CN113157927B - Text classification method, apparatus, electronic device and readable storage medium - Google Patents
Text classification method, apparatus, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN113157927B CN113157927B CN202110581189.8A CN202110581189A CN113157927B CN 113157927 B CN113157927 B CN 113157927B CN 202110581189 A CN202110581189 A CN 202110581189A CN 113157927 B CN113157927 B CN 113157927B
- Authority
- CN
- China
- Prior art keywords
- text
- sequence
- classified
- word
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013145 classification model Methods 0.000 claims abstract description 87
- 238000000605 extraction Methods 0.000 claims abstract description 57
- 230000011218 segmentation Effects 0.000 claims abstract description 57
- 230000004927 fusion Effects 0.000 claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 34
- 230000001537 neural effect Effects 0.000 claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims description 73
- 239000013598 vector Substances 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of semantic parsing, and discloses a text classification method, which comprises the following steps: carrying out category label marking on each text in a text set to obtain a target label set of the text set; performing text splicing processing on the text set and the target tag set to obtain a sample sequence set; performing iterative training based on neural feature fusion extraction on a pre-constructed text classification model by using the sample sequence set until the text classification model converges to obtain a trained text classification model; when receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result. The invention also relates to a blockchain technique, the set of text may be stored in a blockchain node. The invention also provides a text classification device, electronic equipment and a storage medium. The invention can improve the accuracy of text classification.
Description
Technical Field
The present invention relates to the field of semantic parsing, and in particular, to a text classification method, apparatus, electronic device, and readable storage medium.
Background
With the development of artificial intelligence, the field of natural language processing becomes an important component of artificial intelligence, and text classification is also receiving attention as a basic technology in the field of natural language processing.
However, at present, text classification is carried out by means of a model, only simple feature fusion among words is considered in the model classification process, feature extraction is incomplete, and therefore the accuracy of text classification is low.
Disclosure of Invention
The invention provides a text classification method, a text classification device, electronic equipment and a computer readable storage medium, and mainly aims to improve the accuracy of text classification.
In order to achieve the above object, the present invention provides a text classification method, including:
performing intention recognition on each text in a text set, and performing category label marking on each text in the text set according to a result of the intention recognition to obtain a target label set of the text set;
performing word segmentation processing on each text in the text set, and performing sequence combination according to the word segmentation processing result to obtain a text sequence of each text;
Performing text splicing processing on all the labels in the target label set and the text sequence to obtain a sample sequence set;
training a pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model;
when receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
When receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
Optionally, the text splicing processing is performed on all tags in the target tag set and the text sequence to obtain a sample sequence set, including:
randomly combining all the tags in the target tag set to obtain a tag sequence;
splicing each text sequence with the tag sequence by using preset characters to obtain a sample sequence;
And summarizing all sample sequences to obtain the sample sequence set.
Optionally, the word segmentation processing is performed on each text in the text set, and sequence combination is performed according to the word segmentation processing result, so as to obtain a text sequence of each text, including:
performing word segmentation on each text in the text set by using a preset word segmentation dictionary to obtain a corresponding initial text word set;
deleting the stop words by using the initial text word set to obtain the text word set;
and combining each word in the text word set according to the sequence in the corresponding text to obtain a text sequence of each text.
Optionally, the training the pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model includes:
step A: converting words in each sample sequence into vectors by utilizing a coding layer of the text classification model, and combining all the vectors obtained by conversion according to the sequence of the corresponding words in the sample sequence to obtain a sample matrix;
and (B) step (B): performing neural feature fusion extraction on the sample matrix by utilizing a feature extraction layer of the text classification model to obtain a fusion feature matrix;
Step C: performing weight calculation on the fusion feature matrix by using an attention mechanism layer of the text classification model to obtain a target matrix;
step D: calculating a classification prediction probability value corresponding to the target matrix by using a preset activation function;
step E: determining a sample classification true value according to the category label of the text corresponding to the sample matrix, and calculating a loss value between the classification prediction probability value and the sample classification true value by using a preset loss function;
step F: and (C) updating the model parameters of the text classification model when the loss value is greater than or equal to a preset loss threshold value, returning to the step (A) for iterative training until the loss value is less than the preset loss threshold value, and stopping training to obtain the trained text classification model.
Optionally, the feature extraction layer of the text classification model performs neural feature fusion extraction on the sample matrix to obtain a fusion feature matrix, including:
obtaining a target column by traversing and selecting the columns of the sample matrix;
performing neural feature fusion extraction on the target column to obtain a feature word vector;
and transversely combining all the feature word vectors according to the sequence of the corresponding target columns in the sample matrix to obtain the feature matrix.
Optionally, the feature extraction layer of the text classification model performs neural feature fusion extraction on the sample matrix to obtain a fusion feature matrix, including:
traversing and selecting the columns of the sample matrix to obtain a target column;
performing neural feature fusion extraction on the target column to obtain a feature word vector;
and transversely combining all the feature word vectors according to the sequence of the corresponding target columns in the sample matrix to obtain the feature matrix.
Optionally, the performing neural feature fusion extraction on the target column to obtain a feature word vector includes:
performing tensor multiplication calculation on the target column and each column of the sample matrix to obtain a first word vector matrix;
stacking all the first word vector matrixes according to the sequence of the corresponding columns in the sample matrix to obtain a three-dimensional word vector matrix;
longitudinally segmenting the three-dimensional word vector matrix according to columns to obtain a plurality of second word vector matrixes;
and selecting the maximum value in each second word vector matrix for combination to obtain the characteristic word vector.
Optionally, the word segmentation and label stitching are performed on the classified text to obtain a text sequence to be classified, and the text sequence to be classified is classified by using the trained text classification model to obtain a classification result, which includes:
Performing word segmentation processing on the text to be classified to obtain a word segmentation word set;
combining the word segmentation word sets according to the sequence of each word in the text to be classified to obtain a text sequence to be classified;
splicing the text sequence to be classified with the tag sequence by using the preset characters to obtain the text sequence to be classified;
and classifying the text sequence to be classified by using the trained text classification model to obtain the classification result.
In order to solve the above problems, the present invention also provides a text classification apparatus, including:
the data processing module is used for marking each text in the text set by category labels to obtain a target label set of the text set; performing text splicing processing on the text set and the target tag set to obtain a sample sequence set;
the model training module is used for carrying out iterative training based on neural feature fusion extraction on the pre-constructed text classification model by utilizing the sample sequence set until the text classification model converges to obtain a trained text classification model;
and the text classification module is used for performing word segmentation and label splicing on the classified text when receiving the text to be classified to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
a memory storing at least one computer program; and
And a processor executing the computer program stored in the memory to implement the text classification method.
In order to solve the above-described problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-described text classification method.
The embodiment of the invention carries out category label marking on each text in a text set to obtain a target label set of the text set; performing text splicing processing on the text set and the target tag set to obtain a sample sequence set; performing iterative training based on neural feature fusion extraction on a pre-constructed text classification model by using the sample sequence set until the text classification model converges to obtain a trained text classification model; when receiving a text to be classified, word segmentation and label splicing are carried out on the text to be classified to obtain a text sequence to be classified, the text sequence to be classified is classified by utilizing the text classification model which is completed through training to obtain a classification result, and the feature extraction layer contained in the text classification model can carry out neural feature fusion extraction on the text to be classified, so that feature extraction is more comprehensive, and therefore, the text classification model which is completed through training is stronger in feature extraction-based capability and higher in text classification accuracy. Therefore, the text classification method, the device, the electronic equipment and the computer readable storage medium provided by the embodiment of the invention improve the accuracy of text classification.
Drawings
FIG. 1 is a flow chart of a text classification method according to an embodiment of the present application;
fig. 2 is a schematic block diagram of a text classification device according to an embodiment of the application;
fig. 3 is a schematic diagram of an internal structure of an electronic device for implementing a text classification method according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
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 application.
The embodiment of the application provides a text classification method. The execution subject of the text classification method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the text classification method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Referring to fig. 1, a flowchart of a text classification method according to an embodiment of the present application is shown, where in the embodiment of the present application, the text classification method includes:
S1, carrying out intention recognition on each text in a text set, and carrying out category label marking on each text in the text set according to a result of the intention recognition to obtain a target label set of the text set;
in the embodiment of the invention, the text set consists of a plurality of user dialogue texts of a certain scene, alternatively, the text set can be obtained from a customer service database of a certain company,
in another embodiment of the present invention, the text set may also be stored in a blockchain node, and the high throughput of the blockchain to the data is utilized to improve the access efficiency of the text set.
Further, for better training of the subsequent model, in the embodiment of the present invention, each text in the text set is labeled with a category label, where the category label is a text intention, such as: the text set is a text set of a travel scene, the text A contained in the text set is "hotel has a room of tomorrow", the text corresponding to the text A is intended to be hotel ordering, and then the text A is marked as a hotel ordering category label.
Optionally, the embodiment of the invention uses a pre-constructed intention recognition model to perform intention recognition on each text in the text set to obtain an intention recognition result; and marking the corresponding text by category labels according to the intention recognition result, such as: the text set is a text set of a travel scene, the text A contained in the text set is "hotel has a room in the open world", the text corresponding to the text A is identified as hotel ordering, and then the text A is marked as a hotel ordering type label.
Further, since different texts may correspond to the same label, in order to avoid counting repeated labels, in the embodiment of the present invention, an initial label set is obtained by summarizing each text in the labeled text set and the corresponding category label, and since different texts may correspond to the same label, repeated labels exist in the initial label set, and therefore, the initial label set needs to be de-duplicated to obtain the target label set. Such as: the text set comprises a text A, a text B and a text C, the text A is marked with a class A label, the text B is marked with a class B label, and the text C is marked with a class A label, then the initial label set comprises two class A labels and one class B label, the initial label set is de-duplicated, one repeated class A label is removed, a target label set is obtained, and the target label set comprises one class A label and one class B label.
S2, performing word segmentation on each text in the text set, and performing sequence combination according to the word segmentation result to obtain a text sequence of each text;
in the embodiment of the invention, in order to construct a model training sample, each text in the text set is subjected to word segmentation, and sequence combination is performed according to the word segmentation result to obtain a text sequence of each text.
In detail, in the embodiment of the invention, word segmentation is carried out on each text in the text set to obtain a text word set of each text; combining the sequence of each word in the text word set in the corresponding text to obtain a corresponding text sequence, for example: the text A is a Chinese character, the text word set corresponding to the text A comprises three words including I, chinese and YES, and the I, the Chinese and the YES are combined according to the sequence of each word in the text A to obtain a text sequence I, the Chinese; optionally, in the embodiment of the present invention, each text in the text set is segmented by using a preset word segmentation dictionary, so as to obtain an initial text word set; and further, deleting the stop words by using the word segmentation word set to obtain the text word set. Wherein, the stop word is nonsensical word, including: the mood aid words, adverbs, prepositions, conjunctions, etc., such as "at".
S3, performing text splicing processing on all labels in the target label set and the text sequence to obtain a sample sequence set;
specifically, in the embodiment of the present invention, all tags in the target tag set are randomly combined to obtain a tag sequence, and further, in order to distinguish text from a tag, in the embodiment of the present invention, each text sequence is spliced with the tag sequence by using a preset character to obtain a sample sequence, for example: the text sequence is [ A ], the label sequence is [ B ], and the text sequence and the label sequence are spliced by using a special character SEP, so that the text sequence and the label sequence are expressed as sample sequences [ A, SEP, B ]; and summarizing all sample sequences to obtain the sample sequence set.
S4, training a pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model;
in order to better classify the text to be classified later in the embodiment of the invention, the model training based on the fusion and extraction of the neural characteristics is carried out on the pre-constructed text classification model by utilizing the sample sequence set, so as to obtain the text classification model after training.
Specifically, the text classification model has the capability of fusion and extraction of neural features, the feature extraction dimension is comprehensive, and the text classification of the trained text classification model is more accurate.
Optionally, in an embodiment of the present invention, the text classification model includes: coding layer, feature extraction layer, attention mechanism layer. The text classification model comprises the feature extraction layer, the neural feature fusion extraction can be carried out on the text to be classified, the feature extraction is more comprehensive, and the text classification accuracy of the model is higher.
Optionally, the coding layer is an coding layer.
In detail, in the embodiment of the present invention, iterative training based on neural feature fusion extraction is performed on a pre-constructed text classification model by using the sample sequence set until the text classification model converges, so as to obtain a trained text classification model, including:
Step A: converting words in each sample sequence into vectors by utilizing a coding layer of the text classification model, and combining all the vectors obtained by conversion according to the sequence of the corresponding words in the sample sequence to obtain a sample matrix;
and (B) step (B): performing neural feature fusion extraction on the sample matrix by utilizing a feature extraction layer of the text classification model to obtain a fusion feature matrix;
step C: performing weight calculation on the fusion feature matrix by using an attention mechanism layer of the text classification model to obtain a target matrix;
step D: calculating a classification prediction probability value corresponding to the target matrix by using a preset activation function;
optionally, the activation function is a relu function;
step E: determining a sample classification true value according to the category label of the text corresponding to the sample matrix, and calculating a loss value between the classification prediction probability value and the sample classification true value by using a preset loss function;
such as: the target label set comprises a class A label and a class B label, the class label of the text corresponding to the sample matrix is the class A, and then the corresponding true value is that the class A is 1 and the class B is 0.
Optionally, in an embodiment of the present invention, the loss function is a cross entropy loss function.
Step F: and (C) updating the model parameters of the text classification model when the loss value is greater than or equal to a preset loss threshold value, returning to the step (A) for iterative training until the loss value is less than the preset loss threshold value, and stopping training to obtain the trained text classification model.
In detail, in the embodiment of the present invention, the feature extraction layer is used to perform feature fusion extraction on the sample matrix to obtain a fusion feature matrix, including: traversing and selecting the columns of the sample matrix to obtain a target column, performing neural feature fusion extraction on the target column to obtain feature word vectors, and performing transverse combination on all the feature word vectors according to the sequence of the corresponding target column in the sample matrix to obtain a fusion feature matrix, for example: the sample matrix has three columns, the feature word vector corresponding to each column in the sample matrix is B, A, C, B corresponds to the first column in the sample matrix, A corresponds to the second column in the sample matrix, C corresponds to the third column in the sample matrix, then B is taken as the first column, A is taken as the second column, and C is taken as the third column, and transverse combination is carried out, so that a fusion feature matrix [ B A C ] is obtained.
Further, in the embodiment of the present invention, the neural feature fusion extraction is performed on the target column to obtain a feature word vector, including: selecting the target column and each column of the sample matrix to perform tensor multiplication calculation to obtain a corresponding first word vector matrix, stacking all the first word vector matrices according to the sequence of the columns in the corresponding sample matrix to obtain a three-dimensional word vector matrix, longitudinally segmenting the three-dimensional word vector matrix according to the columns to obtain a plurality of second word vector matrices, and selecting the maximum value in each second word vector matrix to combine to obtain a characteristic word vector. For example: the target column is a 1*n column vector, the sample matrix includes m columns, tensor multiplication is performed on the target column and each column of the sample matrix, so as to obtain a corresponding n×n first word vector matrix, for example: vector quantityVector->Tensor multiplication is performed to obtain a matrixObtaining m n first word vector matrixes, stacking the m n first word vector matrixes according to the sequence of columns in the corresponding sample matrixes to obtain n three-dimensional word vector matrixes, and stacking the first word vector matrixes on a first layer if the first word vector matrixes are the result of multiplication calculation of the target columns and the first column tensors in the sample matrixes; longitudinally segmenting the n-m three-dimensional word vector matrix according to columns to obtain n-n second word vector matrices, namely selecting the same column of each layer of the n-n three-dimensional word vector matrix, such as a first column, a second column, a third column and the like of each layer, and forming n-m second word vector matrixes, obtaining n-m second word vector matrixes, selecting the maximum value in each n-m second word vector matrix, and longitudinally combining the maximum value in each n-m second word vector matrix according to the sequence of the columns of the corresponding three-dimensional word vector matrix to obtain n-1 feature word vectors.
By utilizing the feature extraction layer to conduct nerve feature fusion extraction on the sample matrix, the accuracy of feature extraction is improved, and therefore the accuracy of classification of the text classification model after training is improved.
S5, when receiving the text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
In detail, in the embodiment of the present invention, the text to be classified refers to a text that needs to be classified, so that the classification is more accurate.
Further, in the embodiment of the present invention, in order to better classify the text to be classified by using the text classification model, the text to be classified needs to be preprocessed.
In detail, in the embodiment of the present invention, preprocessing the text to be classified includes: word segmentation is carried out on the text to be classified, all words obtained after word segmentation of the text to be classified are combined according to the sequence of each word in the text to be classified, and a text sequence to be classified is obtained, for example: the text to be classified is I'm is Chinese, three words of I'm, chinese and Y are obtained after word segmentation, combining I, chinese and Yes according to the sequence of each word in the text to be classified to obtain a text sequence to be classified [ I, yes, chinese ]; splicing the text sequence to be classified with the tag sequence by using the preset characters to obtain the text sequence to be classified; the technical means used for word segmentation and splicing are consistent with the foregoing, and are not described in detail herein.
Further, the embodiment of the invention classifies the text sequence to be classified by using the trained text classification model to obtain the classification result.
As shown in fig. 2, a functional block diagram of the text classification apparatus according to the present invention.
The text classification apparatus 100 of the present invention may be installed in an electronic device. Depending on the functions implemented, the text classification means may comprise a data processing module 101, a model training module 102, a text classification module 103, which may also be referred to as a unit, refers to a series of computer program segments capable of being executed by the processor of the electronic device and of performing fixed functions, which are stored in the memory of the electronic device.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the data processing module 101 is configured to perform category label labeling on each text in a text set, so as to obtain a target label set of the text set; performing text splicing processing on the text set and the target tag set to obtain a sample sequence set;
in the embodiment of the invention, the text set consists of a plurality of user dialogue texts of a certain scene, and optionally, the text set can be obtained from a customer service database of a certain company.
In another embodiment of the present invention, the text set may also be stored in a blockchain node, and the high throughput of the blockchain to the data is utilized to improve the access efficiency of the text set.
Further, for better training of the subsequent model, in the embodiment of the present invention, the data processing module 101 marks each text in the text set with a category label, where the category label is a text intention, such as: the text set is a text set of a travel scene, the text A contained in the text set is "hotel has a room of tomorrow", the text corresponding to the text A is intended to be hotel ordering, and then the text A is marked as a hotel ordering category label.
Further, since different texts may correspond to the same label, in order to avoid statistics of repeated labels, in the embodiment of the present invention, the data processing module 101 gathers each text in the text set and the corresponding category label after marking to obtain an initial label set, and since different texts may correspond to the same label, repeated labels exist in the initial label set, and therefore, the data processing module 101 needs to perform de-duplication on the initial label set to obtain the target label set. Such as: the text set comprises a text A, a text B and a text C, the text A is marked with a class A label, the text B is marked with a class B label, and the text C is marked with a class A label, then the initial label set comprises two class A labels and one class B label, the initial label set is de-duplicated, one repeated class A label is removed, a target label set is obtained, and the target label set comprises one class A label and one class B label.
In the embodiment of the present invention, in order to construct a model training sample, the data processing module 101 performs word segmentation processing on each text in the text set, and performs sequence combination according to the result of the word segmentation processing, so as to obtain a text sequence of each text.
In detail, in the embodiment of the present invention, the data processing module 101 performs word segmentation processing on each text in the text set to obtain a text word set of each text; combining the sequence of each word in the text word set in the corresponding text to obtain a corresponding text sequence, for example: the text A is a Chinese character, the text word set corresponding to the text A comprises three words including I, chinese and YES, and the I, the Chinese and the YES are combined according to the sequence of each word in the text A to obtain a text sequence I, the Chinese; optionally, in the embodiment of the present invention, each text in the text set is segmented by using a preset word segmentation dictionary, so as to obtain an initial text word set; and further, deleting the stop words by using the word segmentation word set to obtain the text word set. Wherein, the stop word is nonsensical word, including: the mood aid words, adverbs, prepositions, conjunctions, etc., such as "at".
Specifically, the data processing module 101 in the embodiment of the present invention performs random combination on all the tags in the target tag set to obtain a tag sequence, and further, in order to distinguish text from a tag, in the embodiment of the present invention, each text sequence and the tag sequence are spliced by using preset characters respectively, so as to obtain a sample sequence, for example: the text sequence is [ A ], the label sequence is [ B ], and the text sequence and the label sequence are spliced by using a special character SEP, so that the text sequence and the label sequence are expressed as sample sequences [ A, SEP, B ]; and summarizing all sample sequences to obtain the sample sequence set.
The model training module 102 is configured to perform iterative training based on neural feature fusion extraction on a pre-constructed text classification model by using the sample sequence set until the text classification model converges, so as to obtain a trained text classification model;
in order to better classify the text to be classified later in the embodiment of the invention, the pre-constructed text classification model is subjected to iterative training based on neural feature fusion extraction by using the sample sequence set until the text classification model converges, so as to obtain the trained text classification model.
Specifically, the text classification model has the capability of fusion and extraction of neural features, the feature extraction dimension is comprehensive, and the text classification of the trained text classification model is more accurate.
Optionally, in an embodiment of the present invention, the text classification model includes: coding layer, feature extraction layer, attention mechanism layer. The text classification model comprises the feature extraction layer, the neural feature fusion extraction can be carried out on the text to be classified, the feature extraction is more comprehensive, and the classification accuracy of the model is higher.
Optionally, the coding layer is an coding layer.
In detail, in the embodiment of the present invention, the model training module 102 obtains the trained text classification model by using the following means, including:
step A: converting words in each sample sequence into vectors by utilizing a coding layer of the text classification model, and combining all the vectors obtained by conversion according to the sequence of the corresponding words in the sample sequence to obtain a sample matrix;
and (B) step (B): performing neural feature fusion extraction on the sample matrix by utilizing a feature extraction layer of the text classification model to obtain a fusion feature matrix;
step C: performing weight calculation on the fusion feature matrix by using an attention mechanism layer of the text classification model to obtain a target matrix;
Step D: calculating a classification prediction probability value corresponding to the target matrix by using a preset activation function;
optionally, the activation function is a relu function;
step E: determining a sample classification true value according to the category label of the text corresponding to the sample matrix, and calculating a loss value between the classification prediction probability value and the sample classification true value by using a preset loss function;
such as: the target label set comprises a class A label and a class B label, the class label of the text corresponding to the sample matrix is the class A, and then the corresponding true value is that the class A is 1 and the class B is 0.
Optionally, in an embodiment of the present invention, the loss function is a cross entropy loss function.
Step F: and (C) updating the model parameters of the text classification model when the loss value is greater than or equal to a preset loss threshold value, returning to the step (A) for iterative training until the loss value is less than the preset loss threshold value, and stopping training to obtain the trained text classification model.
In detail, in the embodiment of the present invention, the feature extraction layer is used to perform feature fusion extraction on the sample matrix to obtain a fusion feature matrix, including: traversing and selecting the columns of the sample matrix to obtain a target column, performing neural feature fusion extraction on the target column to obtain feature word vectors, and performing transverse combination on all the feature word vectors according to the sequence of the corresponding target column in the sample matrix to obtain a fusion feature matrix, for example: the sample matrix has three columns, the feature word vector corresponding to each column in the sample matrix is B, A, C, B corresponds to the first column in the sample matrix, A corresponds to the second column in the sample matrix, C corresponds to the third column in the sample matrix, then B is taken as the first column, A is taken as the second column, and C is taken as the third column, and transverse combination is carried out, so that a fusion feature matrix [ B A C ] is obtained.
Further, in the embodiment of the present invention, the model training module 102 performs neural feature fusion extraction on the target column to obtain a feature word vector, including: selecting the target column and each column of the sample matrix to perform tensor multiplication calculation to obtain a corresponding first word vector matrix, stacking all the first word vector matrices according to the sequence of the columns in the corresponding sample matrix to obtain a three-dimensional word vector matrix, longitudinally segmenting the three-dimensional word vector matrix according to the columns to obtain a plurality of second word vector matrices, and selecting the maximum value in each second word vector matrix to combine to obtain a characteristic word vector. For example: the target column is a 1*n column vector, the sample matrix includes m columns, tensor multiplication is performed on the target column and each column of the sample matrix, so as to obtain a corresponding n×n first word vector matrix, for example: vector quantityVector->Tensor multiplication is performed to obtain a matrix->Obtaining m n first word vector matrixes, stacking the m n first word vector matrixes according to the sequence of columns in the corresponding sample matrixes to obtain n three-dimensional word vector matrixes, and stacking the first word vector matrixes on a first layer if the first word vector matrixes are the result of multiplication calculation of the target columns and the first column tensors in the sample matrixes; longitudinally segmenting the n-m three-dimensional word vector matrix according to columns to obtain n-n second word vector matrices, namely selecting the same column of each layer of the n-n three-dimensional word vector matrix, such as a first column, a second column, a third column and the like of each layer, and forming n-m second word vector matrixes, obtaining n-m second word vector matrixes, selecting the maximum value in each n-m second word vector matrix, and longitudinally combining the maximum value in each n-m second word vector matrix according to the sequence of the columns of the corresponding three-dimensional word vector matrix to obtain n-1 feature word vectors.
By utilizing the feature extraction layer to conduct nerve feature fusion extraction on the sample matrix, the accuracy of feature extraction is improved, and therefore the accuracy of classification of the text classification model after training is improved.
The text classification module 103 is configured to, when receiving a text to be classified, perform word segmentation and label stitching on the classified text to obtain a text sequence to be classified, and classify the text sequence to be classified by using the trained text classification model to obtain a classification result.
In detail, in the embodiment of the present invention, the text to be classified refers to a text that needs to be classified, so that the classification is more accurate.
Further, in the embodiment of the present invention, in order to better classify the text to be classified by using the text classification model, the text to be classified needs to be preprocessed.
In detail, in the embodiment of the present invention, the text classification module 103 performs preprocessing on the text to be classified, including: word segmentation is carried out on the text to be classified, all words obtained after word segmentation of the text to be classified are combined according to the sequence of each word in the text to be classified, and a text sequence to be classified is obtained, for example: the text to be classified is I'm is Chinese, three words of I'm, chinese and Y are obtained after word segmentation, combining I, chinese and Yes according to the sequence of each word in the text to be classified to obtain a text sequence to be classified [ I, yes, chinese ]; splicing the text sequence to be classified with the tag sequence by using the preset characters to obtain the text sequence to be classified; the technical means used for word segmentation and splicing are consistent with the foregoing, and are not described in detail herein.
Further, the embodiment of the invention classifies the text sequence to be classified by using the trained text classification model to obtain the classification result.
Fig. 3 is a schematic structural diagram of an electronic device for implementing the text classification method according to the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a text classification program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile 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. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of text classification programs, etc., but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective components of the entire electronic device using various interfaces and lines, and executes various functions of the electronic device 1 and processes data by running or executing programs or modules (e.g., text classification programs, etc.) stored in the memory 11, and calling data stored in the memory 11.
The bus may be a peripheral component interconnect standard (perIPheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or 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 text classification program 12 stored in the memory 11 in the electronic device 1 is a combination of a plurality of computer programs, which, when run in the processor 10, can realize:
performing intention recognition on each text in a text set, and performing category label marking on each text in the text set according to a result of the intention recognition to obtain a target label set of the text set;
performing word segmentation processing on each text in the text set, and performing sequence combination according to the word segmentation processing result to obtain a text sequence of each text;
Performing text splicing processing on all the labels in the target label set and the text sequence to obtain a sample sequence set;
training a pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model;
when receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
In particular, the specific implementation method of the processor 10 on the computer program may refer to the description of the relevant 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 medium may be non-volatile or volatile. The computer readable 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).
Embodiments of the present invention may also provide a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, may implement:
performing intention recognition on each text in a text set, and performing category label marking on each text in the text set according to a result of the intention recognition to obtain a target label set of the text set;
performing word segmentation processing on each text in the text set, and performing sequence combination according to the word segmentation processing result to obtain a text sequence of each text;
performing text splicing processing on all the labels in the target label set and the text sequence to obtain a sample sequence set;
training a pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model;
when receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
Further, the computer-usable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.
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 (7)
1. A method of text classification, the method comprising:
performing intention recognition on each text in a text set, and performing category label marking on each text in the text set according to a result of the intention recognition to obtain a target label set of the text set;
performing word segmentation processing on each text in the text set, and performing sequence combination according to the word segmentation processing result to obtain a text sequence of each text;
performing text splicing processing on all the labels in the target label set and the text sequence to obtain a sample sequence set;
Training a pre-constructed text classification model based on neural feature fusion extraction by using the sample sequence set to obtain a trained text classification model;
when receiving a text to be classified, performing word segmentation and label splicing on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result;
the training of the model based on the fusion and extraction of the neural characteristics is carried out on the pre-constructed text classification model by using the sample sequence set to obtain a trained text classification model, and the training method comprises the following steps: step A: converting words in each sample sequence into vectors by utilizing a coding layer of the text classification model, and combining all the vectors obtained by conversion according to the sequence of the corresponding words in the sample sequence to obtain a sample matrix; and (B) step (B): performing neural feature fusion extraction on the sample matrix by utilizing a feature extraction layer of the text classification model to obtain a fusion feature matrix; step C: performing weight calculation on the fusion feature matrix by using an attention mechanism layer of the text classification model to obtain a target matrix; step D: calculating a classification prediction probability value corresponding to the target matrix by using a preset activation function; step E: determining a sample classification true value according to the category label of the text corresponding to the sample matrix, and calculating a loss value between the classification prediction probability value and the sample classification true value by using a preset loss function; step F: and (C) updating model parameters of the text classification model when the loss value is greater than or equal to a preset loss threshold value, and returning to the step (A) for iterative training until the loss value is less than the preset loss threshold value, stopping training, and obtaining the trained text classification model;
The feature extraction layer for the text classification model performs neural feature fusion extraction on the sample matrix to obtain a fusion feature matrix, and the method comprises the following steps: obtaining a target column by traversing and selecting the columns of the sample matrix; performing neural feature fusion extraction on the target column to obtain a feature word vector; transversely combining all the feature word vectors according to the sequence of the corresponding target columns in the sample matrix to obtain the feature matrix;
the step of performing the neural feature fusion extraction on the target column to obtain a feature word vector comprises the following steps: performing tensor multiplication calculation on the target column and each column of the sample matrix to obtain a first word vector matrix; stacking all the first word vector matrixes according to the sequence of the corresponding columns in the sample matrix to obtain a three-dimensional word vector matrix; longitudinally segmenting the three-dimensional word vector matrix according to columns to obtain a plurality of second word vector matrixes; and selecting the maximum value in each second word vector matrix for combination to obtain the characteristic word vector.
2. The text classification method of claim 1, wherein performing text stitching on all tags in the target tag set and the text sequence to obtain a sample sequence set includes:
Randomly combining all the tags in the target tag set to obtain a tag sequence;
splicing each text sequence with the tag sequence by using preset characters to obtain a sample sequence;
and summarizing all sample sequences to obtain the sample sequence set.
3. The text classification method of claim 2, wherein said performing word segmentation on each text in the text set and performing sequence combination according to the result of the word segmentation to obtain a text sequence of each text comprises:
performing word segmentation on each text in the text set by using a preset word segmentation dictionary to obtain a corresponding initial text word set;
deleting the stop words by using the initial text word set to obtain the text word set;
and combining each word in the text word set according to the sequence in the corresponding text to obtain a text sequence of each text.
4. A method for classifying text according to any one of claims 1 to 3, wherein the performing word segmentation and label stitching on the classified text to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result includes:
Performing word segmentation processing on the text to be classified to obtain a word segmentation word set;
combining the word segmentation word sets according to the sequence of each word in the text to be classified to obtain a middle text sequence to be classified;
splicing the intermediate text sequence to be classified with the label by using preset characters to obtain a text sequence to be classified;
and classifying the text sequence to be classified by using the trained text classification model to obtain the classification result.
5. A text classification apparatus for implementing the text classification method according to any one of claims 1 to 4, comprising:
the data processing module is used for carrying out intention recognition on each text in the text set, and carrying out category label marking on each text in the text set according to the result of the intention recognition to obtain a target label set of the text set; performing word segmentation processing on each text in the text set, and performing sequence combination according to the word segmentation processing result to obtain a text sequence of each text; performing text splicing processing on all the labels in the target label set and the text sequence to obtain a sample sequence set;
The model training module is used for carrying out model training based on neural feature fusion extraction on the pre-constructed text classification model by utilizing the sample sequence set to obtain a trained text classification model;
and the text classification module is used for performing word segmentation and label splicing on the classified text when receiving the text to be classified to obtain a text sequence to be classified, and classifying the text sequence to be classified by using the trained text classification model to obtain a classification result.
6. 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 a computer program executable by the at least one processor to enable the at least one processor to perform the text classification method of any of claims 1 to 4.
7. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the text classification method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581189.8A CN113157927B (en) | 2021-05-27 | 2021-05-27 | Text classification method, apparatus, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581189.8A CN113157927B (en) | 2021-05-27 | 2021-05-27 | Text classification method, apparatus, electronic device and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113157927A CN113157927A (en) | 2021-07-23 |
| CN113157927B true CN113157927B (en) | 2023-10-31 |
Family
ID=76877849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110581189.8A Active CN113157927B (en) | 2021-05-27 | 2021-05-27 | Text classification method, apparatus, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113157927B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114330357B (en) * | 2021-08-04 | 2024-05-10 | 腾讯科技（深圳）有限公司 | Text processing method, device, computer equipment and storage medium |
| CN113688239B (en) * | 2021-08-20 | 2024-04-16 | 平安国际智慧城市科技股份有限公司 | Text classification method and device under small sample, electronic equipment and storage medium |
| CN113806540B (en) * | 2021-09-18 | 2023-08-08 | 平安银行股份有限公司 | Text labeling method, text labeling device, electronic equipment and storage medium |
| CN113919344B (en) * | 2021-09-26 | 2022-09-23 | 腾讯科技（深圳）有限公司 | Text processing method and device |
| CN113836303A (en) * | 2021-09-26 | 2021-12-24 | 平安科技（深圳）有限公司 | Text type identification method and device, computer equipment and medium |
| CN115098688B (en) * | 2022-07-20 | 2024-05-31 | 平安科技（深圳）有限公司 | Multi-label classification model training method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543032A (en) * | 2018-10-26 | 2019-03-29 | 平安科技（深圳）有限公司 | File classification method, device, computer equipment and storage medium |
| CN111061881A (en) * | 2019-12-27 | 2020-04-24 | 浪潮通用软件有限公司 | Text classification method, equipment and storage medium |
| CN112015863A (en) * | 2020-08-26 | 2020-12-01 | 华东师范大学 | Multi-feature fusion Chinese text classification method based on graph neural network |
| CN112597312A (en) * | 2020-12-28 | 2021-04-02 | 深圳壹账通智能科技有限公司 | Text classification method and device, electronic equipment and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021000362A1 (en) * | 2019-07-04 | 2021-01-07 | 浙江大学 | Deep neural network model-based address information feature extraction method |
-
2021
- 2021-05-27 CN CN202110581189.8A patent/CN113157927B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543032A (en) * | 2018-10-26 | 2019-03-29 | 平安科技（深圳）有限公司 | File classification method, device, computer equipment and storage medium |
| CN111061881A (en) * | 2019-12-27 | 2020-04-24 | 浪潮通用软件有限公司 | Text classification method, equipment and storage medium |
| CN112015863A (en) * | 2020-08-26 | 2020-12-01 | 华东师范大学 | Multi-feature fusion Chinese text classification method based on graph neural network |
| CN112597312A (en) * | 2020-12-28 | 2021-04-02 | 深圳壹账通智能科技有限公司 | Text classification method and device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113157927A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113157927B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN112528616B (en) | Service form generation method and device, electronic equipment and computer storage medium | |
| CN113658002B (en) | Transaction result generation method and device based on decision tree, electronic equipment and medium | |
| CN113435308B (en) | Text multi-label classification method, device, equipment and storage medium | |
| CN113360654B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN113505273B (en) | Data sorting method, device, equipment and medium based on repeated data screening | |
| CN113656690B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113344125B (en) | Long text matching recognition method and device, electronic equipment and storage medium | |
| CN113591881B (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN115409041B (en) | Unstructured data extraction method, device, equipment and storage medium | |
| CN113626605B (en) | Information classification method, device, electronic equipment and readable storage medium | |
| CN116578696A (en) | Text abstract generation method, device, equipment and storage medium | |
| CN116450829A (en) | Medical text classification method, device, equipment and medium | |
| CN114548114B (en) | Text emotion recognition method, device, equipment and storage medium | |
| CN112434157B (en) | Method and device for classifying documents in multiple labels, electronic equipment and storage medium | |
| CN114677526A (en) | Image classification method, device, equipment and medium | |
| CN114708073A (en) | Intelligent detection method and device for surrounding mark and serial mark, electronic equipment and storage medium | |
| CN113723114A (en) | Semantic analysis method, device and equipment based on multi-intent recognition and storage medium | |
| CN113822215A (en) | Equipment operation guide file generation method and device, electronic equipment and storage medium | |
| CN113706207A (en) | Order transaction rate analysis method, device, equipment and medium based on semantic analysis | |
| CN112380343B (en) | Problem analysis method, device, electronic equipment and storage medium | |
| CN113704478B (en) | Text element extraction method, device, electronic equipment and medium | |
| CN115146627B (en) | Entity identification method, entity identification device, electronic equipment and storage medium | |
| CN113672722B (en) | Online course intelligent recommendation method and device, electronic equipment and storage medium | |
| CN113656703B (en) | Intelligent recommendation method, device, equipment and storage medium based on new online courses |
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 |