CN111104790B - Method, apparatus, device and computer readable medium for extracting key relation - Google Patents
Method, apparatus, device and computer readable medium for extracting key relation Download PDFInfo
- Publication number
- CN111104790B CN111104790B CN201811179956.7A CN201811179956A CN111104790B CN 111104790 B CN111104790 B CN 111104790B CN 201811179956 A CN201811179956 A CN 201811179956A CN 111104790 B CN111104790 B CN 111104790B
- Authority
- CN
- China
- Prior art keywords
- entity
- key
- article
- group
- extracting
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000013598 vector Substances 0.000 claims description 55
- 238000000605 extraction Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 3
- 230000015654 memory Effects 0.000 description 21
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The invention provides a method, a device, equipment and a computer readable medium for extracting key relations, wherein the method for extracting the key relations comprises the following steps: extracting an entity relation group from an article, wherein the entity relation group comprises at least two entities of the article and a relation between the at least two entities; extracting key anchor points from the article; and selecting the entity relation group as the key relation of the article based on the similarity between each entity relation group and the key anchor point. The technical scheme of the invention can help the user to know the important entity relationship in the article.
Description
Technical Field
The present invention relates to the field of information technologies, and in particular, to a method, an apparatus, a device, and a computer readable medium for extracting a key relationship.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
To help the user better understand the content of the article, titles and keywords may be extracted from the article. However, some important entities in the title are not necessarily included, and the corresponding entity relationship cannot be clearly understood. Keywords themselves provide key information points, but entity relationships in articles cannot be represented.
Disclosure of Invention
Embodiments of the present invention provide a method, apparatus, device, and computer readable medium for extracting key relationships, so as to at least solve one or more technical problems in the prior art.
In a first aspect, an embodiment of the present invention provides a method for extracting a key relationship, including:
extracting an entity relation group from an article, wherein the entity relation group comprises at least two entities of the article and a relation between the at least two entities;
extracting key anchor points from the article;
and selecting the entity relation group as the key relation of the article based on the similarity between each entity relation group and the key anchor point.
With reference to the first aspect, in a first implementation manner of the first aspect, the extracting an entity relationship group from the article includes:
segmenting the article into a plurality of sentences;
extracting the entity relation group of each sentence;
and performing de-duplication processing on the extracted plurality of entity relation groups.
With reference to the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the extracting an entity relationship group of each sentence includes:
carrying out named entity recognition on the sentence to obtain at least two entities of the sentence;
based on grammar rules, a relationship between the at least two entities is extracted from the sentence.
With reference to the first aspect, in a third implementation manner of the first aspect, the extracting a key anchor point from the article includes:
acquiring the title of the article, and taking the title as the key anchor point; and/or
And acquiring keywords of the article, and taking the keywords as the key anchor points.
With reference to the first aspect, in a fourth implementation manner of the first aspect, the selecting, as the key relationship of the article, the entity relationship group based on the similarity between each entity relationship group and the key anchor point includes:
obtaining vectors of the entity relation group;
acquiring the vector of the key anchor point;
calculating the similarity between the vector of each entity relation group and the vector of the key anchor point;
and selecting the entity relation group corresponding to the first N maximum similarity as the key relation, wherein N is a positive integer smaller than or equal to a set threshold value.
With reference to the first aspect, in a fifth implementation manner of the first aspect, if the selected entity relationship group is a plurality of, the method further includes:
setting the importance of the selected entity relationship group based on the similarity;
adding the importance degree into a corresponding entity relation group;
and determining the entity relation group comprising the importance degree as the key relation.
In a second aspect, an embodiment of the present invention provides an apparatus for extracting a key relationship, including:
the entity relation group extraction module is used for extracting an entity relation group from an article, wherein the entity relation group comprises at least two entities of the article and a relation between the at least two entities;
the key anchor point extraction module is used for extracting key anchor points from the article;
and the selecting module is used for selecting the entity relation group as the key relation of the article based on the similarity between each entity relation group and the key anchor point.
With reference to the second aspect, in a first implementation manner of the embodiment of the present invention, the entity relationship extraction module includes:
the molecule cutting module is used for cutting the article into a plurality of sentences;
the extraction submodule is used for extracting the entity relation group of each sentence;
and the de-duplication sub-module is used for de-duplication processing the extracted plurality of entity relation groups.
With reference to the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the extracting submodule includes:
the identifying unit is used for carrying out named entity identification on the sentences to obtain two entities of the sentences;
and the extraction unit is used for extracting the relation between the two entities from the sentence based on grammar rules.
With reference to the second aspect, in a third implementation manner of the embodiment of the second aspect, the key anchor point extracting module includes:
the first acquisition sub-module is used for acquiring the title of the article and taking the title as the key anchor point; and/or
And the second acquisition sub-module is used for acquiring the keywords of the article and taking the keywords as the key anchor points.
With reference to the second aspect, in a fourth implementation manner of the second aspect, the selecting module includes:
a first vector acquisition sub-module, configured to acquire a vector of the entity relationship group;
a second vector acquisition sub-module, configured to acquire a vector of the key anchor point;
the computing sub-module is used for computing the similarity between the vector of each entity relation group and the vector of the key anchor point;
the selecting sub-module is used for selecting the entity relation group corresponding to the first N maximum similarity as the key relation, wherein N is a positive integer smaller than or equal to a set threshold value.
With reference to the second aspect, in a fifth implementation manner of the embodiment of the present invention in the second aspect, if the entity relationship group selected by the selection module is a plurality of entity relationship groups, the apparatus further includes:
the setting module is used for setting the importance of the selected entity relation group based on the similarity;
the adding module is used for adding the importance degree into the corresponding entity relation group;
and the determining module is used for determining the entity relation group comprising the importance degree as the key relation.
The functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.
In a third aspect, an embodiment of the present invention provides an apparatus for extracting a critical relationship, including a processor and a memory, where the memory is configured to store a program for enabling the apparatus for extracting a critical relationship to execute the method for extracting a critical relationship in the first aspect, and the processor is configured to execute the program stored in the memory. The device for extracting the key relation may further comprise a communication interface for communicating with other devices or a communication network.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium storing computer software instructions for use by an apparatus for extracting a critical relationship, which includes a program for executing the method for extracting a critical relationship in the first aspect.
The embodiment of the invention can help the user to know the important entity relationship in the article.
The foregoing summary is for the purpose of the specification only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will become apparent by reference to the drawings and the following detailed description.
Drawings
In the drawings, the same reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily drawn to scale. It is appreciated that these drawings depict only some embodiments according to the disclosure and are not therefore to be considered limiting of its scope.
FIG. 1 is a flow chart of a method for extracting key relationships according to an embodiment of the present invention.
FIG. 2 is a flow chart of a method for extracting key relationships according to another embodiment of the present invention.
FIG. 3 is a flow chart of a method for extracting key relationships according to yet another embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an apparatus for extracting key relationships according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an apparatus for extracting key relationships according to another embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an apparatus for extracting key relationships according to still another embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an apparatus for extracting key relationships according to an embodiment of the present invention.
Detailed Description
Hereinafter, only certain exemplary embodiments are briefly described. As will be recognized by those of skill in the pertinent art, the described embodiments may be modified in various different ways without departing from the spirit or scope of the present invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.
The embodiment of the invention aims to provide a method and a device for extracting key relations, which can characterize important entities of an article and relations among the important entities by extracting an important entity relation group from the article as the key relations of the article, so that a user can be helped to quickly know the content of the article.
As shown in fig. 1, the method for extracting key relationships in this embodiment may include:
s110, extracting an entity relation group from the article, wherein the entity relation group comprises at least two entities of the article and relations between the at least two entities.
Specifically, the article of the present embodiment may include various grammars, such as news, papers, novels, comments, drama, or the like. The set of entity relationships may include two or more entities in the article, as well as relationships between the entities. Where an Entity is typically a Named Entity (name), such as a person's name, place's name (e.g., city name, geographic name, etc.), institution's name, proper nouns (e.g., song name, star name, etc.), etc. In addition, the relation between the entities can be extracted from the corresponding sentences based on the grammar structure information of the sentences where the entities are located, can be obtained by using a neural network for supervised learning, can also be obtained by adopting other modes, and is not limited in the embodiment of the invention.
In one possible implementation, extracting the set of entity relationships from the article may include: segmenting the article into a plurality of sentences; extracting the entity relation group of each sentence; and performing de-duplication processing on the extracted plurality of entity relation groups.
Specifically, an article may be segmented into multiple sentences based on sentence segmentation rules. For example, sentence segmentation is performed according to punctuation marks; or, sentence segmentation is performed according to the complete semantics expressed by the sentences.
For each sentence obtained after segmentation, named entity recognition can be performed, and two or more recognized named entities are used as entities in the entity relation group; then, based on grammar rules, the relationships between the entities are extracted from sentences in which the entities are located.
The grammar rules can include rules such as 'subject predicate object relation', 'post-subject guest relation', 'mediate-guest relation main-predicate-complement', and the like, and the rules can be used for representing the dependency relationship among entities. For example, for a sentence "i am not in love of own country" obtained after segmentation, the entities obtained based on the recognition of the named entities are "i am" and "country", wherein "i am the subject," country "is the object, and according to the" subject predicate object relationship ", predicate" love "can be extracted from the sentence" i am not in love of own country "at any time, thereby obtaining the entity relationship group < i am, love, country >.
For the entity-relationship group extracted from each sentence, a deduplication process may be performed, deleting the duplicate entity-relationship group.
S120, extracting key anchor points from the article.
Wherein the extraction of the key anchor point may include at least one of the following examples:
example one, the title of the article is obtained and the title is used as the key anchor point.
And secondly, acquiring keywords of the article, and taking the keywords as the key anchor points.
For example, a title and a plurality of keywords are extracted from an article, and the extracted title and the plurality of keywords are used as key anchor points.
S130, selecting an entity relation group as the key relation of the article based on the similarity between each entity relation group and the key anchor point.
Specifically, one or more entity relationship groups may be selected as key relationships of the article based on the similarity between each entity relationship group and the key anchor point.
In a possible implementation manner, as shown in fig. 2, in step S130, selecting, as the key relationship of the article, the entity relationship group based on the similarity between each entity relationship group and the key anchor point may include:
s210, obtaining the vector of the entity relation group.
Specifically, the entity-relationship group includes a plurality of entities and relationships between the entities, i.e., a plurality of words in one entity-relationship group. The vector of the set of entity relationships may be an accumulated vector resulting from accumulating the vectors of each word in the set of entity relationships.
S220, acquiring the vector of the key anchor point.
Specifically, if the key anchor points are plural, the sum of the vectors of all the key anchor points may be added as the vector of the key anchor point. For example, the keyword vector v1 is obtained by adding the vectors of all keywords obtained from the article. The headlines of the articles are segmented, and the vector of each word in the headlines is added to obtain a headline vector v2. Then, the keyword vector v1 and the heading vector v2 are added to obtain a vector v of the key anchor point. In addition, a first weight w1 may be set for the keyword vector v1 and a second weight w2 may be set for the header vector v2 based on the importance degrees of the keywords and the headers, so that the vector v=w1×v1+w2×v2 of the key anchor point.
It should be noted that, in this embodiment, the word-to-vector conversion may be performed based on a word-to-vector (word 2 vec) model, including but not limited to: converting each word in the entity relation group into a corresponding vector; converting the keywords into corresponding vectors; each word in the heading is translated into a corresponding vector.
S230, calculating the similarity between the vector of each entity relation group and the vector of the key anchor point.
Specifically, the method for calculating the similarity may be a cosine similarity algorithm (similarity calculation performed by calculating cosine values of two vector angles); or may be a euclidean distance algorithm (similarity calculation based on a measure of the absolute distance of each point in space).
S240, selecting the entity relation group corresponding to the first N maximum similarity as the key relation, wherein N is a positive integer smaller than or equal to a set threshold value.
Specifically, calculating the similarity between the vector of each entity relationship group and the vector of the key anchor point respectively will obtain a plurality of similarities, and each similarity corresponds to one entity relationship group. And arranging all the similarities in a descending order, selecting the first N similarities, and taking the entity relation group corresponding to the first N similarities as a key relation. The set threshold value may be set according to the number of words of the article. For example, the number of words of the article is large, and the set threshold value may be large; the number of words of the article is smaller, and the set threshold value can be smaller.
In a possible implementation manner, as shown in fig. 3, in step S130, if the selected entity relationship group is a plurality of entity relationship groups, the method for extracting key relationships in this embodiment may further include:
s310, setting the importance of the selected entity relation group based on the similarity.
Specifically, the similarity between each selected entity relationship group and the key anchor point may be different, and the corresponding importance may be set according to the similarity. For example, if the similarity between the entity relation group G1 and the key anchor point belongs to the first set interval, the importance of the entity relation group G1 is set to be one level; if the similarity between the entity relation G2 and the key anchor point belongs to a second set interval, setting the importance of the entity relation group G2 as a second level; if the similarity between the entity relation group G3 and the key anchor point belongs to the fifth set interval, the importance of the entity relation group G3 is set to be five-level.
S320, adding the importance degree into the corresponding entity relation group.
For example, the entity relation group is < me, love, ancestor > and the importance of the entity relation group is first order, and the entity relation group added with the importance is < me, love, ancestor, first order >.
S330, determining the entity relation group comprising the importance degree as the key relation.
For example, the entity-relationship group < me, love, ancestor, first-order > is determined as a key relationship.
According to the method for extracting the key relation, through extracting the key relation of the article, a user can clearly know important information in the article, and the important information comprises the following steps: the important entities to which the article relates, and the relationships between the entities. This representation is a very compact presentation of critical information and can cover the entire article. Further, based on the importance degree in the key relation, key information can be displayed to the user in a layered manner, and user experience is improved.
As shown in fig. 4, this embodiment further provides an apparatus for extracting a key relationship, which may include:
an entity relationship group extraction module 110, configured to extract an entity relationship group from an article, where the entity relationship group includes at least two entities of the article and a relationship between the at least two entities;
a key anchor extraction module 120, configured to extract a key anchor from the article;
and the selecting module 130 is configured to select the entity relationship group as the key relationship of the article based on the similarity between each entity relationship group and the key anchor point.
In one possible implementation manner, the entity relationship extraction module may include:
the molecule cutting module is used for cutting the article into a plurality of sentences;
the extraction submodule is used for extracting the entity relation group of each sentence;
and the de-duplication sub-module is used for de-duplication processing the extracted plurality of entity relation groups.
In one possible implementation, the extraction sub-module may include:
the identifying unit is used for carrying out named entity identification on the sentences to obtain at least two entities of the sentences;
and the extraction unit is used for extracting the relation between the at least two entities from the sentence based on grammar rules.
In one possible implementation manner, the key anchor point extraction module may include:
the first acquisition sub-module is used for acquiring the title of the article and taking the title as the key anchor point; and/or
And the second acquisition sub-module is used for acquiring the keywords of the article and taking the keywords as the key anchor points.
In one possible implementation, as shown in fig. 5, the selecting module 130 may include:
a first vector obtaining sub-module 210, configured to obtain a vector of the entity-relationship group;
a second vector obtaining sub-module 220, configured to obtain a vector of the key anchor point;
a computing sub-module 230, configured to compute a similarity between the vector of each entity relationship group and the vector of the key anchor point;
the selecting sub-module 240 is configured to select, as the key relationship, the entity relationship group corresponding to the first N maximum similarities, where N is a positive integer less than or equal to a set threshold.
In a possible implementation manner, as shown in fig. 6, if the entity relationship group selected by the selection module 130 is a plurality of entity relationship groups, the apparatus for extracting a key relationship in this embodiment may further include:
a setting module 310, configured to set importance of the selected entity relationship group based on the similarity;
a joining module 320, configured to join the importance degree into a corresponding entity relationship group;
a determining module 330 is configured to determine a set of entity relationships including the importance as the key relationships.
The embodiment also provides an apparatus for extracting key relationships, as shown in fig. 7, where the apparatus includes: memory 21 and processor 22, and memory 21 stores a computer program executable on processor 22. The processor 22, when executing the computer program, implements the method of extracting key relationships in the above-described embodiments. The number of the memories 21 and the processors 22 may be one or more.
The apparatus further comprises:
and the communication interface 23 is used for communicating with external equipment and carrying out data interaction transmission.
The memory 21 may comprise a high-speed RAM memory or may further comprise a non-volatile memory (non-volatile memory), such as at least one disk memory.
If the memory 21, the processor 22 and the communication interface 23 are implemented independently, the memory 21, the processor 22 and the communication interface 23 may be connected to each other and perform communication with each other through a bus. The bus may be an industry standard architecture (ISA, industry Standard Architecture) bus, a peripheral component interconnect (PCI, peripheral Component) bus, or an extended industry standard architecture (EISA, extended Industry Standard Component) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 21, the processor 22 and the communication interface 23 are integrated on a chip, the memory 21, the processor 22 and the communication interface 23 may communicate with each other through internal interfaces.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that various changes and substitutions are possible within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for extracting key relationships, comprising:
extracting an entity relation group from an article, wherein the entity relation group comprises at least two entities of the article and a relation between the at least two entities;
extracting key anchor points from the article;
based on the similarity between each entity relation group and the key anchor point, selecting the entity relation group as the key relation of the article, including: accumulating the vectors of each word in each entity relation group to obtain the vector of each entity relation group; acquiring the vector of the key anchor point; respectively calculating the similarity between the vector of each entity relation group and the vector of the key anchor point; selecting an entity relation group corresponding to the first N maximum similarity as the key relation, wherein N is a positive integer smaller than or equal to a set threshold value;
if the selected entity relationship group is a plurality of, the method further comprises: setting the importance of the selected entity relationship group based on the similarity; adding the importance degree into a corresponding entity relation group; and determining the entity relation group comprising the importance degree as the key relation.
2. The method of claim 1, wherein extracting the set of entity relationships from the article comprises:
segmenting the article into a plurality of sentences;
extracting the entity relation group of each sentence;
and performing de-duplication processing on the extracted plurality of entity relation groups.
3. The method of claim 2, wherein extracting the set of physical relationships for each sentence comprises:
carrying out named entity recognition on the sentence to obtain at least two entities of the sentence;
based on grammar rules, a relationship between the at least two entities is extracted from the sentence.
4. The method of claim 1, wherein extracting key anchor points from the article comprises:
acquiring the title of the article, and taking the title as the key anchor point; and/or
And acquiring keywords of the article, and taking the keywords as the key anchor points.
5. An apparatus for extracting key relationships, comprising:
the entity relation group extraction module is used for extracting an entity relation group from an article, wherein the entity relation group comprises at least two entities of the article and a relation between the at least two entities;
the key anchor point extraction module is used for extracting key anchor points from the article;
the selecting module is used for selecting the entity relation group as the key relation of the article based on the similarity between each entity relation group and the key anchor point;
the selecting module comprises: the first vector acquisition submodule is used for accumulating the vector of each word in each entity relation group to acquire the vector of each entity relation group; a second vector acquisition sub-module, configured to acquire a vector of the key anchor point; the computing sub-module is used for respectively computing the similarity between the vector of each entity relation group and the vector of the key anchor point; the selecting sub-module is used for selecting the entity relation group corresponding to the first N maximum similarity as the key relation, wherein N is a positive integer smaller than or equal to a set threshold value;
if the entity relation group selected by the selecting module is a plurality of, the device further comprises: the setting module is used for setting the importance of the selected entity relation group based on the similarity; the adding module is used for adding the importance degree into the corresponding entity relation group; and the determining module is used for determining the entity relation group comprising the importance degree as the key relation.
6. The apparatus of claim 5, wherein the entity-relationship group extraction module comprises:
the molecule cutting module is used for cutting the article into a plurality of sentences;
the extraction submodule is used for extracting the entity relation group of each sentence;
and the de-duplication sub-module is used for de-duplication processing the extracted plurality of entity relation groups.
7. The apparatus of claim 6, wherein the extraction submodule comprises:
the identifying unit is used for carrying out named entity identification on the sentences to obtain at least two entities of the sentences;
and the extraction unit is used for extracting the relation between the at least two entities from the sentence based on grammar rules.
8. The apparatus of claim 5, wherein the key anchor extraction module comprises:
the first acquisition sub-module is used for acquiring the title of the article and taking the title as the key anchor point; and/or
And the second acquisition sub-module is used for acquiring the keywords of the article and taking the keywords as the key anchor points.
9. An apparatus for extracting key relationships, the apparatus comprising:
one or more processors;
a storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-4.
10. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811179956.7A CN111104790B (en) | 2018-10-10 | 2018-10-10 | Method, apparatus, device and computer readable medium for extracting key relation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811179956.7A CN111104790B (en) | 2018-10-10 | 2018-10-10 | Method, apparatus, device and computer readable medium for extracting key relation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111104790A CN111104790A (en) | 2020-05-05 |
| CN111104790B true CN111104790B (en) | 2024-03-22 |
Family
ID=70417501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811179956.7A Active CN111104790B (en) | 2018-10-10 | 2018-10-10 | Method, apparatus, device and computer readable medium for extracting key relation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111104790B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235772A (en) * | 2013-03-08 | 2013-08-07 | 北京理工大学 | Method for automatically extracting character relations from text set |
| WO2015080561A1 (en) * | 2013-11-27 | 2015-06-04 | Mimos Berhad | A method and system for automated relation discovery from texts |
| CN106095737A (en) * | 2016-06-07 | 2016-11-09 | 杭州凡闻科技有限公司 | Documents Similarity computational methods and similar document the whole network retrieval tracking |
| CN106776544A (en) * | 2016-11-24 | 2017-05-31 | 四川无声信息技术有限公司 | Character relation recognition methods and device and segmenting method |
| CN106933787A (en) * | 2017-03-20 | 2017-07-07 | 上海智臻智能网络科技股份有限公司 | Adjudicate the computational methods of document similarity, search device and computer equipment |
| CN107526722A (en) * | 2017-07-31 | 2017-12-29 | 努比亚技术有限公司 | A kind of character relation analysis method and terminal |
| CN107992477A (en) * | 2017-11-30 | 2018-05-04 | 北京神州泰岳软件股份有限公司 | Text subject determines method, apparatus and electronic equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9576249B2 (en) * | 2013-03-18 | 2017-02-21 | Educational Testing Service | System and method for automated scoring of a summary-writing task |
| US10282468B2 (en) * | 2015-11-05 | 2019-05-07 | International Business Machines Corporation | Document-based requirement identification and extraction |
| US11276010B2 (en) * | 2017-03-06 | 2022-03-15 | Wipro Limited | Method and system for extracting relevant entities from a text corpus |
-
2018
- 2018-10-10 CN CN201811179956.7A patent/CN111104790B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103235772A (en) * | 2013-03-08 | 2013-08-07 | 北京理工大学 | Method for automatically extracting character relations from text set |
| WO2015080561A1 (en) * | 2013-11-27 | 2015-06-04 | Mimos Berhad | A method and system for automated relation discovery from texts |
| CN106095737A (en) * | 2016-06-07 | 2016-11-09 | 杭州凡闻科技有限公司 | Documents Similarity computational methods and similar document the whole network retrieval tracking |
| CN106776544A (en) * | 2016-11-24 | 2017-05-31 | 四川无声信息技术有限公司 | Character relation recognition methods and device and segmenting method |
| CN106933787A (en) * | 2017-03-20 | 2017-07-07 | 上海智臻智能网络科技股份有限公司 | Adjudicate the computational methods of document similarity, search device and computer equipment |
| CN107526722A (en) * | 2017-07-31 | 2017-12-29 | 努比亚技术有限公司 | A kind of character relation analysis method and terminal |
| CN107992477A (en) * | 2017-11-30 | 2018-05-04 | 北京神州泰岳软件股份有限公司 | Text subject determines method, apparatus and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| Deep Belief Networks Based Toponym Recognition for Chinese Text;Wang, Shu等;《ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION》;全文 * |
| 一种基于句子结构特征的领域术语上下位关系获取方法;王长有等;《重庆邮电大学学报(自然科学版)》;全文 * |
| 基于多重文本术语关系叠加识别文本核心主题的有效性探索;郭红梅;张智雄;;情报学报(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111104790A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109189991B (en) | Duplicate video identification method, device, terminal and computer readable storage medium | |
| CN109657213B (en) | Text similarity detection method and device and electronic equipment | |
| CN111814770B (en) | Content keyword extraction method of news video, terminal device and medium | |
| CN106844341B (en) | Artificial intelligence-based news abstract extraction method and device | |
| CN111241813B (en) | Corpus expansion method, apparatus, device and medium | |
| CN111767713B (en) | Keyword extraction method and device, electronic equipment and storage medium | |
| WO2019028990A1 (en) | Code element naming method, device, electronic equipment and medium | |
| CN109508391B (en) | Input prediction method and device based on knowledge graph and electronic equipment | |
| CN111291571A (en) | Semantic error correction method, electronic device and storage medium | |
| CN111291177A (en) | Information processing method and device and computer storage medium | |
| CN111949798A (en) | Map construction method and device, computer equipment and storage medium | |
| CN109614478B (en) | Word vector model construction method, keyword matching method and device | |
| CN114861635A (en) | Chinese spelling error correction method, device, equipment and storage medium | |
| CN113935312A (en) | Long text matching method and device, electronic equipment and computer readable storage medium | |
| CN113128205A (en) | Script information processing method and device, electronic equipment and storage medium | |
| CN110929647B (en) | Text detection method, device, equipment and storage medium | |
| CN111104790B (en) | Method, apparatus, device and computer readable medium for extracting key relation | |
| CN110826323A (en) | Comment information validity detection method and device | |
| CN115617978A (en) | Index name retrieval method and device, electronic equipment and storage medium | |
| CN115391551A (en) | Event detection method and device | |
| CN114970467A (en) | Composition initial draft generation method, device, equipment and medium based on artificial intelligence | |
| CN110175331B (en) | Method and device for identifying professional terms, electronic equipment and readable storage medium | |
| CN112541069A (en) | Text matching method, system, terminal and storage medium combined with keywords | |
| CN110866106A (en) | Text recommendation method and related equipment | |
| CN111061869A (en) | Application preference text classification method based on TextRank |
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 |