CN114048748B - Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium - Google Patents
Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium Download PDFInfo
- Publication number
- CN114048748B CN114048748B CN202111363516.9A CN202111363516A CN114048748B CN 114048748 B CN114048748 B CN 114048748B CN 202111363516 A CN202111363516 A CN 202111363516A CN 114048748 B CN114048748 B CN 114048748B
- Authority
- CN
- China
- Prior art keywords
- entity recognition
- named entity
- text
- processed
- layer
- 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 41
- 239000013598 vector Substances 0.000 claims abstract description 57
- 238000012216 screening Methods 0.000 claims abstract description 50
- 238000000605 extraction Methods 0.000 claims abstract description 32
- 230000004927 fusion Effects 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 35
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000012634 fragment Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 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
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 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
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Abstract
The invention provides a named entity recognition system, a named entity recognition method, electronic equipment and a named entity recognition medium, wherein the named entity recognition system comprises the following components: a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer; the word embedding layer is used for converting the text to be processed into characteristic word vectors and inputting the characteristic word vectors into the coarse granularity screening layer; the coarse granularity screening layer is used for screening the feature word vectors based on the target scene, and inputting the screened feature word vectors into the fine granularity screening layer; the fine granularity extraction layer is used for extracting target entities corresponding to the target scene from the filtered feature word vectors. The invention can shorten the processing period of mass texts and improve the processing efficiency under the condition of meeting the requirement of a certain accuracy.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a named entity recognition system, a named entity recognition method, an electronic device, and a medium.
Background
Named entity recognition (Named Entity Recognition, NER) task is one of the basic tasks in the field of artificial intelligence that involves natural language processing (Natural Language Processing, NLP) technology, which aims to extract predefined target entities from text, such as person names, organization names, predefined professional names, etc., providing rich information for subsequent classes of deeper text tasks. In the present big data age, massive trivial information and text fragments can be quickly stacked in a short time, and although various algorithms related to NER are endless at present, the massive texts are difficult to quickly process in a short time under the requirement of a certain accuracy.
Disclosure of Invention
In view of the above, the present invention aims to provide a named entity recognition system, a named entity recognition method, an electronic device and a named entity recognition medium, which can shorten the processing period of a large number of texts and improve the processing efficiency under the condition of meeting the requirement of a certain accuracy.
In order to achieve the above object, the technical scheme adopted by the embodiment of the invention is as follows:
in a first aspect, an embodiment of the present invention provides a named entity recognition system, including: a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer; the word embedding layer is used for converting the text to be processed into characteristic word vectors and inputting the characteristic word vectors into the coarse granularity screening layer; the coarse granularity screening layer is used for screening the feature word vectors based on the target scene, and inputting the screened feature word vectors into the fine granularity screening layer; the fine granularity extraction layer is used for extracting target entities corresponding to the target scene from the filtered feature word vectors.
In one embodiment, the word embedding layer includes: a word segmentation model and a pre-training language model; the word segmentation model is used for segmenting the text to be processed; the pre-training language model is used for converting the text to be processed after word segmentation into characteristic word vectors.
In one embodiment, the coarse-granularity screening layer includes one or more of the following scene classifiers: rule classifier, machine learning classifier, deep learning classifier.
In one embodiment, the fine grain decimation layer comprises a one-dimensional convolution network comprising: the system comprises a first sub-network, a second sub-network, a feature fusion module and an entity identification module; the first sub-network is used for carrying out a first convolution operation on the filtered feature word vectors to obtain a first convolution result; the second sub-network is used for carrying out second convolution operation on the first convolution result to obtain a second convolution result; the feature fusion module is used for carrying out feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and the entity identification module is used for carrying out entity identification based on the feature fusion result to obtain a target entity.
In a second aspect, an embodiment of the present invention provides a named entity identifying method, including: acquiring a text to be processed; inputting a text to be processed into a preset named entity recognition system; wherein the named entity recognition system is the system of any one of the first aspects provided above; and carrying out entity recognition on the text to be processed through a named entity recognition system to obtain a target entity.
In one embodiment, the step of performing entity recognition on the text to be processed through the named entity recognition system to obtain the target entity includes: converting the text to be processed into a feature word vector through a named entity recognition system; screening the feature word vectors based on the target scene to obtain screened feature word vectors; and extracting a target entity corresponding to the target scene from the filtered feature word vector.
In one embodiment, the step of converting the text to be processed into feature word vectors by a named entity recognition system includes: word segmentation is carried out on the text to be processed through a named entity recognition system; and converting the text to be processed after word segmentation into a characteristic word vector.
In one embodiment, the step of extracting the target entity corresponding to the target scene from the filtered feature word vector includes: performing a first convolution operation on the feature word vector to obtain a first convolution result; performing a second convolution operation on the first convolution result to obtain a second convolution result; performing feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and carrying out entity identification based on the feature fusion result to obtain a target entity corresponding to the target scene.
In a third aspect, an embodiment of the present invention provides an electronic device comprising a processor and a memory storing computer executable instructions executable by the processor to perform the steps of the method of any one of the second aspects described above.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any of the second aspects provided above.
The embodiment of the invention has the following beneficial effects:
the named entity recognition system, the named entity recognition method, the electronic equipment and the named entity recognition medium provided by the embodiment of the invention, wherein the named entity recognition system comprises the following components: a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer; the word embedding layer is used for converting the text to be processed into characteristic word vectors and inputting the characteristic word vectors into the coarse granularity screening layer; the coarse granularity screening layer is used for screening the feature word vectors based on the target scene, and inputting the screened feature word vectors into the fine granularity screening layer; the fine granularity extraction layer is used for extracting target entities corresponding to the target scene from the filtered feature word vectors. According to the system, the recognition process is split into coarse granularity screening and fine granularity extraction of related entity texts, firstly, the text to be processed far away from a target scene is separated out as quickly as possible through the coarse granularity screening layer, and then the target entity is extracted through the fine granularity extraction layer, so that the processing speed of the entity texts is accelerated.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a named entity recognition system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another named entity recognition system according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a coarse-grained screening layer according to an embodiment of the invention;
FIG. 4 is a training flowchart of a named entity recognition system according to an embodiment of the present invention;
FIG. 5 is a flowchart of a named entity recognition method according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. 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.
In the present big data age, massive trivial information and text fragments can be quickly stacked in a short time, and although various algorithms related to NER are layered endlessly at present, in practical engineering application, especially in the field of financial wind control, how to quickly process the massive texts in a short time under the condition of meeting the requirement of a certain accuracy is a pain point of engineering application.
At present, the main current NER algorithm such as a cyclic neural network or a graph neural network structure of Bert+Bi-LSTM, bert+Transformer and the like can meet higher accurate effects, but when hundreds of millions of short texts are processed rapidly, the application of the network structure needs a processing machine to have very high GPU configuration resources, and under the condition of limited implementation cost, the Bert memory or the cyclic neural network model cannot meet the performance requirement of rapid processing. Based on the above, the cavity convolution model IDCNN/IDCNN+CRF algorithm enters application work tables of many NLP engineers, and under the condition of the same ratio, the calculation performance is greatly improved (the text processing speed is about 2 times of the former), but the accuracy rate does not show great advantages compared with various cyclic neural networks under Bert, for example, the accuracy rate of Bi-LSTM+CRF/Bi-LSTM is 90.43/89.34, and the accuracy rate of IDCNN+CRF/IDCNN is 90.54/90.32. For the cavity convolution layer, the purpose is mainly to increase the sense field of view and avoid that the resolution of the traditional CNN is lost due to the fact that the multi-scale context information is integrated in a Pooling mode, but for short texts, the text length of the traditional CNN is limited, and under the condition that the calculation performance is considered, the effect of performing the field of view by utilizing the cavity convolution layer of the IDCNN is not necessarily the best mode because the calculation speed of the two-dimensional cavity convolution layer is slower than that of the one-dimensional convolution layer. Therefore, the existing NER algorithm is difficult to meet the requirement of a certain accuracy, and massive texts are rapidly processed in a short time.
Based on the above, the named entity recognition system, the named entity recognition method, the electronic equipment and the named entity recognition medium provided by the embodiment of the invention can shorten the processing period of mass texts and improve the processing efficiency under the condition of meeting the requirement of a certain accuracy.
For the sake of understanding the present embodiment, first, a named entity recognition system disclosed in the present embodiment will be described in detail, referring to a schematic structural diagram of a named entity recognition system shown in fig. 1, which schematically includes: the word embedding layer, the coarse granularity screening layer and the fine granularity extraction layer are sequentially connected.
The word embedding layer is used for converting the text to be processed into a characteristic word vector and inputting the characteristic word vector into the coarse granularity screening layer; the coarse granularity screening layer is used for screening the feature word vectors based on the target scene, rapidly filtering out scenes irrelevant to the target entity or texts with weak correlation, and inputting the screened feature word vectors into the fine granularity screening layer; the fine granularity extraction layer is used for extracting target entities corresponding to the target scene from the filtered feature word vectors.
According to the named entity recognition system provided by the embodiment of the invention, the recognition process is split into coarse granularity screening and fine granularity extraction of related entity texts, firstly, texts to be processed far away from a target scene are separated out as quickly as possible through the coarse granularity screening layer, and then the target entity is obtained through the fine granularity extraction layer, so that the processing speed of the entity texts is increased.
Further, referring to the schematic structural diagram of another named entity recognition system shown in fig. 2, it is shown that the general mechanism of the named entity recognition system is divided into three layers: a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer.
Specifically, the word embedding layer includes: a word segmentation model and a pre-training language model; the word segmentation model is used for segmenting the text to be processed; the pre-training language model is used for converting the text to be processed after word segmentation into characteristic word vectors. After Word embedding layer carries out Word segmentation (token) on the batch of texts, the segmented texts are converted into batch feature Word vectors through a Word vector layer generated under a pre-training language model (Word 2 vec). In the selection of the pre-training language model of the word embedding layer, the word embedding layer relates to large-scale data batch processing, and the performance of the second-generation pre-training language model is compared with that of the first-generation pre-training language model, and the second-generation pre-training language model is represented by Bert, so that the word embedding layer has better context semantic understanding performance, but brings huge performance processing pressure and configuration pressure, and is a difficult problem in industrial batch processing speed. For short text, the text content is often single-segment or small-segment sentence content, and the advantages of the language model represented by the second-generation pre-training language model Bert are mainly reflected on the content-level, namely, the text content plays a more remarkable effect on the long text of the multi-segment sentence. Based on this, a pre-trained language model Word2vec can be employed in the present application, exploiting its advantages in short text applications.
In one embodiment, a coarse-grained screening layer, i.e., a Scene Classifier, is used to quickly filter out scenes or weakly relevant text that are not relevant to the target extraction entity, such as: to extract the entity of financial wind control type short text, the coarse granularity screening layer can filter the relevant text of scenes such as schools, hospitals and the like.
It is considered that the named entity recognition task is itself a classification task, i.e. fine-grained classification of each word or word in a text, to determine the location, part of speech, etc. of the target entity in the text by the final classification. In massive texts, application of professional entities often appears in one or more types of scenes, and a conventional named entity recognition method can directly classify characters/words in each text in fine granularity, and the purpose of recognizing the positions and parts of speech of the entities is achieved by recognizing information such as Targetword-B (initial position tag), targetword-I (intermediate position tag), targetword-E (end position tag), targetword-S (individual character/word position tag), 0 (irrelevant character/word tag) and the like. In hundreds of millions of random texts, most of the texts are often irrelevant scene texts for predefined professional entity targets that need to be extracted, i.e. the fine-grained classification result of most of the texts is often a full 0 series. Therefore, in order to accelerate the data processing, referring to fig. 3, the coarse-granularity filtering layer in the embodiment of the present invention may select one or more of the following scene classifiers according to different task sources: rule classifiers (syncax Rules), machine learning classifiers (ML-classifiers), deep learning classifiers (DL-classifiers). The rule classifier can be a text tcnn deep learning model, and the rule classifier can be a keyword or regular rule based filtering.
The coarse-granularity screening layer in the embodiment of the invention is similar to a coarse-granularity flow divider, text irrelevant to a professional target entity is directly separated as far as possible, and the processing performance of the macro-coarse-granularity classifier is obviously better than the fine-granularity classification processing performance because the classification task of a single text is simplified. For a financial wind control type short text scene, the processing speed of only a single CPU processor (adopting AMD Ryzen7 PRO AVX2 8 core 16 threads) can reach 3.3 pieces/ms, namely 8.42 h/billion level, the scene group of related type and the scene group of unrelated entity identification task can be completely separated, and the micro-f1 of the scene type can reach 95.6%, so that the data processing speed is greatly accelerated.
In one embodiment, the fine granularity extraction layer, NER Classifier Block entity extraction layer, i.e. classification and extraction of words or characters within a single text, extracts target entity information. In the embodiment of the present invention, in combination with the actual situation of the short text, the fine granularity extraction layer is reformed by using a one-dimensional convolution network structure, and as shown in fig. 2, the one-dimensional convolution network of the fine granularity extraction layer includes: the system comprises a first sub-network, a second sub-network, a feature fusion module and an entity identification module; the first sub-network is used for carrying out a first convolution operation on the filtered feature word vectors to obtain a first convolution result; the second sub-network is used for carrying out second convolution operation on the first convolution result to obtain a second convolution result; the feature fusion module is used for carrying out feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and the entity identification module is used for carrying out entity identification based on the feature fusion result to obtain a target entity.
The fine granularity extraction layer in the embodiment of the invention adopts a convolution network structure which is more suitable for reconstruction of short texts, and is different from a common cyclic neural network (RNN, LSTM, GRU and the like) or a Transfomer structure, so that the calculation speed is higher; meanwhile, the method of using Pooling by a conventional CNN network is skillfully avoided during final feature processing, so that the information of the feature fusion module is as rich as possible to improve the accuracy of the model and the overfitting is avoided.
The named entity recognition system provided by the embodiment of the invention skillfully performs layering reconstruction based on the classification angle by combining the condition of short texts, the recognition process of the named entity recognition system is divided into coarse granularity screening and entity fine granularity extraction of related entity texts, and scenes far away from target entities are separated out in coarse granularity classification (Scene classification) as quickly as possible so as to accelerate the processing speed of actual irrelevant texts; meanwhile, in the fine-granularity classifier (NER Classifier Block), the invention avoids the conventional method of using a cyclic neural network to identify the named entity, uses a one-dimensional convolution network structure layer to conduct the task of the named entity, constructs a convolution network structure suitable for short texts, accelerates the calculation processing speed, combines the characteristics of the short texts, and skillfully avoids the traditional CNN network using a Pooling mode in a final feature processing block, so that the information of a feature fusion module is as rich as possible to improve the accuracy of the model and is not too fit. Under the cooperation of the coarse-granularity screening layer and the fine-granularity extraction layer, the processing performance of massive texts can be accelerated, and the processing performance of the massive texts can be accelerated, and especially the texts with the size of more than one hundred million levels can be related.
In addition, on a single common CPU processor (adopting AMD Ryzen7 PRO AVX2 8 core 16 thread), the processing speed of the coarse classification screening in the Scene classification link can reach 3.3 strips/ms, namely 8.42 h/billion level, and micro-f1 can reach 0.956; the processing speed of the fine grain classifier is about 0.5 bar/ms, namely 55.56 h/billion grade, and f1 can reach 0.9223. In practical applications, the processing performance of the system fluctuates in the range of 8.42 h/billion-55.56 h/billion-level due to the change of scene correlation related to batch text, such as multi-CPU/GPU cluster processing, and the processing performance is improved by times.
For the named entity recognition system, the whole system model needs to be trained, optimized and evaluated before the formal work, referring to a training flowchart of the named entity recognition system shown in fig. 4, the training process mainly includes the following steps S402 to S408:
step S402: and acquiring massive text data.
Step S404: and marking the acquired text data.
Specifically, text data marking is mainly divided into two parts: the first part is the scene marking of the coarse-granularity screening layer, text data is marked according to the scene, and when the coarse-granularity classification layer only adopts Syntax Rules to judge Rules, data marking is not needed; when the coarse-granularity classification layer adopts a machine learning classifier or a deep learning classifier, scene marking of text data is needed; the second part is entity marking of the fine granularity extraction layer, namely sequence marking of text entity position and part of speech. Therefore, if the coarse-granularity classification layer comprises a machine learning classifier or a deep learning classifier, each marked text should comprise two parts of marking information of scene marking and entity marking at the same time, otherwise, only the marking information of entity marking needs to be contained.
Step S406: and carrying out data preprocessing and data set division according to the marked text data.
The text data marked is divided into a training set, a verification set and a test set according to a certain proportion (such as 8:1:1), and the abstract text data is converted into structured data which can be learned by a model after passing through a word embedding layer.
Step S408: and training the coarse granularity screening layer and the fine granularity extraction layer based on the divided data set to obtain an optimal model.
Specifically, the training set is used for training and learning the model, the verification set is used for capturing the optimized model in the training process, and the test set is used for evaluating the quality and accuracy of the trained model.
Further, the trained or optimized Scene classifiers and NER Classifier Block are applied to the hierarchical structure of fig. 1, and the process of quickly discriminating and extracting the related entity text is completed according to the three-layer structure (word embedding layer, coarse granularity screening layer and fine granularity extraction layer) shown in fig. 1.
For the named entity recognition system, the embodiment of the present invention further provides a named entity recognition method, referring to a flowchart of a named entity recognition method shown in fig. 5, which mainly includes steps S502 to S506:
step S502: and acquiring a text to be processed.
The text to be processed may include a huge amount of short text.
Step S504: and inputting the text to be processed into a preset named entity recognition system.
The named entity recognition system comprises a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer.
Step S506: and carrying out entity recognition on the text to be processed through a named entity recognition system to obtain a target entity.
Specifically, the named entity recognition system firstly converts a text to be processed into a characteristic word vector through a word embedding layer; then screening the feature word vectors based on the target scene through a coarse-granularity screening layer, rapidly filtering out scenes irrelevant to the target entity or texts with weak correlation, and inputting the screened feature word vectors into a fine-granularity screening layer; and finally, extracting target entities corresponding to the target scene from the screened feature word vectors through a fine granularity extraction layer.
According to the named entity recognition method provided by the embodiment of the invention, named entity recognition can be performed through the named entity recognition system, the named entity recognition system divides the recognition process into coarse granularity screening and fine granularity extraction of related entity texts, firstly, texts to be processed far away from a target scene are separated out as quickly as possible through the coarse granularity screening layer, then, the target entity is obtained through the fine granularity extraction layer, so that the processing speed of the entity texts is increased.
In one embodiment, when converting text to be processed into feature word vectors by the named entity recognition system, the following may be used, but is not limited to: firstly, word segmentation is carried out on a text to be processed through a named entity recognition system; and then, converting the segmented text to be processed into a characteristic word vector.
In one embodiment, when extracting the target entity corresponding to the target scene from the filtered feature word vector, the following manner may be adopted, but is not limited to: firstly, performing a first convolution operation on a feature word vector to obtain a first convolution result; then, performing a second convolution operation on the first convolution result to obtain a second convolution result; then, performing feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and finally, carrying out entity identification based on the feature fusion result to obtain a target entity corresponding to the target scene.
The method provided by the embodiment of the present invention has the same implementation principle and technical effects as those of the embodiment of the system, and for the sake of brief description, reference may be made to the corresponding content in the embodiment of the system where the embodiment of the method is not mentioned.
It should be noted that all the embodiments mentioned in the examples of the present invention are merely exemplary, and may be different from the present examples in practical application, and are not limited herein.
The embodiment of the invention also provides electronic equipment, which comprises a processor and a storage device; the storage means has stored thereon a computer program which, when run by a processor, performs the method according to any of the above embodiments.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 100 includes: a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 being connected by the bus 62; the processor 60 is arranged to execute executable modules, such as computer programs, stored in the memory 61.
The memory 61 may include a high-speed random access memory (RAM, random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is achieved via at least one communication interface 63 (which may be wired or wireless), and may use the internet, a wide area network, a local network, a metropolitan area network, etc.
Bus 62 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.
The memory 61 is configured to store a program, and the processor 60 executes the program after receiving an execution instruction, and the method executed by the apparatus for flow defining disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 60 or implemented by the processor 60.
The processor 60 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuitry in hardware or instructions in software in the processor 60. The processor 60 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (Digital Signal Processing, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory 61 and the processor 60 reads the information in the memory 61 and in combination with its hardware performs the steps of the method described above.
The computer program product of the readable storage medium provided by the embodiment of the present invention includes a computer readable storage medium storing a program code, where the program code includes instructions for executing the method described in the foregoing method embodiment, and the specific implementation may refer to the foregoing method embodiment and will not be described herein.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In addition, in the description of embodiments of the present invention, unless explicitly stated and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in 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 (7)
1. A named entity recognition system, comprising: a word embedding layer, a coarse granularity screening layer and a fine granularity extraction layer;
the word embedding layer is used for converting the text to be processed into characteristic word vectors and inputting the characteristic word vectors into the coarse granularity screening layer;
the coarse granularity screening layer is used for screening the feature word vectors based on a target scene, and inputting the screened feature word vectors into the fine granularity screening layer;
the fine granularity extraction layer is used for extracting target entities corresponding to the target scene from the screened feature word vectors;
the fine grain extraction layer comprises a one-dimensional convolution network comprising: the system comprises a first sub-network, a second sub-network, a feature fusion module and an entity identification module; the first subnetwork is used for carrying out a first convolution operation on the filtered feature word vectors to obtain a first convolution result; the second sub-network is used for performing a second convolution operation on the first convolution result to obtain a second convolution result; the feature fusion module is used for carrying out feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and the entity identification module is used for carrying out entity identification based on the feature fusion result to obtain the target entity.
2. The named entity recognition system of claim 1, wherein the word embedding layer comprises: a word segmentation model and a pre-training language model;
the word segmentation model is used for segmenting the text to be processed;
the pre-training language model is used for converting the text to be processed after word segmentation into the characteristic word vector.
3. The system of claim 1, wherein the coarse-granularity screening layer comprises one or more of the following scene classifiers: rule classifier, machine learning classifier, deep learning classifier.
4. A named entity recognition method, comprising:
acquiring a text to be processed;
inputting the text to be processed into a preset named entity recognition system; wherein the named entity recognition system is the system of any one of claims 1 to 3;
performing entity recognition on the text to be processed through the named entity recognition system to obtain a target entity;
the step of performing entity recognition on the text to be processed through the named entity recognition system to obtain a target entity comprises the following steps: converting the text to be processed into a feature word vector through the named entity recognition system; screening the feature word vectors based on a target scene to obtain screened feature word vectors; extracting a target entity corresponding to the target scene from the screened characteristic word vector;
the step of extracting the target entity corresponding to the target scene from the filtered feature word vector comprises the following steps: performing a first convolution operation on the feature word vector to obtain a first convolution result; performing a second convolution operation on the first convolution result to obtain a second convolution result; performing feature fusion operation on the first convolution result and the second convolution result to obtain a feature fusion result; and carrying out entity identification based on the feature fusion result to obtain a target entity corresponding to the target scene.
5. The method of claim 4, wherein the step of converting the text to be processed into feature word vectors by the named entity recognition system comprises:
word segmentation is carried out on the text to be processed through the named entity recognition system;
and converting the text to be processed after word segmentation into a characteristic word vector.
6. An electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the steps of the method of any one of claims 4 to 5.
7. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor performs the steps of the method of any of the preceding claims 4 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111363516.9A CN114048748B (en) | 2021-11-17 | 2021-11-17 | Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111363516.9A CN114048748B (en) | 2021-11-17 | 2021-11-17 | Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114048748A CN114048748A (en) | 2022-02-15 |
| CN114048748B true CN114048748B (en) | 2024-04-05 |
Family
ID=80209919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111363516.9A Active CN114048748B (en) | 2021-11-17 | 2021-11-17 | Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114048748B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918500A (en) * | 2019-01-17 | 2019-06-21 | 平安科技（深圳）有限公司 | File classification method and relevant device based on convolutional neural networks |
| CN111368541A (en) * | 2018-12-06 | 2020-07-03 | 北京搜狗科技发展有限公司 | Named entity identification method and device |
| WO2020232861A1 (en) * | 2019-05-20 | 2020-11-26 | 平安科技（深圳）有限公司 | Named entity recognition method, electronic device and storage medium |
| CN112711948A (en) * | 2020-12-22 | 2021-04-27 | 北京邮电大学 | Named entity recognition method and device for Chinese sentences |
| CN112800764A (en) * | 2020-12-31 | 2021-05-14 | 江苏网进科技股份有限公司 | Entity extraction method in legal field based on Word2Vec-BilSTM-CRF model |
| CN112818694A (en) * | 2021-03-02 | 2021-05-18 | 浙江工业大学 | Named entity recognition method based on rules and improved pre-training model |
| CN112989829A (en) * | 2021-02-10 | 2021-06-18 | 海尔数字科技（上海）有限公司 | Named entity identification method, device, equipment and storage medium |
-
2021
- 2021-11-17 CN CN202111363516.9A patent/CN114048748B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111368541A (en) * | 2018-12-06 | 2020-07-03 | 北京搜狗科技发展有限公司 | Named entity identification method and device |
| CN109918500A (en) * | 2019-01-17 | 2019-06-21 | 平安科技（深圳）有限公司 | File classification method and relevant device based on convolutional neural networks |
| WO2020232861A1 (en) * | 2019-05-20 | 2020-11-26 | 平安科技（深圳）有限公司 | Named entity recognition method, electronic device and storage medium |
| CN112711948A (en) * | 2020-12-22 | 2021-04-27 | 北京邮电大学 | Named entity recognition method and device for Chinese sentences |
| CN112800764A (en) * | 2020-12-31 | 2021-05-14 | 江苏网进科技股份有限公司 | Entity extraction method in legal field based on Word2Vec-BilSTM-CRF model |
| CN112989829A (en) * | 2021-02-10 | 2021-06-18 | 海尔数字科技（上海）有限公司 | Named entity identification method, device, equipment and storage medium |
| CN112818694A (en) * | 2021-03-02 | 2021-05-18 | 浙江工业大学 | Named entity recognition method based on rules and improved pre-training model |
Non-Patent Citations (1)
| Title |
|---|
| 多场景文本的细粒度命名实体识别;盛剑 等;《中文信息学报》;正文第1-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114048748A (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110032737B (en) | Boundary combination named entity recognition method based on neural network | |
| CN111475649B (en) | False news prediction method, system, device and medium based on deep learning | |
| CN107291822A (en) | The problem of based on deep learning disaggregated model training method, sorting technique and device | |
| CN108108355A (en) | Text emotion analysis method and system based on deep learning | |
| CN109241383B (en) | A kind of type of webpage intelligent identification Method and system based on deep learning | |
| CN108228704A (en) | Identify method and device, the equipment of Risk Content | |
| CN110309301B (en) | Enterprise category classification method and device and intelligent terminal | |
| CN113051500B (en) | Phishing website identification method and system fusing multi-source data | |
| CN109543826A (en) | A kind of activation amount quantization method and device based on deep neural network | |
| CN104933420A (en) | A scene image identification method and a scene image identification device | |
| Li et al. | Publication date estimation for printed historical documents using convolutional neural networks | |
| CN112528637A (en) | Text processing model training method and device, computer equipment and storage medium | |
| CN110968689A (en) | Training method of criminal name and law bar prediction model and criminal name and law bar prediction method | |
| CN104978354A (en) | Text classification method and text classification device | |
| CN113723330A (en) | Method and system for understanding chart document information | |
| CN109918658A (en) | A kind of method and system obtaining target vocabulary from text | |
| CN111475651B (en) | Text classification method, computing device and computer storage medium | |
| CN113032525A (en) | False news detection method and device, electronic equipment and storage medium | |
| CN111241271B (en) | Text emotion classification method and device and electronic equipment | |
| CN115374325A (en) | Website classification method and device, classification equipment and storage medium | |
| CN112732910B (en) | Cross-task text emotion state evaluation method, system, device and medium | |
| CN111611781B (en) | Data labeling method, question answering device and electronic equipment | |
| CN114048748B (en) | Named entity recognition system, named entity recognition method, named entity recognition electronic equipment and named entity recognition medium | |
| CN116910251A (en) | Text classification method, device, equipment and medium based on BERT model | |
| CN115438658A (en) | Entity recognition method, recognition model training method and related device |
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 |