CN111563152A - Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium - Google Patents
Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111563152A CN111563152A CN202010564937.7A CN202010564937A CN111563152A CN 111563152 A CN111563152 A CN 111563152A CN 202010564937 A CN202010564937 A CN 202010564937A CN 111563152 A CN111563152 A CN 111563152A
- Authority
- CN
- China
- Prior art keywords
- corpus
- enhanced
- training
- prediction model
- answer
- 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.)
- Pending
Links
Images
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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/355—Class or cluster creation or modification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an artificial intelligence technology, and discloses an intelligent question-answer corpus analysis method, which comprises the following steps: inputting the historical question-answer corpus into a pre-constructed data enhancement model to obtain an enhancement corpus; training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model; analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset; training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model; and analyzing the corpus text of the user to be analyzed by utilizing the analysis prediction model to obtain a final analysis result. The invention also relates to a block chain technology, and data used for model training can be stored in the block chain. The invention also provides an intelligent question-answering corpus analyzing device, electronic equipment and a computer storage medium. The invention can improve the accuracy of intelligent question-answering corpus analysis.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a method and a device for analyzing intelligent question-answering corpus, electronic equipment and a readable storage medium.
Background
Along with the development of artificial intelligence, the intelligence of the machine is higher and higher, the analysis of the human behavior through human language is no longer a patent of human, and the machine can analyze and judge the human behavior through linguistic data, so that the labor cost is reduced.
At present, because the computational power limitation machine cannot analyze through any language material, only can analyze and judge through analyzing the question-answer language material of the user, the question-answer language material refers to the language material that the user answers to the preset questions, and the intelligent analysis of the question-answer language material is applied to multiple aspects of life, such as: the mobile phone manufacturer mobile phone evaluates the system version of the mobile phone by analyzing the question and answer corpus of the user, the doctor preliminarily screens mental diseases by analyzing the question and answer corpus of the patient, and the human resources analyze interviews by analyzing the question and answer corpus of the interviewee.
However, the query and answer corpus data of the user is less and difficult to obtain, so that the training data volume of the deep learning model of the existing intelligent query and answer corpus analysis system is smaller, and the accuracy of the model is not high.
Disclosure of Invention
The invention provides an intelligent question-answering corpus analysis method, an intelligent question-answering corpus analysis device, electronic equipment and a computer readable storage medium, and mainly aims to solve the problems of few training data samples and low model accuracy.
In order to achieve the above object, the present invention provides an intelligent question-answering corpus analyzing method, which comprises:
acquiring a historical question and answer corpus, and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhancement corpus;
training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model;
analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model;
and acquiring a corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
Optionally, the training of the pre-constructed convolutional neural network model by using the historical question-answer corpus to obtain an initial classification prediction model includes:
determining the historical question and answer corpus as a first training set;
carrying out preset analysis gear marking on the historical question and answer corpus to obtain a first label set;
and training the convolutional neural network model by using the first training set and the first label set to obtain the initial classification prediction model.
Optionally, the training the convolutional neural network model using the first training set and the first label set includes:
a: according to preset depth separable convolution pooling times, performing depth separable convolution pooling operation on the first training set to obtain a dimension reduction data set;
b: calculating the dimensionality reduction data set by using a preset activation function to obtain a predicted value, and calculating by using a pre-constructed loss function according to the predicted value and a label value contained in the first label set to obtain a loss value;
c: comparing the loss value with a preset loss threshold value, and if the loss value is greater than or equal to the loss threshold value, returning to the step A; and if the loss value is smaller than the loss threshold value, obtaining the initial classification prediction model.
Optionally, the analyzing and screening the enhanced corpus with the initial classification prediction model to obtain an enhanced corpus subset includes:
analyzing the enhanced corpus by using the initial classification prediction model to obtain a classification analysis result set of each piece of data in the enhanced corpus;
and deleting the data corresponding to the classification analysis result set with the classification analysis results smaller than a preset threshold from the enhanced corpus set to obtain the enhanced corpus subset.
Optionally, the obtaining the corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result includes:
analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a classification analysis result set;
sorting the classification analysis results in the classification analysis result set;
and selecting the classification analysis result with the maximum value as the final analysis result.
Optionally, the performing a deep separable convolution pooling operation on the first training set to obtain a reduced-dimension data set includes:
performing packet convolution operation on the first training set to obtain a deep convolution data set;
performing point-by-point convolution operation on the depth convolution data set to obtain a point-by-point convolution data set;
and carrying out average pooling operation on the point-by-point convolution data set to obtain the dimensionality reduction data set.
In order to solve the above problem, the present invention further provides an intelligent question-answering corpus analyzing device, including:
the corpus enhancement module is used for acquiring a historical question and answer corpus and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhanced corpus;
the enhanced corpus screening module is used for training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model; analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
the model training module is used for training the convolutional neural network model by utilizing the enhanced corpus subset and the historical question-answer corpus set to obtain an analysis prediction model;
and the model analysis module is used for acquiring the corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
Optionally, the enhanced corpus screening module obtains an initial classification prediction model by using the convolutional neural network model pre-constructed by training the historical question-answer corpus, and includes:
determining the historical question and answer corpus as a first training set;
carrying out preset analysis gear marking on the historical question and answer corpus to obtain a first label set;
and training the convolutional neural network model by using the first training set and the first label set to obtain the initial classification prediction model.
Optionally, the enhanced corpus screening module trains the convolutional neural network model using the first training set and the first label set, including:
a: according to preset depth separable convolution pooling times, performing depth separable convolution pooling operation on the first training set to obtain a dimension reduction data set;
b: calculating the dimensionality reduction data set by using a preset activation function to obtain a predicted value, and calculating by using a pre-constructed loss function according to the predicted value and a label value contained in the first label set to obtain a loss value;
c: comparing the loss value with a preset loss threshold value, and if the loss value is greater than or equal to the loss threshold value, returning to the step A; and if the loss value is smaller than the loss threshold value, obtaining the initial classification prediction model.
Optionally, the enhanced corpus screening module analyzes and screens the enhanced corpus set by using the initial classification prediction model to obtain an enhanced corpus subset, including:
analyzing the enhanced corpus by using the initial classification prediction model to obtain a classification analysis result set of each piece of data in the enhanced corpus;
and deleting the data corresponding to the classification analysis result set with the classification analysis results smaller than a preset threshold from the enhanced corpus set to obtain the enhanced corpus subset.
Optionally, the model analysis module obtains a corpus text of a user to be analyzed, and analyzes the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result, where the final analysis result includes:
analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a classification analysis result set;
sorting the classification analysis results in the classification analysis result set;
and selecting the classification analysis result with the maximum value as the final analysis result.
Optionally, the enhanced corpus filtering module performs a deep separable convolution pooling operation on the first training set to obtain a dimensionality reduction data set, including:
performing packet convolution operation on the first training set to obtain a deep convolution data set;
performing point-by-point convolution operation on the depth convolution data set to obtain a point-by-point convolution data set;
and carrying out average pooling operation on the point-by-point convolution data set to obtain the dimensionality reduction data set.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the intelligent question-answer corpus analysis method.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, which includes a storage data area and a storage program area, wherein the storage data area stores data created according to the use of the blockchain node, and the storage program area stores a computer program, and the computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the intelligent questioning and answering corpus analyzing method.
In the embodiment of the invention, the historical question and answer corpus is input into a pre-constructed data enhancement model to obtain an enhancement corpus, and the historical question and answer corpus is subjected to data expansion; training a pre-constructed convolutional neural network model by using the historical question-answer corpus to obtain an initial classification prediction model, analyzing and screening the enhanced corpus by using the initial classification prediction model, summarizing data with classification analysis results larger than a preset threshold in the enhanced corpus to obtain an enhanced corpus subset, and screening the enhanced corpus to improve the data authenticity of the enhanced corpus; training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model, so that the training precision of the model is improved; obtaining a user corpus text to be analyzed, and analyzing the user corpus text to be analyzed by using the analysis prediction model to obtain a final analysis result; by enhancing the data of the existing small sample training data, the sample capacity is improved, the enhanced data is further screened, the accuracy of model prediction is improved, and the problem of inaccurate model training caused by less training data samples is solved.
Drawings
Fig. 1 is a schematic flow chart of an intelligent question-answer corpus analysis method according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of an intelligent corpus analyzer according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an internal structure of an electronic device implementing the intelligent corpus questioning and answering analysis method according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides an intelligent question-answering corpus analysis method. Fig. 1 is a schematic flow chart of an intelligent question-answering corpus analysis method according to an embodiment of the present invention. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the intelligent question-answering corpus analyzing method includes:
s1, obtaining a historical question and answer corpus, and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhancement corpus;
in the embodiment of the present invention, the query and answer corpus in the historical query and answer corpus set is a set of answer texts for the recruiters to answer the preset recruitment questions, for example: the recruitment question may be "what are your job plans? "," what do you have a view of the company's foreground? ". The historical corpus of questions and answers may be obtained from a database of a human resources department of a company.
Furthermore, because the data of the historical question and answer corpus is less and not easy to obtain, the data of the historical question and answer corpus needs to be expanded, and the embodiment of the invention adopts a pre-constructed data enhancement model to expand the historical question and answer corpus.
Preferably, the data enhancement model may be constructed by using a currently known Seq2Seq algorithm and a variational self-coder, and the training of the data enhancement model is completed by using a question and answer corpus as a training set and using a labeled question and answer corpus as a label set, wherein the question and answer corpus is different from the historical question and answer corpus.
And further, inputting the historical question and answer corpus into the data enhancement model, outputting the enhancement corpus, and further completing data expansion of the historical question and answer corpus.
S2, training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model;
in the embodiment of the present invention, the historical corpus of questions and answers is determined as a first training set, and a preset analysis gear mark is performed on the historical corpus of questions and answers to obtain a first label set, wherein preferably, the analysis gear can be five types, i.e., excellent, good, medium, passing and failing.
Preferably, the convolutional neural network model in the preferred embodiment of the present invention can be constructed by using a deep separable convolutional network model.
Further, training the convolutional neural network model using the first training set and the first label set according to the embodiment of the present invention includes:
s21: according to preset depth separable convolution pooling times, performing depth separable convolution pooling operation on the first training set to obtain a dimension reduction data set;
s22: and calculating the dimensionality reduction data set by using a preset activation function to obtain a predicted value, and calculating by using a pre-constructed loss function to obtain a loss value according to the predicted value and the label value contained in the first label set.
S23: comparing the loss value with a preset loss threshold value, and if the loss value is greater than or equal to the loss threshold value, returning to the step S21; and if the loss value is smaller than the loss threshold value, obtaining the classification prediction model.
In detail, the depth separable convolution pooling operation includes: and performing grouping convolution operation on the first training set to obtain a depth convolution data set, performing point-by-point convolution operation on the depth convolution data set to obtain a point-by-point convolution data set, and performing average pooling operation on the point-by-point convolution data set to obtain the dimensionality reduction data set.
In a preferred embodiment of the present invention, the activation function can be calculated using the following formula:
f(x)＝max(0,x)
wherein f (x) is the predicted value and x is the data in the dimension reduction dataset.
In a preferred embodiment of the present invention, the loss function can be calculated using the following formula:
wherein N is the number of data contained in the training sample, i is a positive integer, and hiIs the tag value, miAnd the predicted value is used.
S3, analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
in the embodiment of the invention, the data of the enhanced corpus is generated through a model, and the enhanced corpus is screened in order to improve the data truth of the enhanced corpus and further improve the training precision of a subsequent model.
In detail, the initial classification prediction model is used for analyzing the enhanced corpus to obtain a classification analysis result set of each piece of data in the enhanced corpus. For example: the classification prediction model has five-grade classification prediction: excellent, good, medium, passing and failing, and when the classification prediction model predicts data, the result outputs a classification analysis result set and includes classification analysis results of various gears, such as excellent 0.6, good 0.4, medium 0.45, passing 0.6 and failing 0.5.
Further, in order to ensure the reliability of the prediction score, the data corresponding to the classification analysis result set in which the classification analysis results in the enhanced corpus are all smaller than a preset threshold is deleted to obtain an enhanced corpus subset, and preferably, the threshold may be set to 0.5, for example: the classification prediction model predicts the data A of the enhanced corpus to obtain a classification analysis result set which is as follows: excellent 0.3, good 0.4, medium 0.45, passing 0.2 and failing 0.2, and the classification analysis results of all the gears are less than 0.5, which indicates that the truth of the data A is low, and the data A is deleted.
S4, training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus to obtain an analysis prediction model;
in the embodiment of the present invention, in order to make the training data of the model more real and comprehensive, the enhanced corpus subset and the historical question and answer corpus set are used as a second training set, and a preset analysis gear mark is performed on the second training set to obtain a second label set, and preferably, the analysis gear can be five types, i.e., excellent, good, medium, passing and failing.
Preferably, the convolutional neural network model in the preferred embodiment of the present invention can be constructed by using a deep separable convolutional network model.
Further, in the embodiment of the present invention, the convolutional neural network model is trained by using the second training set and the second label set to obtain the analysis prediction model.
S5, obtaining a user corpus text to be analyzed, and analyzing the user corpus text to be analyzed by using the analysis prediction model to obtain a final analysis result;
in the embodiment of the present invention, the corpus text of the user to be analyzed is an answer text answered by the user according to a preset recruitment question, for example: the recruitment question may be "what are your job plans? "," what do you have a view of the company's foreground? ".
In another embodiment of the present invention, the data used to train the analytical prediction model may be stored in a blockchain.
Further, the analytic prediction model is used for analyzing the corpus text of the user to be analyzed to obtain a classification analysis result set, classification analysis results in the classification analysis result set are sorted, and the classification analysis result with the largest numerical value is selected as a final analysis result. For example: the analysis of each class in the analysis result set was excellent 0.3, good 0.4, medium 0.45, passing 0.2 and failing 0.2, with 0.45 analysis being the largest, so medium 0.45 was taken as the final analysis result.
In the embodiment of the invention, the historical question and answer corpus is input into a pre-constructed data enhancement model to obtain an enhancement corpus, and the historical question and answer corpus is subjected to data expansion; training a pre-constructed convolutional neural network model by using the historical question-answer corpus to obtain an initial classification prediction model, analyzing and screening the enhanced corpus by using the initial classification prediction model, summarizing data with classification analysis results larger than a preset threshold in the enhanced corpus to obtain an enhanced corpus subset, and screening the enhanced corpus to improve the data authenticity of the enhanced corpus; training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model, so that the training precision of the model is improved; obtaining a user corpus text to be analyzed, and analyzing the user corpus text to be analyzed by using the analysis prediction model to obtain a final analysis result; by enhancing the data of the existing small sample training data, the sample capacity is improved, the enhanced data is further screened, the accuracy of model prediction is improved, and the problem of inaccurate model training caused by less training data samples is solved.
FIG. 2 is a functional block diagram of the intelligent questioning and answering corpus analyzer according to the present invention.
The intelligent question-answer corpus analyzing device 100 of the present invention may be installed in an electronic device. According to the realized functions, the intelligent question-answering corpus analyzing device can comprise a corpus enhancing module 101, an enhanced corpus screening module 102, a model training module 103 and a model analyzing module 104. A module according to the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the corpus enhancement module 101 is configured to obtain a historical question-answer corpus, and input the historical question-answer corpus into a pre-constructed data enhancement model to obtain an enhanced corpus.
In the embodiment of the present invention, the query and answer corpus in the historical query and answer corpus set is a set of answer texts for the recruiters to answer the preset recruitment questions, for example: the recruitment question may be "what are your job plans? "," what do you have a view of the company's foreground? ". The historical corpus of questions and answers may be obtained from a database of a human resources department of a company.
Furthermore, because the data of the historical question and answer corpus is less and not easy to obtain, the data of the historical question and answer corpus needs to be expanded, and the embodiment of the invention adopts a pre-constructed data enhancement model to expand the historical question and answer corpus.
Preferably, the data enhancement model may be constructed by using a currently known Seq2Seq algorithm and a variational self-coder, and the corpus enhancement module 101 uses a query and answer corpus as a training set and uses a labeled query and answer corpus as a label set to complete training of the data enhancement model, wherein the query and answer corpus is different from the historical query and answer corpus.
Further, the corpus enhancement module 101 inputs the historical question and answer corpus into the pre-constructed data enhancement model, outputs the enhanced corpus, and then completes data expansion of the historical question and answer corpus.
The enhanced corpus screening module 102 is configured to train a pre-constructed convolutional neural network model by using the historical question-answer corpus to obtain an initial classification prediction model; and analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset.
In the embodiment of the present invention, the enhanced corpus screening module 102 determines the historical corpus of questions and answers as a first training set, and performs a preset analysis gear marking on the historical corpus of questions and answers to obtain a first label set, where preferably, the analysis gear may be five excellent, good, medium, passing and failing.
Preferably, the convolutional neural network model in the preferred embodiment of the present invention can be constructed by using a deep separable convolutional network model.
Further, the enhanced corpus screening module 102 in the embodiment of the present invention obtains the classification prediction model by using the following means:
a: according to preset depth separable convolution pooling times, performing depth separable convolution pooling operation on the first training set to obtain a dimension reduction data set;
b: and calculating the dimensionality reduction data set by using a preset activation function to obtain a predicted value, and calculating by using a pre-constructed loss function to obtain a loss value according to the predicted value and the label value contained in the first label set.
C: comparing the loss value with a preset loss threshold value, and if the loss value is greater than or equal to the loss threshold value, returning to the step A; and if the loss value is smaller than the loss threshold value, obtaining the classification prediction model.
In detail, the enhanced corpus filtering module 102 obtains the dimension reduction dataset by using the following means: and performing grouping convolution operation on the first training set to obtain a depth convolution data set, performing point-by-point convolution operation on the depth convolution data set to obtain a point-by-point convolution data set, and performing average pooling operation on the point-by-point convolution data set to obtain the dimensionality reduction data set.
In a preferred embodiment of the present invention, the activation function can be calculated using the following formula:
f(x)＝max(0,x)
wherein f (x) is the predicted value and x is the data in the dimension reduction dataset.
In a preferred embodiment of the present invention, the loss function can be calculated using the following formula:
wherein N is the number of data contained in the training sample, i is a positive integer, and hiIs the tag value, miAnd the predicted value is used.
In the embodiment of the invention, the data of the enhanced corpus is generated through a model, and the enhanced corpus is screened in order to improve the data truth of the enhanced corpus and further improve the training precision of a subsequent model.
In detail, the enhanced corpus screening module 102 analyzes the enhanced corpus using the initial classification prediction model to obtain a classification analysis result set of each piece of data in the enhanced corpus. For example: the classification prediction model has five-grade classification prediction: excellent, good, medium, passing and failing, and when the classification prediction model predicts data, the result outputs a classification analysis result set and includes classification analysis results of various gears, such as excellent 0.6, good 0.4, medium 0.45, passing 0.6 and failing 0.5.
Further, in order to ensure the reliability of the prediction score, the enhanced corpus filtering module 102 deletes the data corresponding to the classification analysis result sets, of which the classification analysis results in the enhanced corpus are all smaller than a preset threshold, to obtain an enhanced corpus subset, preferably, the threshold may be set to 0.5, for example: the classification prediction model predicts the data A of the enhanced corpus to obtain a classification analysis result set which is as follows: excellent 0.3, good 0.4, medium 0.45, passing 0.2 and failing 0.2, and the classification analysis results of all the gears are less than 0.5, which indicates that the truth of the data A is low, and the data A is deleted.
The model training module 103 is configured to train the convolutional neural network model by using the enhanced corpus subset and the historical question-answer corpus set to obtain an analysis prediction model.
In an embodiment of the present invention, in order to make training data of a model more real and comprehensive, the model training module 103 uses the enhanced corpus subset and the historical question and answer corpus set as a second training set, and performs a preset analysis gear marking on the second training set to obtain a second label set, where preferably, the analysis gear may be five of excellent, good, medium, passing and failing.
Preferably, the convolutional neural network model in the preferred embodiment of the present invention can be constructed by using a deep separable convolutional network model.
Further, in the embodiment of the present invention, the model training module 103 trains the convolutional neural network model by using the second training set and the second label set to obtain the analysis prediction model.
The model analysis module 104 obtains the corpus text of the user to be analyzed, and analyzes the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
In the embodiment of the present invention, the corpus text of the user to be analyzed is an answer text answered by the user according to a preset recruitment question, for example: the recruitment question may be "what are your job plans? "," what do you have a view of the company's foreground? ".
In another embodiment of the present invention, the data used to train the analytical prediction model training may be stored in a blockchain.
Further, the model analysis module 104 analyzes the corpus text of the user to be analyzed by using the analysis prediction model to obtain a classification analysis result set, sorts the classification analysis results in the classification analysis result set, and selects the classification analysis result with the largest value as a final analysis result. For example: the analysis of each class in the analysis result set was excellent 0.3, good 0.4, medium 0.45, passing 0.2 and failing 0.2, with 0.45 analysis being the largest, so medium 0.45 was taken as the final analysis result.
Fig. 3 is a schematic structural diagram of an electronic device implementing the intelligent question-answering corpus analyzing method according to the present invention.
The electronic device 1 may include a processor 10, a memory 11 and a bus, and may further include a computer program, such as a smart questionnaire analysis program, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, 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 also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and 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 to store not only application software installed in the electronic device 1 and various types of data, such as codes of the smart corpus analysis program, but also temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., an intelligent questionnaire analysis program, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 3 shows only an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The smart corpus 12 stored in the memory 11 of the electronic device 1 is a combination of instructions, which when executed in the processor 10, can implement:
acquiring a historical question and answer corpus, and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhancement corpus;
training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model;
analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model;
and acquiring a corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiment corresponding to fig. 1, which is not described herein again.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
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 according to the use of the blockchain node, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
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 attributes 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 block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. An intelligent question-answer corpus analysis method is characterized by comprising the following steps:
acquiring a historical question and answer corpus, and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhancement corpus;
training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model;
analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
training the convolutional neural network model by using the enhanced corpus subset and the historical question and answer corpus set to obtain an analysis prediction model;
and acquiring a corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
2. The method according to claim 1, wherein the training of the pre-constructed convolutional neural network model with the historical corpus of questions and answers to obtain an initial classification prediction model comprises:
determining the historical question and answer corpus as a first training set;
carrying out preset analysis gear marking on the historical question and answer corpus to obtain a first label set;
and training the convolutional neural network model by using the first training set and the first label set to obtain the initial classification prediction model.
3. The method of claim 2, wherein training the convolutional neural network model using the first training set and the first tag set comprises:
a: according to preset depth separable convolution pooling times, performing depth separable convolution pooling operation on the first training set to obtain a dimension reduction data set;
b: calculating the dimensionality reduction data set by using a preset activation function to obtain a predicted value, and calculating by using a pre-constructed loss function according to the predicted value and a label value contained in the first label set to obtain a loss value;
c: comparing the loss value with a preset loss threshold value, and if the loss value is greater than or equal to the loss threshold value, returning to the step A; and if the loss value is smaller than the loss threshold value, obtaining the initial classification prediction model.
4. The method according to claim 1, wherein the analyzing and screening the enhanced corpus using the initial classification prediction model to obtain an enhanced corpus subset comprises:
analyzing the enhanced corpus by using the initial classification prediction model to obtain a classification analysis result set of each piece of data in the enhanced corpus;
and deleting the data corresponding to the classification analysis result set with the classification analysis results smaller than a preset threshold from the enhanced corpus set to obtain the enhanced corpus subset.
5. The method according to claim 1, wherein the obtaining a corpus text of a user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result comprises:
analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a classification analysis result set;
sorting the classification analysis results in the classification analysis result set;
and selecting the classification analysis result with the maximum value as the final analysis result.
6. The method according to claim 3, wherein said performing deep separable convolution pooling on said first training set to obtain a reduced-dimension data set comprises:
performing packet convolution operation on the first training set to obtain a deep convolution data set;
performing point-by-point convolution operation on the depth convolution data set to obtain a point-by-point convolution data set;
and carrying out average pooling operation on the point-by-point convolution data set to obtain the dimensionality reduction data set.
7. An intelligent question-answer corpus analyzing device, comprising:
the corpus enhancement module is used for acquiring a historical question and answer corpus and inputting the historical question and answer corpus into a pre-constructed data enhancement model to obtain an enhanced corpus;
the enhanced corpus screening module is used for training a pre-constructed convolutional neural network model by utilizing the historical question-answer corpus to obtain an initial classification prediction model; analyzing and screening the enhanced corpus by using the initial classification prediction model to obtain an enhanced corpus subset;
the model training module is used for training the convolutional neural network model by utilizing the enhanced corpus subset and the historical question-answer corpus set to obtain an analysis prediction model;
and the model analysis module is used for acquiring the corpus text of the user to be analyzed, and analyzing the corpus text of the user to be analyzed by using the analysis prediction model to obtain a final analysis result.
8. The apparatus according to claim 7, wherein the corpus filtering module obtains the corpus subsets by:
analyzing the enhanced corpus by using the initial classification prediction model to obtain a classification analysis result set of each piece of data in the enhanced corpus;
and deleting the data corresponding to the classification analysis result set with the classification analysis results smaller than a preset threshold from the enhanced corpus set to obtain the enhanced corpus subset.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the intelligent corpus questioning method according to any one of claims 1 to 6.
10. A computer-readable storage medium comprising a storage data area storing data created according to use of blockchain nodes and a storage program area storing a computer program, wherein the computer program, when executed by a processor, implements the intelligent corpus analysis method according to any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564937.7A CN111563152A (en) | 2020-06-19 | 2020-06-19 | Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium |
| PCT/CN2020/119102 WO2021151306A1 (en) | 2020-06-19 | 2020-09-29 | Method and apparatus for smart analysis of question and answer linguistic material, electronic device, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010564937.7A CN111563152A (en) | 2020-06-19 | 2020-06-19 | Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111563152A true CN111563152A (en) | 2020-08-21 |
Family
ID=72072736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010564937.7A Pending CN111563152A (en) | 2020-06-19 | 2020-06-19 | Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111563152A (en) |
| WO (1) | WO2021151306A1 (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932534A (en) * | 2020-09-22 | 2020-11-13 | 平安科技（深圳）有限公司 | Medical image picture analysis method and device, electronic equipment and readable storage medium |
| CN112417121A (en) * | 2020-11-20 | 2021-02-26 | 平安普惠企业管理有限公司 | Client intention recognition method and device, computer equipment and storage medium |
| CN112528112A (en) * | 2020-12-15 | 2021-03-19 | 平安科技（深圳）有限公司 | Data collection and analysis method and device, electronic equipment and storage medium |
| CN112541745A (en) * | 2020-12-22 | 2021-03-23 | 平安银行股份有限公司 | User behavior data analysis method and device, electronic equipment and readable storage medium |
| CN112632220A (en) * | 2020-12-22 | 2021-04-09 | 平安普惠企业管理有限公司 | Loan fund destination analysis method based on AI model and related equipment |
| WO2021151306A1 (en) * | 2020-06-19 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for smart analysis of question and answer linguistic material, electronic device, and readable storage medium |
| CN113312482A (en) * | 2021-06-01 | 2021-08-27 | 平安证券股份有限公司 | Question classification method and device, electronic equipment and readable storage medium |
| CN113344415A (en) * | 2021-06-23 | 2021-09-03 | 中国平安财产保险股份有限公司 | Deep neural network-based service distribution method, device, equipment and medium |
| CN113435998A (en) * | 2021-06-23 | 2021-09-24 | 平安科技（深圳）有限公司 | Loan overdue prediction method and device, electronic equipment and storage medium |
| CN114564916A (en) * | 2022-03-03 | 2022-05-31 | 山东新一代信息产业技术研究院有限公司 | Method, device and medium for simplifying corpus addition and corpus tagging |
| CN116821622A (en) * | 2023-06-29 | 2023-09-29 | 广西昌洲天然药业有限公司 | Method and device for analyzing extraction effect of centella asiatica total glycosides based on neural network |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114141387A (en) * | 2021-11-25 | 2022-03-04 | 泰康保险集团股份有限公司 | Interactive information recommendation method, device and equipment in internet medical session |
| CN114610855B (en) * | 2022-03-15 | 2024-06-18 | 平安科技（深圳）有限公司 | Dialogue reply generation method and device, electronic equipment and storage medium |
| CN116910223B (en) * | 2023-08-09 | 2024-06-11 | 北京安联通科技有限公司 | Intelligent question-answering data processing system based on pre-training model |
| CN117312530A (en) * | 2023-11-10 | 2023-12-29 | 北京百度网讯科技有限公司 | Questionnaire and model training method, device, equipment, medium and product |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106951468B (en) * | 2017-03-02 | 2018-12-28 | 腾讯科技（深圳）有限公司 | Talk with generation method and device |
| JP2019020893A (en) * | 2017-07-13 | 2019-02-07 | 国立研究開発法人情報通信研究機構 | Non-factoid type question answering machine |
| CN108280206B (en) * | 2018-01-30 | 2020-05-26 | 尹忠博 | Short text classification method based on semantic enhancement |
| CN110032632A (en) * | 2019-04-04 | 2019-07-19 | 平安科技（深圳）有限公司 | Intelligent customer service answering method, device and storage medium based on text similarity |
| CN110162627B (en) * | 2019-04-28 | 2022-04-15 | 平安科技（深圳）有限公司 | Data increment method and device, computer equipment and storage medium |
| CN111563152A (en) * | 2020-06-19 | 2020-08-21 | 平安科技（深圳）有限公司 | Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium |
-
2020
- 2020-06-19 CN CN202010564937.7A patent/CN111563152A/en active Pending
- 2020-09-29 WO PCT/CN2020/119102 patent/WO2021151306A1/en active Application Filing
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021151306A1 (en) * | 2020-06-19 | 2021-08-05 | 平安科技（深圳）有限公司 | Method and apparatus for smart analysis of question and answer linguistic material, electronic device, and readable storage medium |
| CN111932534B (en) * | 2020-09-22 | 2021-07-06 | 平安科技（深圳）有限公司 | Medical image picture analysis method and device, electronic equipment and readable storage medium |
| WO2021151338A1 (en) * | 2020-09-22 | 2021-08-05 | 平安科技（深圳）有限公司 | Medical imagery analysis method, apparatus, electronic device and readable storage medium |
| CN111932534A (en) * | 2020-09-22 | 2020-11-13 | 平安科技（深圳）有限公司 | Medical image picture analysis method and device, electronic equipment and readable storage medium |
| CN112417121A (en) * | 2020-11-20 | 2021-02-26 | 平安普惠企业管理有限公司 | Client intention recognition method and device, computer equipment and storage medium |
| CN112528112A (en) * | 2020-12-15 | 2021-03-19 | 平安科技（深圳）有限公司 | Data collection and analysis method and device, electronic equipment and storage medium |
| CN112528112B (en) * | 2020-12-15 | 2024-06-04 | 平安科技（深圳）有限公司 | Data collection and analysis method and device, electronic equipment and storage medium |
| CN112541745B (en) * | 2020-12-22 | 2024-04-09 | 平安银行股份有限公司 | User behavior data analysis method and device, electronic equipment and readable storage medium |
| CN112541745A (en) * | 2020-12-22 | 2021-03-23 | 平安银行股份有限公司 | User behavior data analysis method and device, electronic equipment and readable storage medium |
| CN112632220A (en) * | 2020-12-22 | 2021-04-09 | 平安普惠企业管理有限公司 | Loan fund destination analysis method based on AI model and related equipment |
| CN113312482A (en) * | 2021-06-01 | 2021-08-27 | 平安证券股份有限公司 | Question classification method and device, electronic equipment and readable storage medium |
| CN113435998B (en) * | 2021-06-23 | 2023-05-02 | 平安科技（深圳）有限公司 | Loan overdue prediction method and device, electronic equipment and storage medium |
| CN113435998A (en) * | 2021-06-23 | 2021-09-24 | 平安科技（深圳）有限公司 | Loan overdue prediction method and device, electronic equipment and storage medium |
| CN113344415A (en) * | 2021-06-23 | 2021-09-03 | 中国平安财产保险股份有限公司 | Deep neural network-based service distribution method, device, equipment and medium |
| CN114564916A (en) * | 2022-03-03 | 2022-05-31 | 山东新一代信息产业技术研究院有限公司 | Method, device and medium for simplifying corpus addition and corpus tagging |
| CN116821622A (en) * | 2023-06-29 | 2023-09-29 | 广西昌洲天然药业有限公司 | Method and device for analyzing extraction effect of centella asiatica total glycosides based on neural network |
| CN116821622B (en) * | 2023-06-29 | 2024-02-13 | 广西昌洲天然药业有限公司 | Method and device for analyzing extraction effect of centella asiatica total glycosides based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021151306A1 (en) | 2021-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563152A (en) | Intelligent question and answer corpus analysis method and device, electronic equipment and readable storage medium | |
| CN112732915A (en) | Emotion classification method and device, electronic equipment and storage medium | |
| CN112883190A (en) | Text classification method and device, electronic equipment and storage medium | |
| CN112288337B (en) | Behavior recommendation method, behavior recommendation device, behavior recommendation equipment and behavior recommendation medium | |
| CN114491047A (en) | Multi-label text classification method and device, electronic equipment and storage medium | |
| CN112988963A (en) | User intention prediction method, device, equipment and medium based on multi-process node | |
| CN112906377A (en) | Question answering method and device based on entity limitation, electronic equipment and storage medium | |
| CN113268665A (en) | Information recommendation method, device and equipment based on random forest and storage medium | |
| CN112528013A (en) | Text abstract extraction method and device, electronic equipment and storage medium | |
| CN112750529A (en) | Intelligent medical inquiry device, equipment and medium | |
| CN112885423A (en) | Disease label detection method and device, electronic equipment and storage medium | |
| CN113887930A (en) | Question-answering robot health degree evaluation method, device, equipment and storage medium | |
| CN113435998A (en) | Loan overdue prediction method and device, electronic equipment and storage medium | |
| CN114880449A (en) | Reply generation method and device of intelligent question answering, electronic equipment and storage medium | |
| CN111930897B (en) | Patent retrieval method, device, electronic equipment and computer-readable storage medium | |
| CN114220536A (en) | Disease analysis method, device, equipment and storage medium based on machine learning | |
| CN113505273A (en) | Data sorting method, device, equipment and medium based on repeated data screening | |
| CN113656690A (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN113360654A (en) | Text classification method and device, electronic equipment and readable storage medium | |
| CN111950707A (en) | Behavior prediction method, apparatus, device and medium based on behavior co-occurrence network | |
| CN115146064A (en) | Intention recognition model optimization method, device, equipment and storage medium | |
| CN115982460A (en) | Personalized recommendation method, system and medium for health science popularization information | |
| CN115221274A (en) | Text emotion classification method and device, electronic equipment and storage medium | |
| CN113590845B (en) | Knowledge graph-based document retrieval method and device, electronic equipment and medium | |
| CN113051475B (en) | Content recommendation method, device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40030726 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |