CN113515626A - Method, device and equipment for determining public opinion category - Google Patents
Method, device and equipment for determining public opinion category Download PDFInfo
- Publication number
- CN113515626A CN113515626A CN202110544720.4A CN202110544720A CN113515626A CN 113515626 A CN113515626 A CN 113515626A CN 202110544720 A CN202110544720 A CN 202110544720A CN 113515626 A CN113515626 A CN 113515626A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- target
- information
- summary information
- abstract
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000015654 memory Effects 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000013145 classification model Methods 0.000 claims abstract description 44
- 210000002569 neuron Anatomy 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000007787 long-term memory Effects 0.000 claims abstract description 16
- 230000006403 short-term memory Effects 0.000 claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 73
- 230000006870 function Effects 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 2
- 230000000875 corresponding effect Effects 0.000 description 29
- 238000010586 diagram Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000001537 neural effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the specification provides a method, a device and equipment for determining public opinion categories, and the method, the device and the equipment for determining the public opinion categories can be used in the technical field of big data. The method comprises the steps of obtaining specified public opinion summary information; processing the specified public opinion abstract information by using a public opinion classification model to obtain a public opinion category corresponding to the specified public opinion abstract information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data. The public opinion category can be efficiently and accurately determined by utilizing the embodiment of the specification.
Description
Technical Field
The application relates to the technical field of big data, in particular to a method, a device and equipment for determining public opinion categories.
Background
With the continuous development of internet application, public sentiment needs to be monitored in industries such as advertising, retail and investment, so as to deal with the influence brought by public sentiment information through public sentiment analysis. At present, the public opinion analysis service mainly captures corresponding articles from some open platforms according to keywords provided by users, however, in general, there are many target articles captured from the open platforms, and often, the articles with relatively negative evaluation are the ones that the users really want to know and view. Therefore, it becomes more and more important how to accurately identify articles that are negative.
In the prior art, the type identification of public opinion information is mainly realized by combining a pre-training model and an Attention mechanism. However, this approach requires model training using an officially provided pre-training model (e.g. BERT, ERNIE) in combination with scene data each time, thereby reducing the efficiency of identifying public opinion information.
Therefore, there is a need for a solution to the above technical problems.
Disclosure of Invention
The embodiment of the specification provides a method, a device and equipment for determining public opinion categories, and model training is performed without using a pre-training model provided by an official party and combining scene data every time, so that the public opinion categories can be determined efficiently and accurately.
The method, the device and the equipment for determining the public opinion category are realized in the following modes.
A method of determining a public opinion category, comprising: acquiring specified public opinion abstract information; processing the specified public opinion abstract information by using a public opinion classification model to obtain a public opinion category corresponding to the specified public opinion abstract information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
A public opinion classification model training method comprises the following steps: acquiring target public opinion summary information; wherein, the target public opinion summary information is pre-assigned with exposure weight; determining a feature word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information; calculating TF-IDF values of all the characteristic words in the characteristic word vectors to obtain target abstract vectors of the target public opinion abstract information; determining text similarity of the target public opinion summary information based on the exposure weight and the target summary vector of the target public opinion summary information; the text similarity is used for representing the public opinion category of the target public opinion summary information; training a preset long-short term memory model by using the target public opinion abstract information and the corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
An apparatus for determining a public opinion category, comprising: the acquisition module is used for acquiring the specified public opinion abstract information; the acquisition module is used for processing the specified public opinion summary information by using a public opinion classification model to acquire a public opinion category corresponding to the specified public opinion summary information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
A public opinion classification model training device comprises: the acquisition module is used for acquiring the abstract information of the target public sentiment; wherein, the target public opinion summary information is pre-assigned with exposure weight; the first determining module is used for determining a characteristic word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information; the calculating module is used for calculating TF-IDF values of all the characteristic words in the characteristic word vectors to obtain target abstract vectors of the target public opinion abstract information; the second determination module is used for determining the text similarity of the target public opinion abstract information based on the exposure weight and the target abstract vector of the target public opinion abstract information; the text similarity is used for representing the public opinion category of the target public opinion summary information; the training module is used for training a preset long-short term memory model by utilizing the target public opinion abstract information and the corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
An apparatus for determining a public opinion category comprising at least one processor and a memory storing computer-executable instructions that, when executed by the processor, perform the steps of any one of the method embodiments of the present specification.
A computer readable storage medium having stored thereon computer instructions which, when executed, implement the steps of any one of the method embodiments in the present specification.
The specification provides a method, a device and equipment for determining public opinion categories. In some embodiments, the public opinion summary information can be obtained, and the public opinion classification model is used to process the public opinion summary information to obtain a public opinion category corresponding to the public opinion summary information. The public opinion classification model is obtained by training the preset long-term and short-term memory model based on the public opinion abstract information and the corresponding public opinion category, and the neuron structure of the preset long-term and short-term memory model comprises an external connection gate, so that the model training is performed without using the pre-training model provided by the official part and combining scene data every time, and interactive calculation is performed by adding the external connection gate, so that the memory is strengthened for the important information output by the previous neuron before the input information is transmitted to the next neuron every time, and the public opinion category can be efficiently and accurately determined.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, are incorporated in and constitute a part of this specification, and are not intended to limit the specification. In the drawings:
fig. 1 is a flowchart illustrating an embodiment of a method for determining a public opinion category provided in the present specification;
fig. 2 is a flowchart illustrating an embodiment of a public opinion classification model training method provided in the present specification;
fig. 3 is a block diagram illustrating an example of a public opinion category determining apparatus according to the present disclosure;
fig. 4 is a schematic block diagram illustrating an embodiment of a public opinion classification model training apparatus according to the present disclosure;
fig. 5 is a hardware configuration block diagram of an embodiment of a server for determining a public opinion category provided in the present specification.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments in the present specification, and not all of the embodiments. All other embodiments that can be obtained by a person skilled in the art based on one or more embodiments of the present disclosure without making any creative effort shall fall within the protection scope of the embodiments of the present disclosure.
The following describes an embodiment of the present disclosure with a specific application scenario as an example. Specifically, fig. 1 is a flowchart illustrating an embodiment of a method for determining a public opinion category provided in the present specification. Although the present specification provides the method steps or apparatus structures as shown in the following examples or figures, more or less steps or modules may be included in the method or apparatus structures based on conventional or non-inventive efforts.
One embodiment provided by the present specification can be applied to a client, a server, and the like. The client may include a terminal device, such as a smart phone, a tablet computer, and the like. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed system, and the like.
It should be noted that the following description of the embodiments does not limit the technical solutions in other extensible application scenarios based on the present specification. In an embodiment of a method for determining a public opinion category, as shown in fig. 1, the method may include the following steps.
S0: and acquiring the specified public opinion abstract information.
The public opinion abstract information can be any public opinion abstract information needing to determine the public opinion category.
In some embodiments, the public opinion information may be obtained before the specified public opinion summary information is obtained. The public opinion information may be generated currently or historical public opinion information, and may be determined according to actual conditions, which is not limited in the embodiments of the present specification.
In some implementations, the public opinion information may be information for a company, an individual, or the like. The specific situation can be determined according to actual situations, and the embodiment of the present specification does not limit the specific situation.
In some implementation scenarios, the manner of obtaining public opinion information may include: and pulling the data from a preset database, or retrieving and acquiring the data by utilizing the Internet, and the like. It should be understood that the above description is only exemplary, and the method for obtaining the public opinion information is not limited to the above examples, for example, the public opinion information may be collected according to certain conditions in a plurality of channels such as wan de, penbo, and company internal systems by using the crawler technology, and those skilled in the art may make other modifications within the spirit of the present application, but the present application is within the scope of the present application as long as the functions and effects achieved by the present application are the same as or similar to the present application.
In some implementation scenarios, after obtaining the public opinion information, the public opinion information may be stored in a database or a corresponding memory.
In some embodiments, after obtaining the public opinion information, the obtained public opinion information may be extracted to obtain the public opinion summary information.
In some implementation scenarios, the public opinion information may be abstracted by using a preset abstraction model. The preset extraction model can be obtained by training the neural network by utilizing each sentence and the importance degree of each sentence in the public opinion information. It is to be understood that the above description is only exemplary, and the manner of extracting the abstract of public opinion information is not limited to the above examples, and other modifications are possible for those skilled in the art in light of the spirit of the present application, but all that can be achieved is covered by the scope of the present application as long as the functions and effects achieved by the present application are the same as or similar to those of the present application.
S2: processing the specified public opinion abstract information by using a public opinion classification model to obtain a public opinion category corresponding to the specified public opinion abstract information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
In the embodiment of the specification, after the specified public opinion summary information is obtained, the specified public opinion summary information can be input into the public opinion classification model to obtain the public opinion category corresponding to the specified public opinion summary information. The public opinion categories may include positive public opinion categories (positive public opinion), negative public opinion categories (negative public opinion), and neutral public opinion categories, and the public opinion categories may also include others, and may be determined according to actual situations, which is not limited in the embodiments of the present specification.
In the embodiment of the specification, before the public opinion classification model is used for processing the specified public opinion summary information, the public opinion classification model can be obtained by training the preset long-short term memory model by using the public opinion summary information and the corresponding public opinion category.
As shown in fig. 2, fig. 2 is a flowchart illustrating an embodiment of a public opinion classification model training method provided in this specification, and in this embodiment, the method may include the following steps.
S20: acquiring target public opinion summary information; wherein, the target public opinion summary information is pre-assigned with exposure weight.
In some embodiments, before obtaining the target public opinion summary information, the method may include: acquiring a plurality of pieces of public opinion information; extracting the abstract of each piece of public opinion information to obtain a plurality of pieces of public opinion abstract information; and deleting the public opinion summary information of which the similarity meets the preset condition from the plurality of pieces of public opinion summary information to obtain target public opinion summary information. The preset condition may be set according to an actual scene, and may be, for example, greater than 85%, greater than 90%, and the like, which is not limited in this embodiment of the specification.
In some implementation scenarios, the pieces of public opinion information may be generated currently or historical public opinion information, and may be determined according to actual situations, which is not limited in this specification. It should be noted that, the manner described in the foregoing embodiments may be referred to for the related processing of public opinion information, and details thereof are not repeated.
In some implementation scenarios, after obtaining the plurality of pieces of public opinion information, a summary of each piece of public opinion information may be extracted to obtain a plurality of pieces of public opinion summary information.
In some implementation scenarios, in order to improve the accuracy of the subsequent training model, after a plurality of pieces of public opinion summary information are obtained, the similarity between the public opinion summary information may be calculated, then the public opinion summary information with higher similarity is removed, and the remaining public opinion summary information is stored in the target database. The target database can be a MySQL database, an Oracle database, or the like.
In some implementation scenarios, the target public opinion summary information may be any piece of public opinion summary information in a target database.
In some implementation scenarios, after the public opinion summary information with higher similarity is removed and the remaining public opinion summary information is stored in the target database, an exposure weight may be randomly assigned to each piece of public opinion summary information in the target database. The exposure weight may be used to represent the importance of the public opinion summary information, and the exposure weight of the public opinion summary information may be a numerical value greater than 0.
S22: determining a feature word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information.
In the embodiment of the specification, after the target public opinion summary information is obtained, a feature word vector of the target public opinion summary information can be determined.
Since the target public opinion summary information may include some redundant information (e.g., a large number of "words," characters of non-text information, etc.), in some implementation scenarios, the redundant information in each piece of target public opinion summary information may be removed, and then feature words are extracted from the redundant information to obtain feature word vectors of the target public opinion summary information. The feature word vector may include a plurality of feature words of the target public opinion summary information. The feature words may be keywords extracted from the target public opinion summary information and used for representing the target public opinion summary information, for example: default, overdue, etc.
In some implementation scenes, data cleaning can be carried out on the target public opinion abstract information, redundant information in the public opinion abstract information is removed, and therefore effectiveness of the target public opinion abstract information can be guaranteed, and guarantee is provided for improving accuracy of a subsequent training model.
In some implementation scenarios, in order to efficiently and accurately extract the corresponding feature words from the target public opinion summary information, at least one feature word included in the target public opinion summary information may be extracted by using a feature word recognition model obtained by deep learning network training in advance. The input of the feature word recognition model can be a classification label of the public opinion summary information and a text of the public opinion summary information, and the output can be at least one feature word contained in the public opinion summary information. Wherein, the sensitive keywords (characteristic words) related to different fields may be different.
Since the sensitive keywords related to different fields may be different, in the embodiments of the present specification, a feature word recognition model is obtained by training a deep learning network in advance using a classification tag of the public opinion summary information and a text of the public opinion summary information, and then a feature word included in the target public opinion summary information is extracted using the feature word recognition model obtained by training, so that the determined feature word vector of the target public opinion summary information may be more accurate.
S24: and calculating TF-IDF values of all the characteristic words in the characteristic word vectors to obtain the target abstract vector of the target public opinion abstract information.
In the embodiment of the specification, after the feature word vector of the target public opinion summary information is determined, the TF-IDF value of each feature word in the feature word vector may be calculated to obtain the target summary vector of the target public opinion summary information.
In some embodiments, the calculating TF-IDF values of each feature word in the feature word vector to obtain a target summary vector of the target public opinion summary information may include: counting the occurrence times of target feature words in the feature word vectors in the target public opinion summary information; determining the occurrence frequency of the characteristic word with the maximum occurrence frequency in the target public opinion summary information; calculating the word frequency of the target characteristic word according to the frequency of the target characteristic word appearing in the target public opinion summary information and the frequency of the characteristic word appearing in the target public opinion summary information with the maximum frequency; acquiring the total amount of public opinion summary information recorded in a target database; determining the quantity of public opinion summary information containing the target characteristic words in the target database; calculating the inverse document frequency of the target characteristic words according to the total quantity of the public opinion summary information recorded in the target database and the quantity of the public opinion summary information containing the target characteristic words in the target database; taking the product of the word frequency of the target characteristic word and the inverse document frequency as the TF-IDF value of the target characteristic word; and obtaining a target abstract vector of the target public opinion abstract information based on the TF-IDF value of each feature word in the feature word vector. Among them, TF-IDF (Term Frequency-Inverse Document Frequency) is a commonly used weighting technique for information retrieval and data mining, TF represents a Term Frequency (Term Frequency), and IDF represents an Inverse text Frequency index (Inverse Document Frequency). TF-IDF is a statistical method to assess how important a word is for one of a set of documents or a corpus. The importance of a word increases in proportion to the number of times it appears in a document, but at the same time decreases in inverse proportion to the frequency with which it appears in the corpus.
In some implementation scenarios, the word frequency and the inverse document frequency may be calculated respectively, and then the TF-IDF value of each feature word in the feature word vector may be calculated according to the word frequency and the inverse document frequency. Wherein, the TF-IDF value of the characteristic word can represent the importance of the characteristic word in the target public opinion information.
In some implementation scenarios, the word frequency of the target feature word may be calculated according to the following formula:
wherein, TFiWord frequency, n, of target feature wordsiThe times of appearance of the target characteristic words in the target public opinion summary information, njThe method is used for determining the occurrence frequency of the characteristic words with the largest occurrence frequency in the target public opinion summary information. The target feature word can be any one feature word in the feature word vector.
In some implementations, the inverse document frequency of the target feature word may be calculated according to the following formula:
wherein, IDFiThe inverse document frequency of the target characteristic word; n is the total quantity of public opinion summary information recorded in the target database, MiThe number of public opinion summary information containing the target characteristic words in the target database is shown. The target database can be a database for recording public opinion summary information.
In some implementation scenarios, after the word frequency and the inverse document frequency of the target feature word are obtained, the product of the word frequency and the inverse document frequency of the target feature word may be used as the TF-IDF value of the target feature word. Likewise, the TF-IDF value of each feature word in the feature word vector may be obtained in a similar manner.
In some implementation scenarios, after obtaining the TF-IDF value of each feature word in the feature word vector, the TF-IDF values of each feature word may be arranged in sequence to form a vector, and the vector is used as a target summary vector of the target public opinion summary information. Similarly, a summary vector of each public opinion summary information in the target database can be obtained in a similar manner.
S26: determining text similarity of the target public opinion summary information based on the exposure weight and the target summary vector of the target public opinion summary information; the text similarity is used for representing the public opinion category of the target public opinion summary information.
In an embodiment of the specification, after a target abstract vector of target public opinion abstract information is obtained, text similarity of the target public opinion abstract information may be determined based on an exposure weight of the target public opinion abstract information and the target abstract vector. The text similarity can be used for representing the public opinion category of the target public opinion summary information. The public opinion categories may include positive public opinion category (positive public opinion), negative public opinion category (negative public opinion), and neutral public opinion category, but the public opinion categories may also include others, and may be determined according to actual situations, which is not limited in the embodiments of the present specification.
The probability that the more important public opinion information appears in multiple platforms and channels is higher, so that the public opinion category of the target public opinion abstract information is accurately determined, the requirements on public opinion importance, risk degree and other aspects of analysis are met, and the text similarity of the target public opinion abstract information can be further determined based on the exposure weight and the target abstract vector of the target public opinion abstract information.
In some embodiments, the determining the text similarity of the target public opinion summary information based on the exposure weight and the target summary vector of the target public opinion summary information may include: acquiring abstract vectors of the remaining public opinion abstract information in a target database; respectively calculating text similarity of the target public opinion summary information and the residual public opinion summary information in the target database based on the exposure weight of the target public opinion summary information, the target summary vector and the summary vectors of the residual public opinion summary information in the target database to obtain a text similarity set; and selecting the text similarity with the maximum value in the text similarity set as the text similarity of the target public opinion summary information.
In some implementation scenarios, the road in the target database includes a plurality of pieces of public opinion summary information, so that the text similarity between the target public opinion summary information and each piece of the remaining public opinion summary information can be calculated, and then the maximum value is selected as the text similarity of the target public opinion summary information. For example, the target database includes public opinion summary information 1, public opinion summary information 2 and public opinion summary information 3, when determining the text similarity of the public opinion summary information 1, the public opinion summary information 1 can be used as the target public opinion summary information, then the text similarities of the public opinion summary information 1, the public opinion summary information 2 and the public opinion summary information 3 are respectively calculated and respectively marked as the similarities a12 and a13, finally the similarities a12 and a13 are compared, and the maximum value of the a12 and the maximum value of the a13 is used as the text similarity of the public opinion summary information 1; similarly, when determining the text similarity of the public opinion summary information 2, the public opinion summary information 2 can be used as the target public opinion summary information, then the text similarities of the public opinion summary information 2, the public opinion summary information 1 and the public opinion summary information 3 are respectively calculated and are respectively marked as similarities a21 and a23, and finally a21 and a23 are compared, and the maximum value of a21 and a23 is used as the text similarity of the public opinion summary information 2; when determining the text similarity of the public opinion summary information 3, the public opinion summary information 3 may be used as the target public opinion summary information, then the text similarities of the public opinion summary information 3 with the public opinion summary information 1 and the public opinion summary information 2 are respectively calculated and are respectively marked as similarities a31 and a32, and finally a31 and a32 are compared, and the maximum value of a31 and a32 is used as the text similarity of the public opinion summary information 2.
In some implementation scenarios, after obtaining the text similarity of each piece of public opinion summary information, further, the public opinion category of the target summary information may be determined according to the text similarity.
In some implementation scenarios, the text similarity between the target public opinion summary information and the rest public opinion summary information in the target database can be calculated according to the following formula:
wherein, cos (θ)w) The method comprises the steps of representing text similarity, w representing exposure weight of target public opinion summary information, tanh (w) representing the standardized processing of the exposure weight of the target public opinion summary information, x representing a target summary vector of the target public opinion summary information, y representing a summary vector of any piece of public opinion summary information left in a target database, and the vector dimensions of x and y being the same.
Of course, the text similarity between the target public opinion summary information and the rest of the public opinion summary information in the target database can be calculated in other manners, and other modifications are possible for those skilled in the art with the benefit of the technical spirit of the present application, but the scope of the present application should be covered as long as the functions and effects achieved by the present application are the same as or similar to those of the present application.
S28: training a preset long-short term memory model by using the target public opinion abstract information and the corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
In the embodiment of the specification, after the text similarity of the target public opinion summary information is determined, the preset long-term and short-term memory model can be trained by using the target public opinion summary information and the corresponding text similarity to obtain a public opinion classification model.
In some embodiments, presetting the neuron structure of the long-short term memory model is adding an outlier determination based on the first neuron structure. Wherein the first neuronal structure is a neuronal structure in a long-short term memory model. The external gate may be used to enhance the coupling of input data to output data. The Long Short-Term Memory model (LSTM) is a time-cycle neural network and is specially designed for solving the Long-Term dependence problem of the general RNN (cyclic neural network). The LSTM adds a memory unit in each nerve unit of a hidden layer on the basis of RNN, thereby controlling the memory information on a time sequence. The LSTM can control the memory and forgetting degree of the previous information and the current information through a plurality of controllable gates (forgetting gate, input gate and output gate) when the LSTM is transmitted among the units of the hidden layer every time, so that the LSTM network has a long-term memory function.
In some embodiments, the extrinsic gating function in the neuron structure of the preset long-short term memory model may be:
wherein, wiRepresenting the exposure weight of the ith item public opinion summary information, i belongs to (0.. N), N represents the number of the target public opinion summary information, and xiRepresenting input information of the current neuron, QiRepresenting the number of interaction rounds, xi-1Representing the input information of the last neuron, ht-1The output information of the last neuron is represented, and sigmoid represents an activation function. sigmoid is a sigmoid function commonly found in biology, also called sigmoidal growth curve. In information science, due to the nature of single increment and single increment of an inverse function, a sigmoid function is often used as an activation function of a neural network, and variables are mapped between 0 and 1.
In the embodiment of the specification, the external gating function is used for performing interactive calculation, so that the input information and the last output information can be strongly correlated, the important information is strengthened, and the accuracy of the training model can be improved.
In the embodiment of the specification, on the basis of the LSTM original logic, the information memory among the neural units is enhanced by adding the external connection gate, and the original information is enhanced again by enhancing the memory of the input and output information, so that the more important information before is enhanced once again during output, and better memory can be still realized in a longer text.
In some embodiments, after the public opinion classification model is obtained by training the preset long and short term memory model by using the target public opinion abstract information and the corresponding text similarity, the public opinion classification model can be stored, so that the public opinion classification model can be directly called when the public opinion category needs to be determined subsequently, and the classification efficiency is improved.
In some embodiments, when the public opinion category needs to be determined, a public opinion classification model may be obtained, and the specified public opinion summary information is input into the public opinion classification model, so as to obtain text similarity corresponding to the specified public opinion summary information, wherein the text similarity may represent the public opinion category of the specified public opinion summary information.
In some implementation scenarios, after the public opinion classification model is used to determine the public opinion classification, the public opinion classification may be stored. Furthermore, the classification result can be sent to the user in time through a short message or other modes.
In the embodiment of the specification, exposure weight is distributed to each piece of public opinion abstract information, and the text similarity of the public opinion abstract information is determined based on the exposure weight and the abstract vector of the public opinion abstract information, so that the importance of the articles can be increased by giving weight to high-frequency articles; before the model is trained, the importance of the data layer is judged in advance, so that the accuracy of subsequent model training can be improved; the external connection door is added on the basis of the LSTM, so that the relation of input and output data can be strengthened, the memory between upper and lower information transmission is strengthened, and the prediction of the model aiming at public opinion information classification and importance can be effectively improved.
It is to be understood that the foregoing is only exemplary, and the embodiments of the present disclosure are not limited to the above examples, and other modifications may be made by those skilled in the art within the spirit of the present disclosure, and the scope of the present disclosure is intended to be covered by the claims as long as the functions and effects achieved by the embodiments are the same as or similar to the present disclosure.
From the above description, it can be seen that, in the embodiment of the application, the specified public opinion summary information can be obtained, and the public opinion classification model is used to process the specified public opinion summary information, so as to obtain the public opinion category corresponding to the specified public opinion summary information. The public opinion classification model is obtained by training the preset long-term and short-term memory model based on the public opinion abstract information and the corresponding public opinion category, and the neuron structure of the preset long-term and short-term memory model comprises an external connection gate, so that the model training is performed without using the pre-training model provided by the official part and combining scene data every time, and interactive calculation is performed by adding the external connection gate, so that the memory is strengthened for the important information output by the previous neuron before the input information is transmitted to the next neuron every time, and the public opinion category can be efficiently and accurately determined.
In the present specification, each embodiment of the method is described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments. Reference is made to the description of the method embodiments.
Based on the method for determining the public opinion category, one or more embodiments of the present specification further provide a device for determining the public opinion category. The apparatus may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that use the methods described in the embodiments of the present specification in conjunction with any necessary apparatus to implement the hardware. Based on the same innovative conception, embodiments of the present specification provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific implementation of the apparatus in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Specifically, fig. 3 is a schematic block diagram illustrating an embodiment of an apparatus for determining a public opinion category according to the present specification, and as shown in fig. 3, the apparatus for determining a public opinion category according to the present specification may include: an obtaining module 120 and an obtaining module 122.
An obtaining module 120, configured to obtain the specified public opinion summary information;
an obtaining module 122, configured to process the specified public opinion summary information by using a public opinion classification model, and obtain a public opinion category corresponding to the specified public opinion summary information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
It should be noted that the above-mentioned description of the apparatus according to the method embodiment may also include other embodiments, and specific implementation manners may refer to the description of the related method embodiment, which is not described herein again.
As shown in fig. 4, fig. 4 is a schematic block diagram of an embodiment of a public opinion classification model training apparatus provided in this specification, and the apparatus may include: an acquisition module 210, a first determination module 212, a calculation module 214, a second determination module 216, and a training module 218.
An obtaining module 210, configured to obtain the summary information of the target public opinion; wherein, the target public opinion summary information is pre-assigned with exposure weight;
a first determining module 212, configured to determine a feature word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information;
a calculating module 214, configured to calculate a TF-IDF value of each feature word in the feature word vector, so as to obtain a target summary vector of the target public opinion summary information;
a second determining module 216, configured to determine a text similarity of the target public opinion summary information based on the exposure weight and the target summary vector of the target public opinion summary information; the text similarity is used for representing the public opinion category of the target public opinion summary information;
a training module 218, configured to train a preset long-term and short-term memory model by using the abstract information of the target public opinion and corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
It should be noted that the above-mentioned description of the apparatus according to the method embodiment may also include other embodiments, and specific implementation manners may refer to the description of the related method embodiment, which is not described herein again.
The present specification also provides an embodiment of an apparatus for determining a public opinion category, comprising a processor and a memory for storing processor-executable instructions, which when executed by the processor, implement steps comprising: acquiring specified public opinion abstract information; processing the specified public opinion abstract information by using a public opinion classification model to obtain a public opinion category corresponding to the specified public opinion abstract information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
It should be noted that the above-mentioned apparatuses may also include other embodiments according to the description of the method or apparatus embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.
The method embodiments provided in the present specification may be executed in a mobile terminal, a computer terminal, a server or a similar computing device. For example, fig. 5 is a hardware block diagram of an embodiment of a server for determining a public opinion category provided in this specification, where the server may be the apparatus for determining a public opinion category or the device for determining a public opinion category in the above embodiments. As shown in fig. 5, the server 10 may include one or more (only one shown) processors 100 (the processors 100 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 200 for storing data, and a transmission module 300 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 5 is only an illustration and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer components than shown in FIG. 5, and may also include other processing hardware, such as a database or multi-level cache, a GPU, or have a different configuration than shown in FIG. 5, for example.
The memory 200 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the method for determining public opinion category in the embodiment of the present specification, and the processor 100 may execute various functional applications and data processing by executing the software programs and modules stored in the memory 200. Memory 200 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 200 may further include memory located remotely from processor 100, which may be connected to a computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 300 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission module 300 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 300 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The method or apparatus provided by the present specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, so as to implement the effect of the solution described in the embodiments of the present specification. The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.
The above method or apparatus embodiments for determining public opinion category provided in this specification may be implemented in a computer by executing corresponding program instructions by a processor, for example, implemented in a PC using a c + + language of a windows operating system, implemented in a linux system, or implemented in an intelligent terminal using, for example, android, iOS system programming languages, implemented in processing logic based on a quantum computer, and the like.
It should be noted that descriptions of the apparatus, the device, and the system described above according to the related method embodiments may also include other embodiments, and specific implementations may refer to descriptions of corresponding method embodiments, which are not described in detail herein.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of some modules may be implemented in one or more software and/or hardware, or the modules implementing the same functions may be implemented by a plurality of sub-modules or sub-units, etc.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, devices, systems according to embodiments of the invention. It will be understood that the implementation can be by computer program instructions which can be provided to a processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
As will be appreciated by one skilled in the art, one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The above description is merely exemplary of one or more embodiments of the present disclosure and is not intended to limit the scope of one or more embodiments of the present disclosure. Various modifications and alterations to one or more embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims.
Claims (11)
1. A method of determining a public opinion category, comprising:
acquiring specified public opinion abstract information;
processing the specified public opinion abstract information by using a public opinion classification model to obtain a public opinion category corresponding to the specified public opinion abstract information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
2. A public opinion classification model training method is characterized by comprising the following steps:
acquiring target public opinion summary information; wherein, the target public opinion summary information is pre-assigned with exposure weight;
determining a feature word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information;
calculating TF-IDF values of all the characteristic words in the characteristic word vectors to obtain target abstract vectors of the target public opinion abstract information;
determining text similarity of the target public opinion summary information based on the exposure weight and the target summary vector of the target public opinion summary information; the text similarity is used for representing the public opinion category of the target public opinion summary information;
training a preset long-short term memory model by using the target public opinion abstract information and the corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
3. The method of claim 2, wherein before obtaining the target public opinion summary information, the method comprises:
acquiring a plurality of pieces of public opinion information;
extracting the abstract of each piece of public opinion information to obtain a plurality of pieces of public opinion abstract information;
and deleting the public opinion summary information of which the similarity meets the preset condition from the plurality of pieces of public opinion summary information to obtain target public opinion summary information.
4. The method of claim 2, wherein the calculating the TF-IDF value of each feature word in the feature word vector to obtain the target summary vector of the target public opinion summary information comprises:
counting the occurrence times of target feature words in the feature word vectors in the target public opinion summary information;
determining the occurrence frequency of the characteristic word with the maximum occurrence frequency in the target public opinion summary information;
calculating the word frequency of the target characteristic word according to the frequency of the target characteristic word appearing in the target public opinion summary information and the frequency of the characteristic word appearing in the target public opinion summary information with the maximum frequency;
acquiring the total amount of public opinion summary information recorded in a target database;
determining the quantity of public opinion summary information containing the target characteristic words in the target database;
calculating the inverse document frequency of the target characteristic words according to the total quantity of the public opinion summary information recorded in the target database and the quantity of the public opinion summary information containing the target characteristic words in the target database;
taking the product of the word frequency of the target characteristic word and the inverse document frequency as the TF-IDF value of the target characteristic word;
and obtaining a target abstract vector of the target public opinion abstract information based on the TF-IDF value of each feature word in the feature word vector.
5. The method of claim 4, wherein the determining the text similarity of the target public opinion summary information based on the exposure weight of the target public opinion summary information and the target summary vector comprises:
acquiring abstract vectors of the remaining public opinion abstract information in a target database;
respectively calculating text similarity of the target public opinion summary information and the residual public opinion summary information in the target database based on the exposure weight of the target public opinion summary information, the target summary vector and the summary vectors of the residual public opinion summary information in the target database to obtain a text similarity set;
and selecting the text similarity with the maximum value in the text similarity set as the text similarity of the target public opinion summary information.
6. The method of claim 5, wherein the text similarity of the target public opinion summary information and the rest public opinion summary information in the target database is calculated according to the following formula:
wherein, cos (θ)w) The method comprises the steps of representing text similarity, w representing exposure weight of target public opinion summary information, tanh (w) representing the standardized processing of the exposure weight of the target public opinion summary information, x representing a target summary vector of the target public opinion summary information, y representing a summary vector of any piece of public opinion summary information left in a target database, and the vector dimensions of x and y being the same.
7. The method of claim 2, wherein the extrinsic gating function in the neuron structure of the preset long-short term memory model is:
wherein, wiRepresenting the exposure weight of the ith item public opinion summary information, i belongs to (0.. N), N represents the number of the target public opinion summary information, and xiRepresenting input information of the current neuron, QiRepresenting the number of interaction rounds, xi-1Representing the input information of the last neuron, ht-1The output information of the last neuron is represented, and sigmoid represents an activation function.
8. An apparatus for determining public opinion categories, comprising:
the acquisition module is used for acquiring the specified public opinion abstract information;
the acquisition module is used for processing the specified public opinion summary information by using a public opinion classification model to acquire a public opinion category corresponding to the specified public opinion summary information; the public opinion classification model is obtained by training a preset long-term and short-term memory model based on public opinion abstract information and corresponding public opinion categories; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
9. The utility model provides a public opinion classification model's trainer, its characterized in that includes:
the acquisition module is used for acquiring the abstract information of the target public sentiment; wherein, the target public opinion summary information is pre-assigned with exposure weight;
the first determining module is used for determining a characteristic word vector of the target public opinion summary information; the characteristic word vector comprises a plurality of characteristic words of the target public opinion summary information;
the calculating module is used for calculating TF-IDF values of all the characteristic words in the characteristic word vectors to obtain target abstract vectors of the target public opinion abstract information;
the second determination module is used for determining the text similarity of the target public opinion abstract information based on the exposure weight and the target abstract vector of the target public opinion abstract information; the text similarity is used for representing the public opinion category of the target public opinion summary information;
the training module is used for training a preset long-short term memory model by utilizing the target public opinion abstract information and the corresponding text similarity to obtain a public opinion classification model; the neuron structure of the preset long-short term memory model comprises an external connection door, and the external connection door is used for enhancing the relation between input data and output data.
10. An apparatus for determining public opinion categories, comprising at least one processor and a memory storing computer-executable instructions that, when executed by the processor, implement the steps of the method of any one of claims 1-7.
11. A computer-readable storage medium having stored thereon computer instructions which, when executed, implement the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110544720.4A CN113515626A (en) | 2021-05-19 | 2021-05-19 | Method, device and equipment for determining public opinion category |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110544720.4A CN113515626A (en) | 2021-05-19 | 2021-05-19 | Method, device and equipment for determining public opinion category |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113515626A true CN113515626A (en) | 2021-10-19 |
Family
ID=78064517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110544720.4A Pending CN113515626A (en) | 2021-05-19 | 2021-05-19 | Method, device and equipment for determining public opinion category |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113515626A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232109A (en) * | 2019-05-17 | 2019-09-13 | 深圳市兴海物联科技有限公司 | A kind of Internet public opinion analysis method and system |
| WO2019205318A1 (en) * | 2018-04-25 | 2019-10-31 | 平安科技（深圳）有限公司 | Public opinion information classification method and apparatus, computer device, and storage medium |
| WO2019227710A1 (en) * | 2018-05-31 | 2019-12-05 | 平安科技（深圳）有限公司 | Network public opinion analysis method and apparatus, and computer-readable storage medium |
| CN110750622A (en) * | 2019-09-17 | 2020-02-04 | 南京理工大学 | Financial event discovery method based on big data |
| CN111538931A (en) * | 2020-03-27 | 2020-08-14 | 中国平安财产保险股份有限公司 | Big data-based public opinion monitoring method and device, computer equipment and medium |
| CN111694959A (en) * | 2020-06-08 | 2020-09-22 | 谢沛然 | Network public opinion multi-mode emotion recognition method and system based on facial expressions and text information |
| CN111831824A (en) * | 2020-07-16 | 2020-10-27 | 民生科技有限责任公司 | Public opinion positive and negative face classification method |
| CN112749280A (en) * | 2021-01-18 | 2021-05-04 | 杭州安恒信息技术股份有限公司 | Internet public opinion classification method, device, electronic device and storage medium |
-
2021
- 2021-05-19 CN CN202110544720.4A patent/CN113515626A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019205318A1 (en) * | 2018-04-25 | 2019-10-31 | 平安科技（深圳）有限公司 | Public opinion information classification method and apparatus, computer device, and storage medium |
| WO2019227710A1 (en) * | 2018-05-31 | 2019-12-05 | 平安科技（深圳）有限公司 | Network public opinion analysis method and apparatus, and computer-readable storage medium |
| CN110232109A (en) * | 2019-05-17 | 2019-09-13 | 深圳市兴海物联科技有限公司 | A kind of Internet public opinion analysis method and system |
| CN110750622A (en) * | 2019-09-17 | 2020-02-04 | 南京理工大学 | Financial event discovery method based on big data |
| CN111538931A (en) * | 2020-03-27 | 2020-08-14 | 中国平安财产保险股份有限公司 | Big data-based public opinion monitoring method and device, computer equipment and medium |
| CN111694959A (en) * | 2020-06-08 | 2020-09-22 | 谢沛然 | Network public opinion multi-mode emotion recognition method and system based on facial expressions and text information |
| CN111831824A (en) * | 2020-07-16 | 2020-10-27 | 民生科技有限责任公司 | Public opinion positive and negative face classification method |
| CN112749280A (en) * | 2021-01-18 | 2021-05-04 | 杭州安恒信息技术股份有限公司 | Internet public opinion classification method, device, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694225B (en) | Image searching method, feature vector generating method and device and electronic equipment | |
| US11645554B2 (en) | Method and apparatus for recognizing a low-quality article based on artificial intelligence, device and medium | |
| Yu et al. | Attention-based convolutional approach for misinformation identification from massive and noisy microblog posts | |
| CN111222305A (en) | Information structuring method and device | |
| JP2022141931A (en) | Method and device for training living body detection model, method and apparatus for living body detection, electronic apparatus, storage medium, and computer program | |
| CN110175851B (en) | Cheating behavior detection method and device | |
| CN112307351A (en) | Model training and recommending method, device and equipment for user behavior | |
| WO2020238353A1 (en) | Data processing method and apparatus, storage medium, and electronic apparatus | |
| CN110619064A (en) | Case studying and judging method and device based on deep learning | |
| Ma et al. | Improving rumor detection by promoting information campaigns with transformer-based generative adversarial learning | |
| CN111061837A (en) | Topic identification method, device, equipment and medium | |
| Aziguli et al. | A robust text classifier based on denoising deep neural network in the analysis of big data | |
| CN108229170A (en) | Utilize big data and the software analysis method and device of neural network | |
| CN113297351A (en) | Text data labeling method and device, electronic equipment and storage medium | |
| CN112966072A (en) | Case prediction method and device, electronic device and storage medium | |
| CN117076688A (en) | Knowledge question-answering method and device based on domain knowledge graph and electronic equipment | |
| CN113569118B (en) | Self-media pushing method, device, computer equipment and storage medium | |
| CN115062709A (en) | Model optimization method, device, equipment, storage medium and program product | |
| Hossny et al. | Enhancing keyword correlation for event detection in social networks using SVD and k-means: Twitter case study | |
| CN110019763B (en) | Text filtering method, system, equipment and computer readable storage medium | |
| CN110069558A (en) | Data analysing method and terminal device based on deep learning | |
| CN112270189A (en) | Question type analysis node generation method, question type analysis node generation system and storage medium | |
| CN117033626A (en) | Text auditing method, device, equipment and storage medium | |
| Mengash et al. | Search and Rescue Optimization with Machine Learning Enabled Cybersecurity Model. | |
| Li et al. | Do we really need more training data for object localization |
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 |