain to article A title includes 4:W1, w2, w3, w4 are (assuming that w1 and w2 is people
Thing entity word, w3 and w4 are other classifiers (i.e. keyword)).Because word w1, w2, w3, w4 are appeared in a title simultaneously,
Therefore, these words co-occurrence each other is thought herein.Next the co-occurrence word pair that statistics occurs is, it is necessary to which explanation is that co-occurrence word centering must
Must include people entities word, and co-occurrence word to be it is unordered, thus, the co-occurrence word arrived of statistics to including:<w1,w2>,<
w1,w3>,<w1,w4>,<w2,w3>,<w2,w4>.
In embodiments of the present invention, only calculated once for same piece article, co-occurrence number, in order that between network node
Connection weight is more accurate, and giving each co-occurrence word, the calculating process of weighted value is as follows to being multiplied by a weighted value.
Assuming that<w1,w2>Weighted value represented with weightA, then,
weightA<w1,w2>=min (c (w1), c (w2))/max (c (w1), c (w2), c (w3), c (w4)).
In the formula, c (w) represents the number that word w occurs in article.The weighted value being calculated be one be less than etc.
In 1 numerical value.
If w1 and w2 is respectively as the network node in personage's keyword network, then<w1,w2>Connection weight be institute
There is the weighted value sum of article corresponding to the article title comprising the two network nodes, calculation formula is:weight<w1,w2>
=∑ weightA<w1,w2>.
Step S306, using people entities word and keyword as network node, between people entities word and keyword
Connection weight between connection weight and/or different personage's entity words builds personage's keyword network for side.
In this step, connection weight represents the tight ness rating between network node.
Step S308, label is added to the network node in personage's keyword network based on Predistribution Algorithm.
Step S310, using same label as corporations' partitioning standards, the network node in personage's keyword network is carried out
Corporations divide, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
Divided by foregoing embodiments after obtaining multiple corporations, the arbitrary network node in each corporations can serve as
The creation angle of people entities word in this corporation.The embodiment of the present invention can will create angle and recommend creator.Specifically, work as
When creator carries out article writing by correlation writing APP or website, recorded, will be created with it according to the creation before creator
The creation angle for correlation of noting down recommends creator.
Red often published an article for example, creator is small using blog.Due to it is small it is red be a star fan, it is therefore, small red
The article often delivered in blog is all the content related to star.It is small it is red be video display star " Wang Xiaoxiao " iron bean vermicelli,
Deliver write on she article it is most.The corporations divided according to embodiments of the present invention, also wrapped in corporations where " Wang Xiaoxiao "
Contain keyword " culinary art ".In fact, " Wang Xiaoxiao " also frequently does some cuisines in addition to shooting films and television programs, still,
She likes the thing external world few people for doing cuisines to know.Thus, " culinary art " can be used as by " Wang Xiao by the embodiment of the present invention
Dawn " new creation angle recommend it is small red, red to provide new writing thought to be small.
In the embodiment of the present invention, the form of creation angle is recommended to include for creator a variety of.For example, can be with bullet
The form of window recommends multiple creation angles on people entities on creator's current written interface, can also be with scroll bar
Form recommends multiple creation angles on people entities in the optional position at author's current written interface.Certainly, it is being actually
When creator recommends multiple creation angles on people entities, it is necessary to by the content displaying of recommendation in more eye-catching place,
To cause the attention of creator.
Meanwhile in order to not influence the writing work of creator, the display time of content recommendation can be set.For example, setting
The display time of the creation angle of recommendation is 20 seconds, 30 seconds, 40 seconds etc..Or the creation angle of recommendation is set every 30 seconds
Renewal once, i.e., recommended new creation angle etc. every 30 seconds.The creation angle that the embodiment of the present invention obtains to excavation pushes away
Recommend form and do not do specific restriction.
Based on same inventive concept, the embodiment of the present invention additionally provides a kind of creation angle excavating gear of people entities,
Fig. 4 shows the structural representation of the creation angle excavating gear of people entities according to an embodiment of the invention, referring to figure
4, the creation angle excavating gear 400 of people entities can at least include parsing module 410, structure module 420 and excavate mould
Block 430.
Now introduce the function of each composition or device of the creation angle excavating gear 400 of the people entities of the embodiment of the present invention
And the annexation between each several part:
Parsing module 410, suitable for obtaining article metadata from network data source, and parse and wrapped in article metadata
The people entities word and the keyword related to people entities word contained;
Module 420 is built, is coupled with parsing module 410, suitable for being used as network node by the use of people entities word and keyword
Personage's keyword network is built, label is added to the network node in personage's keyword network;
Wherein, label includes the attribute information and people entities word of at least one of people entities word and/or keyword
And/or people information, the event information related to people entities word and/or keyword of keyword correlation.
Module 430 is excavated, is coupled with structure module 420, suitable for using same label as corporations' partitioning standards, being closed to personage
Network node in keyword network carries out corporations' division, real using the arbitrary network node in same corporations as personage in this corporation
The creation angle of pronouns, general term for nouns, numerals and measure words.
In an embodiment of the present invention, structure module 420 is further adapted for, and network section is used as using people entities word and keyword
Point, the connection weight between connection weight and/or different personage's entity words between people entities word and keyword is side structure
Personage's keyword network is built, wherein, connection weight represents the tight ness rating between network node.
In an embodiment of the present invention, structure module 420 is further adapted for, and has added tagged people entities word using preset
And/or keyword is matched with the network node in personage's keyword network.If the match is successful, corresponding label is added to
The network node that the match is successful, and the connection weight obtained between the network node that the match is successful reaches the network of predetermined threshold value
Node.And then the connection weight to getting reaches the network node addition same label of predetermined threshold value.
In an embodiment of the present invention, structure module 420 is further adapted for, based on Predistribution Algorithm in personage's keyword network
Network node adds label.Wherein, Predistribution Algorithm includes label propagation algorithm LPA.
In an embodiment of the present invention, parsing module 410 is further adapted for, and the article title in article metadata is extracted, to carrying
The article title taken is segmented.And high frequency words are filtered according to the word frequency after participle, and part of speech mark is carried out to the word after filtering
Note, wherein, personage's noun is labeled as people entities word, other words related to people entities word are labeled as keyword.
The embodiment of the present invention additionally provides the creation angle excavating gear of another people entities, and Fig. 5 is shown according to this
The structural representation of the creation angle excavating gear of the people entities of another embodiment is invented, referring to Fig. 5, the wound of people entities
Make angle excavating gear 400 in addition to the modules limited in comprising above-described embodiment, statistical module can also be included
440。
Statistical module 440, coupled respectively with parsing module 410 and structure module 420, suitable for building module 420 with people
Thing entity word and keyword are as network node, connection weight and/or different personages between people entities word and keyword
Before connection weight between entity word builds personage's keyword network for side, the company between people entities word and keyword is counted
Connect the connection weight between weight and/or different personage's entity words.
In an embodiment of the present invention, statistical module 440 is further adapted for, and the article title in article metadata is extracted, from text
People entities word and keyword are parsed in chapter title.And the co-occurrence word pair occurred in article title is counted, co-occurrence word is to be same
The word pair that the people entities word occurred in one article title forms from keyword, different personage's entity words.And then calculate co-occurrence word
To the corresponding weighted value in different articles, and to identical co-occurrence word to the corresponding weighted value summation in different articles, to make
For in personage's keyword network with co-occurrence word to the connection weight and/or different people between corresponding people entities word and keyword
Connection weight between thing entity word.
In an embodiment of the present invention, statistical module 440 is further adapted for, and extracts the article text in article metadata.And according to
The number occurred according to co-occurrence word to the co-occurrence word included in article text, the weighted value of co-occurrence word pair is calculated, wherein, co-occurrence
Word is personage's entity word and/or keyword.
According to the combination of any one above-mentioned preferred embodiment or multiple preferred embodiments, the embodiment of the present invention can reach
Following beneficial effect:
In embodiments of the present invention, first, article metadata is obtained from network data source, and parses article member number
The people entities word and the keyword related to people entities word included in.Then, made using people entities word and keyword
Personage's keyword network is built for network node, and label is added to the network node in personage's keyword network.Finally, with phase
With label as corporations' partitioning standards, corporations' division is carried out to the network node in personage's keyword network, by same corporations
Creation angle of the arbitrary network node as people entities word in this corporation.Thus, the embodiment of the present invention passes through to a large amount of nets
The people entities word and keyword that the excavation of network data is included with extracting in article metadata, closed using each word structure personage
After keyword network, corporations' division is carried out to the node of the network, so as to be used as people in this corporation by the use of the word in same corporations
The creation angle of thing entity word, the cluster of the creation angle of people entities word is realized, so that the creation angle of people entities word is converged
Being polymerized to can open-and-shut form.The present invention program can not only provide more novel writing angle for creator, can be with
The creation thought of creator is widened, helps creator to create the article of more diversification.
Further, creator is helped to carry out article creation using the scheme of the embodiment of the present invention, for the audient of article
Person also has permanent sustainable value.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments
Including some features rather than further feature, but the combination of the feature of different embodiments means to be in the scope of the present invention
Within and form different embodiments.For example, in detail in the claims, the one of any of embodiment claimed all may be used
Used in a manner of in any combination.
The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor or digital signal processor (DSP) realize that the creation angle of people entities according to embodiments of the present invention is excavated
The some or all functions of some or all parts in device.The present invention is also implemented as being used to perform being retouched here
The some or all equipment or program of device (for example, computer program and computer program product) for the method stated.
Such program for realizing the present invention can store on a computer-readable medium, or can have one or more signal
Form.Such signal can be downloaded from internet website and obtained, either provide on carrier signal or with it is any its
He provides form.
The embodiment of the present invention additionally provides a kind of computer program, including computer-readable code, when computer-readable generation
Code is when running on the computing device, the creation angle excavation side based on corporations' division that causes computing device described above
Method.A kind of computer-readable medium is additionally provided, wherein storing computer program as described above.
For example, Fig. 6 shows the computing device for the creation angle method for digging that can realize people entities.The computing device
Conventionally comprise processor 610 and the computer program product or computer-readable medium of the form of memory 620.Memory
620 can be the electricity of such as flash memory, EEPROM (Electrically Erasable Read Only Memory), EPROM, hard disk or ROM etc
Quantum memory.There is memory 620 storage to be used for the storage for performing the program code 631 of any method and step in the above method
Space 630.For example, the memory space 630 of store program codes can be various in above method including being respectively used to realize
Each program code 631 of step.These program codes can be read from one or more computer program product or
It is written in this one or more computer program product.These computer program products include such as hard disk, compact-disc
(CD), the program code carrier of storage card or floppy disk etc.Such computer program product is usually for example shown in Fig. 7
Portable or static memory cell.The memory cell can have and the similar arrangement of memory 620 in Fig. 6 computing device
Memory paragraph, memory space etc..Program code for example can be compressed in a suitable form.Generally, memory cell includes being used for
Perform the computer-readable code 631 ' of the method and step of the present invention, you can with the generation read by such as 610 etc processor
Code, when these codes are run by computing device, causes each step in the computing device method described above.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
So far, although those skilled in the art will appreciate that detailed herein have shown and described multiple showing for the present invention
Example property embodiment, still, still can be direct according to present disclosure without departing from the spirit and scope of the present invention
It is determined that or derive many other variations or modifications for meeting the principle of the invention.Therefore, the scope of the present invention is understood that and recognized
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of creation angle method for digging of people entities, including:
Article metadata is obtained from network data source, and parse the people entities word that is included in the article metadata and
The keyword related to the people entities word;
Personage's keyword network is built as network node by the use of the people entities word and the keyword, the personage is closed
Network node addition label in keyword network;
Using same label as corporations' partitioning standards, corporations' division is carried out to the network node in personage's keyword network,
Creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
2. the method according to claim 11, wherein, it is described to be used as network by the use of the people entities word and the keyword
Node builds personage's keyword network, including:
Using the people entities word and keyword as network node, with the connection weight between people entities word and keyword
And/or the connection weight between different personage's entity words is that side builds personage's keyword network, wherein, the connection weight represents
Tight ness rating between network node.
3. method according to claim 1 or 2, wherein, the network node in personage's keyword network adds
Tag, including:
Tagged people entities word and/or keyword and the network section in personage's keyword network are added using preset
Point is matched;
If the match is successful, by corresponding label added to the network node that the match is successful, and obtain and the network section that the match is successful
Connection weight between point reaches the network node of predetermined threshold value;
Reach the network node addition same label of predetermined threshold value to the connection weight got.
4. according to the method described in claim any one of 1-3, wherein, the network node in personage's keyword network is added
Tag, including:
Label is added to the network node in personage's keyword network based on Predistribution Algorithm.
5. according to the method described in claim any one of 1-4, wherein, the Predistribution Algorithm includes:Label propagation algorithm LPA.
6. according to the method described in claim any one of 1-5, wherein, the label includes at least one of:
The attribute information of the people entities word and/or the keyword;
The people information related to the people entities word and/or the keyword;
The event information related to the people entities word and/or the keyword.
7. according to the method described in claim any one of 1-6, wherein, it is described that net is used as using the people entities word and keyword
Network node, the connection weight between connection weight and/or different personage's entity words using between people entities word and keyword as
Before the structure personage's keyword network of side, in addition to:
Count the connection weight between connection weight and/or the different personage's entity words between the people entities word and keyword
Weight.
8. a kind of creation angle excavating gear of people entities, including:
Parsing module, suitable for obtaining article metadata from network data source, and parse and included in the article metadata
People entities word and the keyword related to the people entities word;
Module is built, suitable for building personage's keyword net as network node by the use of the people entities word and the keyword
Network, label is added to the network node in personage's keyword network;
Module is excavated, suitable for using same label as corporations' partitioning standards, to the network node in personage's keyword network
Carry out corporations' division, the creation angle using the arbitrary network node in same corporations as people entities word in this corporation.
9. a kind of computer program, including computer-readable code, when the computer-readable code is run on the computing device
When, cause the creation angle that based on corporations divides of the computing device according to claim 1-7 described in any one to be excavated
Method.
A kind of 10. computer-readable medium, wherein storing computer program as claimed in claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710914887.9A CN107704572B (en) | 2017-09-30 | 2017-09-30 | Method and device for mining creation angle of character entity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710914887.9A CN107704572B (en) | 2017-09-30 | 2017-09-30 | Method and device for mining creation angle of character entity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107704572A true CN107704572A (en) | 2018-02-16 |
CN107704572B CN107704572B (en) | 2021-07-13 |
Family
ID=61183245
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710914887.9A Active CN107704572B (en) | 2017-09-30 | 2017-09-30 | Method and device for mining creation angle of character entity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107704572B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104520A (en) * | 2019-11-21 | 2020-05-05 | 新华智云科技有限公司 | Figure entity linking method based on figure identity |
CN112685534A (en) * | 2020-12-23 | 2021-04-20 | 上海掌门科技有限公司 | Method and apparatus for generating context information of authored content during authoring process |
CN113220901A (en) * | 2021-05-11 | 2021-08-06 | 中国科学院自动化研究所 | Writing concept auxiliary system and network system based on enhanced intelligence |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7624081B2 (en) * | 2006-03-28 | 2009-11-24 | Microsoft Corporation | Predicting community members based on evolution of heterogeneous networks using a best community classifier and a multi-class community classifier |
CN102393843A (en) * | 2011-06-29 | 2012-03-28 | 广州市动景计算机科技有限公司 | Method and system for establishing relational network of user by using communication information of mobile terminal |
CN103327092A (en) * | 2012-11-02 | 2013-09-25 | 中国人民解放军国防科学技术大学 | Cell discovery method and system on information networks |
CN103744887A (en) * | 2013-12-23 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and device for people search and computer equipment |
CN103942189A (en) * | 2014-03-19 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Method and device for determining keywords of compositions |
CN106372239A (en) * | 2016-09-14 | 2017-02-01 | 电子科技大学 | Social network event correlation analysis method based on heterogeneous network |
WO2017026303A1 (en) * | 2015-08-12 | 2017-02-16 | 国立研究開発法人情報通信研究機構 | Future scenario generation device and method, and computer program |
CN106682169A (en) * | 2016-12-27 | 2017-05-17 | 北京奇虎科技有限公司 | Application label mining method and device, and application searching method and server |
CN106682142A (en) * | 2016-12-21 | 2017-05-17 | 兰州交通大学 | Method for excavating user emotions and analyzing propagation features under specific event situation |
CN107016072A (en) * | 2017-03-23 | 2017-08-04 | 成都市公安科学技术研究所 | Knowledge-based inference system and method based on social networks knowledge mapping |
CN107133877A (en) * | 2017-06-06 | 2017-09-05 | 安徽师范大学 | The method for digging of overlapping corporations in network |
CN107194818A (en) * | 2017-04-13 | 2017-09-22 | 天津科技大学 | Label based on pitch point importance propagates community discovery algorithm |
-
2017
- 2017-09-30 CN CN201710914887.9A patent/CN107704572B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7624081B2 (en) * | 2006-03-28 | 2009-11-24 | Microsoft Corporation | Predicting community members based on evolution of heterogeneous networks using a best community classifier and a multi-class community classifier |
CN102393843A (en) * | 2011-06-29 | 2012-03-28 | 广州市动景计算机科技有限公司 | Method and system for establishing relational network of user by using communication information of mobile terminal |
CN103327092A (en) * | 2012-11-02 | 2013-09-25 | 中国人民解放军国防科学技术大学 | Cell discovery method and system on information networks |
CN103744887A (en) * | 2013-12-23 | 2014-04-23 | 北京百度网讯科技有限公司 | Method and device for people search and computer equipment |
CN103942189A (en) * | 2014-03-19 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Method and device for determining keywords of compositions |
WO2017026303A1 (en) * | 2015-08-12 | 2017-02-16 | 国立研究開発法人情報通信研究機構 | Future scenario generation device and method, and computer program |
CN106372239A (en) * | 2016-09-14 | 2017-02-01 | 电子科技大学 | Social network event correlation analysis method based on heterogeneous network |
CN106682142A (en) * | 2016-12-21 | 2017-05-17 | 兰州交通大学 | Method for excavating user emotions and analyzing propagation features under specific event situation |
CN106682169A (en) * | 2016-12-27 | 2017-05-17 | 北京奇虎科技有限公司 | Application label mining method and device, and application searching method and server |
CN107016072A (en) * | 2017-03-23 | 2017-08-04 | 成都市公安科学技术研究所 | Knowledge-based inference system and method based on social networks knowledge mapping |
CN107194818A (en) * | 2017-04-13 | 2017-09-22 | 天津科技大学 | Label based on pitch point importance propagates community discovery algorithm |
CN107133877A (en) * | 2017-06-06 | 2017-09-05 | 安徽师范大学 | The method for digging of overlapping corporations in network |
Non-Patent Citations (4)
Title |
---|
BOUTEMINE,OUALID等: "Mining Community Structures in Multidimensional Networks", 《ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA》 * |
KIANIAN, SAHAR等: "Semantic community detection using label propagation algorithm", 《JOURNAL OF INFORMATION SCIENCE》 * |
蔡国永等: "社会语义网社区发现标签传递算法研究", 《计算机科学》 * |
黄攀: "基于主题的社团发现", 《中国优秀硕士学位论文全文数据库(电子期刊)》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111104520A (en) * | 2019-11-21 | 2020-05-05 | 新华智云科技有限公司 | Figure entity linking method based on figure identity |
CN112685534A (en) * | 2020-12-23 | 2021-04-20 | 上海掌门科技有限公司 | Method and apparatus for generating context information of authored content during authoring process |
CN113220901A (en) * | 2021-05-11 | 2021-08-06 | 中国科学院自动化研究所 | Writing concept auxiliary system and network system based on enhanced intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN107704572B (en) | 2021-07-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kanakaraj et al. | Performance analysis of Ensemble methods on Twitter sentiment analysis using NLP techniques | |
Rangel Pardo et al. | Overview of the 3rd Author Profiling Task at PAN 2015 | |
Kaati et al. | Detecting multipliers of jihadism on twitter | |
CN104991899B (en) | The recognition methods of user property and device | |
CN105069021B (en) | Chinese short text sensibility classification method based on field | |
CN112015949A (en) | Video generation method and device, storage medium and electronic equipment | |
CN105824923A (en) | Movie and video resource recommendation method and device | |
Lee et al. | Emotion in code-switching texts: Corpus construction and analysis | |
CN107704572A (en) | The creation angle method for digging and device of people entities | |
CN107203520A (en) | The method for building up of hotel's sentiment dictionary, the sentiment analysis method and system of comment | |
CN106294473B (en) | Entity word mining method, information recommendation method and device | |
Pöschko | Exploring twitter hashtags | |
CN107924398B (en) | System and method for providing a review-centric news reader | |
US20170046312A1 (en) | Using content structure to socially connect users | |
CN105447144B (en) | Microblogging forwarding visual analysis method and system based on big data analysis technology | |
CN108536676B (en) | Data processing method and device, electronic equipment and storage medium | |
Lv et al. | Understanding the users and videos by mining a novel danmu dataset | |
JP2014153977A (en) | Content analysis device, content analysis method, content analysis program, and content reproduction system | |
Andriotis et al. | Smartphone message sentiment analysis | |
CN107169011A (en) | The original recognition methods of webpage based on artificial intelligence, device and storage medium | |
CN110162793A (en) | It is a kind of name entity recognition methods and relevant device | |
JP6446987B2 (en) | Video selection device, video selection method, video selection program, feature amount generation device, feature amount generation method, and feature amount generation program | |
Kutuzov et al. | Cross-Lingual Trends Detection for Named Entities in News Texts with Dynamic Neural Embedding Models. | |
Phuvipadawat et al. | Detecting a multi-level content similarity from microblogs based on community structures and named entities | |
Handler et al. | Relational summarization for corpus analysis |
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 |