CN113792539B - Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium - Google Patents
Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium Download PDFInfo
- Publication number
- CN113792539B CN113792539B CN202111083860.2A CN202111083860A CN113792539B CN 113792539 B CN113792539 B CN 113792539B CN 202111083860 A CN202111083860 A CN 202111083860A CN 113792539 B CN113792539 B CN 113792539B
- Authority
- CN
- China
- Prior art keywords
- entity
- feature
- text
- classification
- processed
- 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 62
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 40
- 238000000605 extraction Methods 0.000 claims abstract description 147
- 239000013598 vector Substances 0.000 claims abstract description 124
- 238000012545 processing Methods 0.000 claims abstract description 91
- 238000013145 classification model Methods 0.000 claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000011218 segmentation Effects 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 16
- 230000009467 reduction Effects 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 239000003999 initiator Substances 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses an entity relationship classification method based on artificial intelligence, which comprises the following steps: inputting a target word sequence corresponding to the text to be processed into a first feature extraction network of the entity relation classification model to execute extraction processing of literal features, semantic features and syntactic features to obtain a first feature vector of each word in the target word sequence output by each coding layer; inputting each first feature vector into a second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in a target word sequence; and calculating a second feature vector of the text to be processed based on the first feature vector and the weight value, and inputting the second feature vector into a classification network to obtain a relationship classification result between entities in the text to be processed. The invention also provides an entity relationship classification device, electronic equipment and medium based on the artificial intelligence. The invention realizes rapid and accurate classification of entity relations.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to an artificial intelligence-based entity relationship classification method, apparatus, electronic device, and medium.
Background
The classification of entity relationship is to classify the relationship between entities in a sentence, and the classification of entity relationship has wide application in the field of natural language processing, for example, the construction of knowledge graphs, question understanding in question-answering systems, multi-hop reasoning in machine reading understanding, etc., how to quickly and accurately classify the entity relationship is the current key point of interest.
Currently, a syntactic analysis tool is generally used to extract syntactic features of sentences, sentences and syntactic features are input into a neural network model to perform entity relationship classification, and the entity relationship classification method needs to use the syntactic analysis tool, is complex in operation and low in classification efficiency, and classification accuracy is limited by the influence of the accuracy of the syntactic analysis tool. Therefore, there is a need for an artificial intelligence-based entity relationship classification method to quickly and accurately classify relationships between entities.
Disclosure of Invention
In view of the foregoing, it is desirable to provide an artificial intelligence based entity relationship classification method, which aims to quickly and accurately classify relationships between entities.
The invention provides an artificial intelligence-based entity relationship classification method, which comprises the following steps:
responding to an entity relation classification request sent by a user based on a client for a text to be processed, and executing word segmentation processing and entity marking processing on the text to be processed to obtain a target word sequence corresponding to the text to be processed;
obtaining an entity relation classification model from a preset database, wherein the entity relation classification model comprises a first feature extraction network, a second feature extraction network and a classification network, and the first feature extraction network comprises a plurality of coding layers connected in series;
inputting the target word sequence into the first feature extraction network to execute word feature, semantic feature and syntactic feature extraction processing to obtain a first feature vector of each word in the target word sequence output by each coding layer;
inputting each first feature vector into the second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence;
and calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, inputting the second feature vector into the classification network to execute entity relationship classification processing, and obtaining a relationship classification result between entities in the text to be processed.
Optionally, the performing word segmentation processing and entity marking processing on the text to be processed to obtain a target word sequence corresponding to the text to be processed includes:
performing entity identification processing on the text to be processed to obtain an entity set corresponding to the text to be processed;
executing word segmentation processing on the text to be processed to obtain an initial word sequence corresponding to the text to be processed;
and executing entity marking processing on the initial word sequence based on the entity set to obtain a target word sequence corresponding to the text to be processed.
Optionally, the inputting each first feature vector into the second feature extraction network to perform local feature extraction and global associated feature extraction processing, to obtain a weight value corresponding to each word in the target word sequence, includes:
merging the first feature vectors to obtain a first feature matrix of each word in the target word sequence;
inputting the first feature matrix into a first linear layer of the second feature extraction network to perform feature dimension reduction processing to obtain a second feature matrix of each word in the target word sequence;
inputting the second feature matrix into a plurality of combined feature extraction networks connected in series of the second feature extraction network to execute local feature and global associated feature extraction processing to obtain a third feature matrix of each word in the target word sequence;
Inputting the third feature matrix into a second linear layer of the second feature extraction network to perform feature dimension reduction processing to obtain a third feature vector of each word in the target word sequence;
and inputting the third feature vector into an activation layer of the second feature extraction network to perform weight calculation to obtain a weight value corresponding to each word in the target word sequence.
Optionally, the calculating, based on the first feature vector and the weight value, a second feature vector corresponding to the text to be processed includes:
calculating a fourth feature vector corresponding to the text to be processed based on the first feature vector and the weight value of each word in the target word sequence output by the last coding layer;
calculating a fifth feature vector corresponding to the text to be processed based on first feature vectors of a plurality of preset words in the target word sequence output by the last coding layer;
and stacking the fourth feature vector and the fifth feature vector to obtain a second feature vector corresponding to the text to be processed.
Optionally, the process for constructing the entity relationship classification model includes:
respectively constructing a first feature extraction network, a second feature extraction network and a classification network, and connecting the output of the first feature extraction network with the input of the classification network;
And connecting the output of each coding layer in the first characteristic extraction network with the input of the second characteristic extraction network, and connecting the output of the second characteristic extraction network with the input of the classification network to obtain an entity relation classification model.
Optionally, inputting the second feature vector into the classification network to perform entity relationship classification processing to obtain a relationship classification result between entities in the text to be processed, including:
and inputting the second feature vector into the classification network to obtain the probability value of each relationship category of every two entities in the text to be processed in the target relationship category set, and taking the relationship category with the maximum probability value as the target relationship category of the corresponding two entities.
Optionally, the determining process of the target relation category set includes:
determining the domain category corresponding to each entity in the text to be processed;
acquiring a mapping relation between a domain category and a relation category set, and determining an initial relation category set corresponding to each entity in the text to be processed based on the mapping relation;
and taking the set of the initial relation class set as a target relation class set.
In order to solve the above problems, the present invention further provides an artificial intelligence based entity relationship classification apparatus, which includes:
The response module is used for responding to an entity relation classification request sent by a user based on a client side and aiming at a text to be processed, performing word segmentation processing and entity marking processing on the text to be processed, and obtaining a target word sequence corresponding to the text to be processed;
the system comprises an acquisition module, a classification module and a classification module, wherein the acquisition module is used for acquiring an entity relation classification model from a preset database, the entity relation classification model comprises a first feature extraction network, a second feature extraction network and a classification network, and the first feature extraction network comprises a plurality of coding layers which are connected in series;
the first extraction module is used for inputting the target word sequence into the first feature extraction network to execute extraction processing of literal features, semantic features and syntactic features to obtain a first feature vector of each word in the target word sequence output by each coding layer;
the second extraction module is used for inputting each first feature vector into the second feature extraction network to execute local feature and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence;
and the classification module is used for calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, inputting the second feature vector into the classification network to execute entity relationship classification processing, and obtaining a relationship classification result among entities in the text to be processed.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores an entity relationship classification program executable by the at least one processor to enable the at least one processor to perform the artificial intelligence based entity relationship classification method described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored thereon an entity relationship classification program executable by one or more processors to implement the above-mentioned artificial intelligence-based entity relationship classification method.
Compared with the prior art, the method and the device have the advantages that firstly, word segmentation processing and entity marking processing are carried out on the text to be processed, and a target word sequence is obtained; then, inputting the target word sequence into a first feature extraction network of the entity relation classification model to execute extraction processing of literal features, semantic features and syntactic features to obtain a first feature vector of each word in the target word sequence output by each coding layer; then, inputting each first feature vector into a second feature extraction network to execute local feature and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence; and finally, calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, and inputting the second feature vector into a classification network to obtain a relationship classification result between entities in the text to be processed. According to the invention, the literal features, semantic features, syntactic features, local features and global associated features of the text to be processed are extracted, so that the extracted features are richer, the classification accuracy is higher, the feature extraction and classification are performed by the entity relation classification model, no external tool is relied on, and the high classification efficiency is ensured. Therefore, the invention realizes rapid and accurate classification of the relationship between the entities.
Drawings
FIG. 1 is a flow chart of an artificial intelligence based entity relationship classification method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a physical relationship classification model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a combined feature extraction network according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of an artificial intelligence based entity relationship classification apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an electronic device implementing an artificial intelligence-based entity relationship classification method according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
The invention provides an entity relationship classification method based on artificial intelligence. Referring to fig. 1, a flow chart of an artificial intelligence-based entity relationship classification method according to an embodiment of the invention is shown. The method may be performed by an electronic device, which may be implemented in software and/or hardware.
In this embodiment, the method for classifying entity relationships based on artificial intelligence includes:
s1, responding to an entity relation classification request sent by a user based on a client for a text to be processed, and executing word segmentation processing and entity marking processing on the text to be processed to obtain a target word sequence corresponding to the text to be processed.
In this embodiment, the text to be processed may be one sentence or may be multiple sentences, and the purpose of this solution is to classify the relationship between any two entities in the text to be processed. For example, if the text to be processed is "company a is established in 1980 and is located in guangdong province", the text to be processed includes three entities, "company a", "1980" and "guangdong province", and the scheme is used for classifying the relationship between any two entities of the three entities.
After the text to be processed is obtained, word segmentation processing and entity marking processing are required to be executed on the text to be processed, so that a target word sequence corresponding to the text to be processed is obtained.
The step of performing word segmentation and entity marking on the text to be processed to obtain a target word sequence corresponding to the text to be processed comprises the following steps:
a11, executing entity identification processing on the text to be processed to obtain an entity set corresponding to the text to be processed;
in this embodiment, entity recognition processing is performed on the text to be processed through an entity recognition model, where the entity recognition model may be a BERT model or a neural network model.
A12, performing word segmentation on the text to be processed to obtain an initial word sequence corresponding to the text to be processed;
in this embodiment, the word segmentation process may be performed on the text to be processed by using a forward maximum matching method, a reverse maximum matching method, or a least segmentation method.
A13, performing entity marking processing on the initial word sequence based on the entity set to obtain a target word sequence corresponding to the text to be processed.
The entity marking processing comprises entity marking, sentence head marking and sentence tail marking, and the method adopts a marker to execute entity marking processing on the initial word sequence, wherein the marker comprises a sentence head symbol, a sentence tail symbol, an entity initiator and an entity terminator, and determines the entity needing marking in the initial word sequence through the entity in the entity set.
In this embodiment, the initial symbol is [ CLS ], the end symbol is [ SEP ], the entity initiator of the first entity is [ E11], the entity terminator is [ E12], the entity initiator of the second entity is [ E21], and the entity terminator is [ E22], … ….
For example, the text to be processed "a company stands in 1980, in guangdong province", and after the word segmentation process and the entity marking process are performed thereon, the obtained target word sequence is "[ CLS ] [ E11] a company [ E12] stands in [ E21]1980 [ E22], in [ E31] guangdong province [ E32] [ SEP ].
S2, acquiring an entity relation classification model from a preset database, wherein the entity relation classification model comprises a first feature extraction network, a second feature extraction network and a classification network, and the first feature extraction network comprises a plurality of coding layers connected in series.
In this embodiment, in order to solve the problem in the prior art that entity relationship classification needs to be performed by means of a syntactic analysis tool, an entity relationship classification model is pre-constructed and stored, and the entity relationship classification model can extract literal features, semantic features and syntactic features of an input text, and also extract local features and global associated features of the input text, so that deep learning can be performed on the input text, and entity relationship classification results can be improved.
The construction process of the entity relation classification model comprises the following steps:
b11, respectively constructing a first feature extraction network, a second feature extraction network and a classification network, and connecting the output of the first feature extraction network with the input of the classification network;
referring to fig. 2, a schematic structural diagram of an entity relationship classification model according to an embodiment of the present invention is shown, wherein an output of a first feature extraction network is connected to an input of a classification network, and is used as a backbone network of the entity relationship classification model, and a left side of fig. 2 is a backbone network, wherein the first feature extraction network includes an embedding layer and a plurality of encoding layers (Transformer Encoder layers) connected in series, the embedding layer is used for converting an input text into a word vector, and the encoding layers are used for extracting features of the word vector.
In this embodiment, the coding layers may be 12 layers, similar to the coding layers in the BERT model, and the coding layers 1 to 3 layers may extract the literal features of a single word or several adjacent words in the input text, i.e. may extract the literal features of the input text; the 4 th-7 th coding layers extract parts of speech (such as nouns, verbs and the like) of each word in the input text and grammatical relations among the words, such as main-name relations, guest-moving relations and the like, so that syntactic features of the input text can be extracted; the 8 th layer to the 12 th layer can extract the semantic relation of each word of the input text, namely the semantic features of the input text.
The classification network comprises a full-connection layer and an activation layer, wherein the full-connection layer is used for integrating input features, and the activation layer is used for classification prediction.
And B12, connecting the output of each coding layer in the first characteristic extraction network with the input of the second characteristic extraction network, and connecting the output of the second characteristic extraction network with the input of the classification network to obtain an entity relation classification model.
The right side of fig. 2 is a second feature extraction network, which is a branch network of the entity relationship classification model. In this embodiment, the second feature extraction network includes a linear layer, a plurality of combined feature extraction networks (Local and global combination) connected in series, and an activation layer, where the linear layer is used to convert the input from a high-dimensional sparse feature to a low-dimensional dense feature, the combined feature extraction network is used to extract a local feature and a global associated feature of the input, and the activation layer is used to output weights corresponding to the respective inputs.
Referring to fig. 3, a schematic structural diagram of a combined feature extraction network according to an embodiment of the present invention is shown, where the combined feature extraction network includes a convolution layer, an attention layer, and a linear layer, the convolution layer is used to extract local features of an input, the attention layer is used to extract global associated features of the input, and the linear layer is used to perform dimension reduction processing on the features.
The output of each coding layer in the first characteristic extraction network is used as the input of the second characteristic extraction network, and the second characteristic extraction network enhances the understanding of the input text by learning the local characteristic and the global associated characteristic of the output characteristic of each coding layer, so that the accuracy of classifying the entity relationship in the input text can be improved.
S3, inputting the target word sequence into the first feature extraction network to execute word feature, semantic feature and syntax feature extraction processing, and obtaining a first feature vector of each word in the target word sequence output by each coding layer.
The method comprises the steps of inputting a target word sequence into an embedded layer of a first feature extraction network to perform word vector conversion processing to obtain word vectors of each word in the target word sequence, inputting the word vectors into a plurality of coding layers connected in series to perform word feature, semantic feature and syntax feature extraction processing to obtain first feature vectors of each word output by each coding layer. In this embodiment, the coding layer is 12 layers, and each word corresponds to 12 first feature vectors.
S4, inputting each first feature vector into the second feature extraction network to execute local feature and global associated feature extraction processing, and obtaining a weight value corresponding to each word in the target word sequence.
The second feature extraction network is used for extracting the local features and the global associated features of the input, the first feature vector is fused with the literal features, the semantic features and the syntactic features, and the weight value obtained after the processing of the second feature extraction network is accurate.
Inputting each first feature vector into the second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence, wherein the method comprises the following steps:
c11, merging the first feature vectors to obtain a first feature matrix of each word in the target word sequence;
for example, for the words in the target word sequence, if the first feature vector output by each coding layer is an n-dimensional feature, a first feature matrix obtained by combining the 12 first feature vectors is a 12×n feature.
C12, inputting the first feature matrix into a first linear layer of the second feature extraction network to execute feature dimension reduction processing to obtain a second feature matrix of each word in the target word sequence;
the linear layer is used for carrying out dimension reduction processing on the input characteristics, so that the classification efficiency is improved.
C13, inputting the second feature matrix into a plurality of combined feature extraction networks connected in series of the second feature extraction network to execute local feature and global associated feature extraction processing, so as to obtain a third feature matrix of each word in the target word sequence;
The convolution layer of the combined feature extraction network is used for extracting local features, and the attention layer is used for extracting global associated features, so that the third feature matrix comprises local and global features.
C14, inputting the third feature matrix into a second linear layer of the second feature extraction network to execute feature dimension reduction processing to obtain a third feature vector of each word in the target word sequence;
the second linear layer performs further dimension reduction processing on the third feature matrix.
And C15, inputting the third feature vector into an activation layer of the second feature extraction network to perform weight calculation, so as to obtain a weight value corresponding to each word in the target word sequence.
The activation layer operates through an activation function, and can output a weight value corresponding to each word in the target word sequence.
S5, calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, inputting the second feature vector into the classification network to execute entity relationship classification processing, and obtaining a relationship classification result between entities in the text to be processed.
Through the processing of the first feature extraction network and the second feature extraction network, the features of the input classification network are rich, and the relation types among the entities in the text to be processed can be accurately output.
For example, for the text to be processed, the output relationship classification result is: the relationship between "company a" and "1980" is "company organization-established time", the relationship between "company a" and "guangdong province" is "company organization-place", and the relationship between "1980" and "guangdong province" is "established time-place".
The calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value includes:
d11, calculating a fourth feature vector corresponding to the text to be processed based on the first feature vector and the weight value of each word in the target word sequence output by the last coding layer;
in this embodiment, a second feature vector corresponding to the text to be processed is calculated according to the first feature vector and the weight value of each word output by the last coding layer (i.e. the 12 th coding layer).
The last coding layer has fused the features of each previous coding layer, and the information quantity represented by the output features is the largest.
The calculation formula of the fourth feature vector is as follows: y=a 1 *x 1 +a 2 *x 2 +…+a n *x n Wherein y is a fourth feature vector corresponding to the text to be processed, and x 1 、x 2 、x n A is the first eigenvector of the first, second and nth words in the target word sequence respectively 1 、a 2 、a n The weight values corresponding to the first, second and nth words in the target word sequence are respectively obtained.
D12, calculating a fifth feature vector corresponding to the text to be processed based on first feature vectors of a plurality of preset words in the target word sequence output by the last coding layer;
in this embodiment, the preset word includes a period symbol and each entity initiator, for example, [ CLS ], [ E11], [ E21] and [ E31 ]) in the target word sequence of the text to be processed, where [ CLS ] aggregates the features of the entire target word sequence, [ E11] aggregates the features of the first entity, and [ E21] aggregates the features of the second entity.
And merging the sentence head symbol with the first feature vector of each entity initiator to obtain a fifth feature vector corresponding to the text to be processed.
And D13, stacking the fourth feature vector and the fifth feature vector to obtain a second feature vector corresponding to the text to be processed.
The stacking process is a splicing process, and if the fourth feature vector is a p-dimensional feature and the fifth feature vector is a q-dimensional feature, the number of dimensions of the second feature vector obtained after the stacking process is (p+q).
Inputting the second feature vector into the classification network to perform entity relationship classification processing to obtain a relationship classification result between entities in the text to be processed, including:
and inputting the second feature vector into the classification network to obtain the probability value of each relationship category of every two entities in the text to be processed in the target relationship category set, and taking the relationship category with the maximum probability value as the target relationship category of the corresponding two entities.
In order to prevent low classification efficiency caused by too many relationship categories in the target relationship category set, the method determines the target relationship category set according to the domain categories of the entities in the text to be processed.
The determining process of the target relation class set comprises the following steps:
e11, determining the domain category corresponding to each entity in the text to be processed;
in this embodiment, the entity is matched with the entity library corresponding to each domain category to determine the domain category corresponding to each entity.
E12, acquiring a mapping relation between the domain category and the relation category set, and determining an initial relation category set corresponding to each entity in the text to be processed based on the mapping relation;
in this embodiment, a mapping relationship between the domain category and the relationship category set is stored in advance, and through the mapping relationship, an initial relationship category set corresponding to each entity can be determined.
And E13, taking the set of the initial relation class set as a target relation class set.
And summarizing the initial relation class set corresponding to each entity to obtain the target relation class set corresponding to the text to be processed.
According to the embodiment, the method for classifying the entity relationship based on the artificial intelligence provided by the invention comprises the steps of firstly, executing word segmentation processing and entity marking processing on a text to be processed to obtain a target word sequence; then, inputting the target word sequence into a first feature extraction network of the entity relation classification model to execute extraction processing of literal features, semantic features and syntactic features to obtain a first feature vector of each word in the target word sequence output by each coding layer; then, inputting each first feature vector into a second feature extraction network to execute local feature and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence; and finally, calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, and inputting the second feature vector into a classification network to obtain a relationship classification result between entities in the text to be processed. According to the invention, the literal features, semantic features, syntactic features, local features and global associated features of the text to be processed are extracted, so that the extracted features are richer, the classification accuracy is higher, the feature extraction and classification are performed by the entity relation classification model, no external tool is relied on, and the high classification efficiency is ensured. Therefore, the invention realizes rapid and accurate classification of the relationship between the entities.
Fig. 4 is a schematic block diagram of an artificial intelligence-based entity relationship classification apparatus according to an embodiment of the invention.
The entity relationship classifying device 100 based on artificial intelligence can be installed in electronic equipment. Depending on the functions implemented, the artificial intelligence based entity-relationship classifying apparatus 100 may include a response module 110, an acquisition module 120, a first extraction module 130, a second extraction module 140, and a classification module 150. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the response module 110 is configured to respond to an entity relationship classification request sent by a user based on a client for a text to be processed, and perform word segmentation processing and entity marking processing on the text to be processed, so as to obtain a target word sequence corresponding to the text to be processed.
The step of performing word segmentation and entity marking on the text to be processed to obtain a target word sequence corresponding to the text to be processed comprises the following steps:
A21, executing entity identification processing on the text to be processed to obtain an entity set corresponding to the text to be processed;
a22, performing word segmentation on the text to be processed to obtain an initial word sequence corresponding to the text to be processed;
a23, performing entity marking processing on the initial word sequence based on the entity set to obtain a target word sequence corresponding to the text to be processed.
The obtaining module 120 is configured to obtain an entity relationship classification model from a preset database, where the entity relationship classification model includes a first feature extraction network, a second feature extraction network, and a classification network, and the first feature extraction network includes a plurality of coding layers connected in series.
The construction process of the entity relation classification model comprises the following steps:
b21, respectively constructing a first feature extraction network, a second feature extraction network and a classification network, and connecting the output of the first feature extraction network with the input of the classification network;
and B22, connecting the output of each coding layer in the first characteristic extraction network with the input of the second characteristic extraction network, and connecting the output of the second characteristic extraction network with the input of the classification network to obtain an entity relation classification model.
The first extraction module 130 is configured to input the target word sequence into the first feature extraction network to perform extraction processing of word features, semantic features and syntax features, so as to obtain a first feature vector of each word in the target word sequence output by each coding layer.
And the second extraction module 140 is configured to input each first feature vector into the second feature extraction network to perform local feature extraction and global associated feature extraction processing, so as to obtain a weight value corresponding to each word in the target word sequence.
Inputting each first feature vector into the second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence, wherein the method comprises the following steps:
c21, merging the first feature vectors to obtain a first feature matrix of each word in the target word sequence;
c22, inputting the first feature matrix into a first linear layer of the second feature extraction network to execute feature dimension reduction processing to obtain a second feature matrix of each word in the target word sequence;
c23, inputting the second feature matrix into a plurality of combined feature extraction networks connected in series of the second feature extraction network to execute local feature and global associated feature extraction processing, so as to obtain a third feature matrix of each word in the target word sequence;
C24, inputting the third feature matrix into a second linear layer of the second feature extraction network to execute feature dimension reduction processing to obtain a third feature vector of each word in the target word sequence;
and C25, inputting the third feature vector into an activation layer of the second feature extraction network to perform weight calculation, so as to obtain a weight value corresponding to each word in the target word sequence.
And the classification module 150 is configured to calculate a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, input the second feature vector into the classification network, and perform entity relationship classification processing to obtain a relationship classification result between entities in the text to be processed.
The calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value includes:
d21, calculating a fourth feature vector corresponding to the text to be processed based on the first feature vector and the weight value of each word in the target word sequence output by the last coding layer;
d22, calculating a fifth feature vector corresponding to the text to be processed based on first feature vectors of a plurality of preset words in the target word sequence output by the last coding layer;
And D23, stacking the fourth feature vector and the fifth feature vector to obtain a second feature vector corresponding to the text to be processed.
Inputting the second feature vector into the classification network to perform entity relationship classification processing to obtain a relationship classification result between entities in the text to be processed, including:
and inputting the second feature vector into the classification network to obtain the probability value of each relationship category of every two entities in the text to be processed in the target relationship category set, and taking the relationship category with the maximum probability value as the target relationship category of the corresponding two entities.
The determining process of the target relation class set comprises the following steps:
e21, determining the domain category corresponding to each entity in the text to be processed;
e22, acquiring a mapping relation between the domain category and the relation category set, and determining an initial relation category set corresponding to each entity in the text to be processed based on the mapping relation;
and E23, taking the set of the initial relation class set as a target relation class set.
Fig. 5 is a schematic structural diagram of an electronic device for implementing an artificial intelligence-based entity relationship classification method according to an embodiment of the present invention.
The electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The electronic device 1 may be a computer, a server group formed by a single network server, a plurality of network servers, or a cloud formed by a large number of hosts or network servers based on cloud computing, wherein the cloud computing is one of distributed computing, and is a super virtual computer formed by a group of loosely coupled computer sets.
In the present embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which are communicably connected to each other via a system bus, and the memory 11 stores therein an entity relationship classification program 10, the entity relationship classification program 10 being executable by the processor 12. Fig. 3 shows only the electronic device 1 with the components 11-13 and the entity-relationship classification procedure 10, it will be appreciated by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
Wherein the storage 11 comprises a memory and at least one type of readable storage medium. The memory provides a buffer for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1; in other embodiments, the nonvolatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. In this embodiment, the readable storage medium of the memory 11 is generally used to store an operating system and various application software installed in the electronic device 1, for example, store codes of the entity relationship classifying program 10 in one embodiment of the present invention. Further, the memory 11 may be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices, etc. In this embodiment, the processor 12 is configured to execute the program code or process data stored in the memory 11, for example, execute the entity relationship classifying program 10.
The network interface 13 may comprise a wireless network interface or a wired network interface, the network interface 13 being used for establishing a communication connection between the electronic device 1 and a client (not shown).
Optionally, the electronic device 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The entity-relationship classification program 10 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 12, enable the above-described artificial-intelligence-based entity-relationship classification method.
Specifically, the specific implementation method of the above-mentioned entity relationship classification procedure 10 by the processor 12 may refer to the description of the related steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be nonvolatile or nonvolatile. The computer readable storage medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The computer-readable storage medium has stored thereon an entity relationship classification program 10, the entity relationship classification program 10 being executable by one or more processors to implement the artificial intelligence based entity relationship classification method described above.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. An artificial intelligence based entity relationship classification method, the method comprising:
responding to an entity relation classification request sent by a user based on a client for a text to be processed, and executing word segmentation processing and entity marking processing on the text to be processed to obtain a target word sequence corresponding to the text to be processed;
obtaining an entity relation classification model from a preset database, wherein the entity relation classification model comprises a first feature extraction network, a second feature extraction network and a classification network, and the first feature extraction network comprises a plurality of coding layers connected in series;
inputting the target word sequence into the first feature extraction network to execute word feature, semantic feature and syntactic feature extraction processing to obtain a first feature vector of each word in the target word sequence output by each coding layer;
Inputting each first feature vector into the second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence;
calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, inputting the second feature vector into the classification network to execute entity relationship classification processing, and obtaining a relationship classification result between entities in the text to be processed;
the step of inputting each first feature vector into the second feature extraction network to execute local feature extraction and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence comprises the following steps: merging the first feature vectors to obtain a first feature matrix of each word in the target word sequence; inputting the first feature matrix into a first linear layer of the second feature extraction network to perform feature dimension reduction processing to obtain a second feature matrix of each word in the target word sequence; inputting the second feature matrix into a plurality of combined feature extraction networks connected in series of the second feature extraction network to execute local feature and global associated feature extraction processing to obtain a third feature matrix of each word in the target word sequence; inputting the third feature matrix into a second linear layer of the second feature extraction network to perform feature dimension reduction processing to obtain a third feature vector of each word in the target word sequence; inputting the third feature vector into an activation layer of the second feature extraction network to perform weight calculation to obtain a weight value corresponding to each word in the target word sequence;
The calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value includes: calculating a fourth feature vector corresponding to the text to be processed based on the first feature vector and the weight value of each word in the target word sequence output by the last coding layer; calculating a fifth feature vector corresponding to the text to be processed based on first feature vectors of a plurality of preset words in the target word sequence output by the last coding layer; and stacking the fourth feature vector and the fifth feature vector to obtain a second feature vector corresponding to the text to be processed.
2. The method for classifying entity relationships based on artificial intelligence according to claim 1, wherein the step of performing word segmentation and entity marking on the text to be processed to obtain the target word sequence corresponding to the text to be processed includes:
performing entity identification processing on the text to be processed to obtain an entity set corresponding to the text to be processed;
executing word segmentation processing on the text to be processed to obtain an initial word sequence corresponding to the text to be processed;
and executing entity marking processing on the initial word sequence based on the entity set to obtain a target word sequence corresponding to the text to be processed.
3. The artificial intelligence based entity-relationship classification method of claim 1, wherein the process of constructing the entity-relationship classification model comprises:
respectively constructing a first feature extraction network, a second feature extraction network and a classification network, and connecting the output of the first feature extraction network with the input of the classification network;
and connecting the output of each coding layer in the first characteristic extraction network with the input of the second characteristic extraction network, and connecting the output of the second characteristic extraction network with the input of the classification network to obtain an entity relation classification model.
4. The method for classifying entity relationships based on artificial intelligence according to claim 1, wherein the step of inputting the second feature vector into the classification network to perform entity relationship classification processing to obtain a relationship classification result between entities in the text to be processed comprises:
and inputting the second feature vector into the classification network to obtain the probability value of each relationship category of every two entities in the text to be processed in the target relationship category set, and taking the relationship category with the maximum probability value as the target relationship category of the corresponding two entities.
5. The artificial intelligence based entity-relationship classification method of claim 4 wherein said process of determining a set of target relationship categories comprises:
determining the domain category corresponding to each entity in the text to be processed;
acquiring a mapping relation between a domain category and a relation category set, and determining an initial relation category set corresponding to each entity in the text to be processed based on the mapping relation;
and taking the set of the initial relation class set as a target relation class set.
6. An artificial intelligence based entity-relationship classification apparatus for implementing an artificial intelligence based entity-relationship classification method according to any one of claims 1 to 5, the apparatus comprising:
the response module is used for responding to an entity relation classification request sent by a user based on a client side and aiming at a text to be processed, performing word segmentation processing and entity marking processing on the text to be processed, and obtaining a target word sequence corresponding to the text to be processed;
the system comprises an acquisition module, a classification module and a classification module, wherein the acquisition module is used for acquiring an entity relation classification model from a preset database, the entity relation classification model comprises a first feature extraction network, a second feature extraction network and a classification network, and the first feature extraction network comprises a plurality of coding layers which are connected in series;
The first extraction module is used for inputting the target word sequence into the first feature extraction network to execute extraction processing of literal features, semantic features and syntactic features to obtain a first feature vector of each word in the target word sequence output by each coding layer;
the second extraction module is used for inputting each first feature vector into the second feature extraction network to execute local feature and global associated feature extraction processing to obtain a weight value corresponding to each word in the target word sequence;
and the classification module is used for calculating a second feature vector corresponding to the text to be processed based on the first feature vector and the weight value, inputting the second feature vector into the classification network to execute entity relationship classification processing, and obtaining a relationship classification result among entities in the text to be processed.
7. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores an entity-relationship classification program executable by the at least one processor to cause the at least one processor to perform the artificial intelligence-based entity-relationship classification method of any one of claims 1 to 5.
8. A computer-readable storage medium having stored thereon an entity relationship classification program executable by one or more processors to implement the artificial intelligence based entity relationship classification method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111083860.2A CN113792539B (en) | 2021-09-15 | 2021-09-15 | Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111083860.2A CN113792539B (en) | 2021-09-15 | 2021-09-15 | Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792539A CN113792539A (en) | 2021-12-14 |
| CN113792539B true CN113792539B (en) | 2024-02-20 |
Family
ID=78878565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111083860.2A Active CN113792539B (en) | 2021-09-15 | 2021-09-15 | Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792539B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106855853A (en) * | 2016-12-28 | 2017-06-16 | 成都数联铭品科技有限公司 | Entity relation extraction system based on deep neural network |
| CN110196978A (en) * | 2019-06-04 | 2019-09-03 | 重庆大学 | A kind of entity relation extraction method for paying close attention to conjunctive word |
| WO2019174422A1 (en) * | 2018-03-16 | 2019-09-19 | 北京国双科技有限公司 | Method for analyzing entity association relationship, and related apparatus |
| CN110750642A (en) * | 2019-09-28 | 2020-02-04 | 北京航空航天大学 | CNN-based Chinese relation classification method and system |
| CN111552812A (en) * | 2020-04-29 | 2020-08-18 | 深圳数联天下智能科技有限公司 | Method and device for determining relation category between entities and computer equipment |
| CN112016312A (en) * | 2020-09-08 | 2020-12-01 | 平安科技（深圳）有限公司 | Data relation extraction method and device, electronic equipment and storage medium |
| CN113157923A (en) * | 2021-04-29 | 2021-07-23 | 北京小米移动软件有限公司 | Entity classification method, device and readable storage medium |
| CN113191118A (en) * | 2021-05-08 | 2021-07-30 | 山东省计算中心（国家超级计算济南中心） | Text relation extraction method based on sequence labeling |
| CN113255320A (en) * | 2021-05-13 | 2021-08-13 | 北京熙紫智数科技有限公司 | Entity relation extraction method and device based on syntax tree and graph attention machine mechanism |
-
2021
- 2021-09-15 CN CN202111083860.2A patent/CN113792539B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106855853A (en) * | 2016-12-28 | 2017-06-16 | 成都数联铭品科技有限公司 | Entity relation extraction system based on deep neural network |
| WO2019174422A1 (en) * | 2018-03-16 | 2019-09-19 | 北京国双科技有限公司 | Method for analyzing entity association relationship, and related apparatus |
| CN110196978A (en) * | 2019-06-04 | 2019-09-03 | 重庆大学 | A kind of entity relation extraction method for paying close attention to conjunctive word |
| CN110750642A (en) * | 2019-09-28 | 2020-02-04 | 北京航空航天大学 | CNN-based Chinese relation classification method and system |
| CN111552812A (en) * | 2020-04-29 | 2020-08-18 | 深圳数联天下智能科技有限公司 | Method and device for determining relation category between entities and computer equipment |
| CN112016312A (en) * | 2020-09-08 | 2020-12-01 | 平安科技（深圳）有限公司 | Data relation extraction method and device, electronic equipment and storage medium |
| CN113157923A (en) * | 2021-04-29 | 2021-07-23 | 北京小米移动软件有限公司 | Entity classification method, device and readable storage medium |
| CN113191118A (en) * | 2021-05-08 | 2021-07-30 | 山东省计算中心（国家超级计算济南中心） | Text relation extraction method based on sequence labeling |
| CN113255320A (en) * | 2021-05-13 | 2021-08-13 | 北京熙紫智数科技有限公司 | Entity relation extraction method and device based on syntax tree and graph attention machine mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的中文实体关系抽取方法;孙紫阳;顾君忠;杨静;;计算机工程;20171027(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792539A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111241304B (en) | Answer generation method based on deep learning, electronic device and readable storage medium | |
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN113157927B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN114462412B (en) | Entity identification method, entity identification device, electronic equipment and storage medium | |
| CN115238670B (en) | Information text extraction method, device, equipment and storage medium | |
| CN113688239B (en) | Text classification method and device under small sample, electronic equipment and storage medium | |
| CN114706985A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| CN116450829A (en) | Medical text classification method, device, equipment and medium | |
| CN114818685B (en) | Keyword extraction method and device, electronic equipment and storage medium | |
| CN113705692B (en) | Emotion classification method and device based on artificial intelligence, electronic equipment and medium | |
| CN116468025A (en) | Electronic medical record structuring method and device, electronic equipment and storage medium | |
| CN113792539B (en) | Entity relationship classification method and device based on artificial intelligence, electronic equipment and medium | |
| CN113656586B (en) | Emotion classification method, emotion classification device, electronic equipment and readable storage medium | |
| CN113850260B (en) | Key information extraction method and device, electronic equipment and readable storage medium | |
| CN113610580B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
| CN115346095A (en) | Visual question answering method, device, equipment and storage medium | |
| CN114281991A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN114139530A (en) | Synonym extraction method and device, electronic equipment and storage medium | |
| CN114398877A (en) | Theme extraction method and device based on artificial intelligence, electronic equipment and medium | |
| CN113706207A (en) | Order transaction rate analysis method, device, equipment and medium based on semantic analysis | |
| CN114742060B (en) | Entity identification method, entity identification device, electronic equipment and storage medium | |
| CN112528647A (en) | Similar text generation method and device, electronic equipment and readable storage medium | |
| CN114462411B (en) | Named entity recognition method, device, equipment and storage medium |
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 |