CN110134938A - Comment and analysis method and device - Google Patents
Comment and analysis method and device Download PDFInfo
- Publication number
- CN110134938A CN110134938A CN201810134597.7A CN201810134597A CN110134938A CN 110134938 A CN110134938 A CN 110134938A CN 201810134597 A CN201810134597 A CN 201810134597A CN 110134938 A CN110134938 A CN 110134938A
- Authority
- CN
- China
- Prior art keywords
- comment
- viewpoint
- word segmentation
- item
- segmentation result
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 52
- 230000011218 segmentation Effects 0.000 claims abstract description 112
- 206010028916 Neologism Diseases 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims description 50
- 238000005520 cutting process Methods 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 18
- 239000000284 extract Substances 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000007711 solidification Methods 0.000 claims description 9
- 230000008023 solidification Effects 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 6
- 230000008451 emotion Effects 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 30
- 238000005516 engineering process Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 241000406668 Loxodonta cyclotis Species 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000012092 media component Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to comment and analysis method and device.This method comprises: extracting first group of neologisms from each item comment for specified object；According to first group of neologisms, word segmentation processing is carried out to each item comment for the specified object, obtains the word segmentation result commented on for each item of the specified object；For any one comment for the specified object, by the viewpoint part in the word segmentation result in the word segmentation result input prediction model of the comment, obtaining the corresponding viewpoint classification of the comment and the comment；According to the viewpoint part in the word segmentation result of the corresponding comment of each viewpoint classification, determine the specified object in the Sentiment orientation of each viewpoint classification.The disclosure can carry out fine-grained sentiment analysis to specified object, it is accurate to determine specified object in the Sentiment orientation of each viewpoint classification, business personnel can be helped to understand users to the comment angle of specified object and pass judgement on attitude, sufficiently excavate the value of comment information.
Description
Technical field
This disclosure relates to field of computer technology more particularly to a kind of comment and analysis method and device.
Background technique
As social networks, the continuous of mobile Internet are popularized, the cost of people's release information is lower and lower, more and more
User be happy to share the viewpoint of oneself and the comment for personage, event, product on the internet.These comments reflect
People have great significance for the analysis of public opinion and the prediction based on big data for the viewpoint and Sentiment orientation of things.
Therefore, sentiment analysis technology is come into being.Sentiment analysis is also referred to as opining mining, viewpoint analysis, and the purpose of sentiment analysis is
The viewpoint that user's expression is excavated from text, usually indicates (for example, forward direction, negative sense, neutrality etc.) with feeling polarities.Traditional
Sentiment analysis is primarily upon the whole feeling polarities of comment, however often granularity is thicker for whole feeling polarities, Yong Huwu
Method judges whether current production has good reputation on some attribute oneself paid close attention to according to whole feeling polarities.One
The preferable product of a entirety public praise not necessarily has good reputation on each attribute, and different users is to generic
Often there is also certain differences for the attribute of product concern.Therefore, how to carry out fine-grained sentiment analysis to product becomes urgently
Problem to be solved.
Summary of the invention
In view of this, the present disclosure proposes a kind of comment and analysis method and devices.
According to the one side of the disclosure, a kind of comment and analysis method is provided, comprising:
First group of neologisms is extracted from each item comment for specified object；
According to first group of neologisms, word segmentation processing is carried out to each item comment for the specified object, is directed to
The word segmentation result of each item comment of the specified object；
For any one comment for the specified object, by the word segmentation result input prediction model of the comment
In, obtain the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment；
According to the viewpoint part in the word segmentation result of the corresponding comment of each viewpoint classification, determine the specified object each
The Sentiment orientation of a viewpoint classification.
In one possible implementation, described before in the word segmentation result input prediction model by the comment
Method further include:
For any one training object that training data is concentrated, extracted from each item comment for the trained object
Second group of neologisms；
According to second group of neologisms, word segmentation processing is carried out to each item comment for the trained object, is directed to
The word segmentation result of each item comment of the trained object；
For any one comment for the trained object, according to the corresponding viewpoint classification of the comment, Yi Jisuo
Viewpoint part in the word segmentation result of commentary opinion is labeled each word in the word segmentation result of the comment, obtains described
Comment on corresponding annotation results；
The corresponding annotation results training prediction model is commented on according to each item for the trained object.
In one possible implementation, for any one comment for the trained object, according to institute's commentary
By the viewpoint part in corresponding viewpoint classification and the word segmentation result of the comment, in the word segmentation result of the comment
Each word is labeled, and obtains the corresponding annotation results of the comment, comprising:
It will be described according to the corresponding viewpoint classification of the comment for any one comment for the trained object
Each word in the word segmentation result of comment be labeled as the beginning of viewpoint part, the centre of viewpoint part, viewpoint part ending or
Person is not belonging to viewpoint part, obtains the corresponding annotation results of the comment.
In one possible implementation, according to the viewpoint portion in the word segmentation result of the corresponding comment of each viewpoint classification
Point, determine the specified object in the Sentiment orientation of each viewpoint classification, comprising:
For any one viewpoint classification, according to the viewpoint portion in the word segmentation result of the corresponding comment of the viewpoint classification
Point, determine that each item comments on corresponding viewpoint and extracts result；
Each item is commented on into corresponding viewpoint extraction result and is converted to two-dimensional matrix；
The two-dimensional matrix is inputted in convolutional neural networks, and is mentioned by the maximum pond layer of the convolutional neural networks
Take the matching characteristic of all convolution kernels；
Determine the specified object in the Sentiment orientation of the viewpoint classification according to the matching characteristic.
In one possible implementation, first group of neologisms is extracted from each item comment for specified object, comprising:
Adjacent text cutting is carried out to each item comment for specified object, obtains cutting result；
According to the solidification degree and freedom degree of the cutting result, neologisms are extracted from each item comment for specified object.
According to another aspect of the present disclosure, a kind of comment and analysis device is provided, comprising:
First extraction module, for extracting first group of neologisms from each item comment for specified object；
First participle module, for commenting on each item for the specified object and carrying out according to first group of neologisms
Word segmentation processing obtains the word segmentation result commented on for each item of the specified object；
Prediction module, for any one comment for being directed to the specified object, by the word segmentation result of the comment
In input prediction model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained；
Determining module determines institute for the viewpoint part in the word segmentation result according to the corresponding comment of each viewpoint classification
Specified object is stated in the Sentiment orientation of each viewpoint classification.
In one possible implementation, described device further include:
Second extraction module, any one training object for being concentrated for training data, from for the training pair
Second group of neologisms is extracted in each item comment of elephant；
Second word segmentation module, for commenting on each item for the trained object and carrying out according to second group of neologisms
Word segmentation processing obtains the word segmentation result commented on for each item of the trained object；
Labeling module, for commenting on corresponding sight according to described for any one comment for the trained object
Viewpoint part in point classification and the word segmentation result of the comment, carries out each word in the word segmentation result of the comment
Mark obtains the corresponding annotation results of the comment；
Training module, for commenting on the corresponding annotation results training prediction according to each item for the trained object
Model.
In one possible implementation, the labeling module is used for:
It will be described according to the corresponding viewpoint classification of the comment for any one comment for the trained object
Each word in the word segmentation result of comment be labeled as the beginning of viewpoint part, the centre of viewpoint part, viewpoint part ending or
Person is not belonging to viewpoint part, obtains the corresponding annotation results of the comment.
In one possible implementation, the determining module includes:
First determines submodule, is used for for any one viewpoint classification, according to the corresponding comment of the viewpoint classification
Viewpoint part in word segmentation result determines that each item comments on corresponding viewpoint and extracts result；
Transform subblock is converted to two-dimensional matrix for each item to be commented on corresponding viewpoint extraction result；
First extracting sub-module for inputting the two-dimensional matrix in convolutional neural networks, and passes through the convolution mind
Maximum pond layer through network extracts the matching characteristic of all convolution kernels；
Second determines submodule, for determining the specified object in the feelings of the viewpoint classification according to the matching characteristic
Sense tendency.
In one possible implementation, first extraction module includes:
Submodule is cut, for carrying out adjacent text cutting to each item comment for specified object, obtains cutting result；
Second extracting sub-module, for the solidification degree and freedom degree according to the cutting result, from for specified object
Neologisms are extracted in each item comment.
According to another aspect of the present disclosure, a kind of comment and analysis device is provided, comprising: processor；It is handled for storage
The memory of device executable instruction；Wherein, the processor is configured to executing the above method.
According to another aspect of the present disclosure, a kind of non-volatile computer readable storage medium storing program for executing is provided, is stored thereon with
Computer program instructions, wherein the computer program instructions realize the above method when being executed by processor.
The comment and analysis method and device of all aspects of this disclosure from each item comment for specified object by extracting
First group of neologisms carries out word segmentation processing to each item comment for specified object, obtains for specified pair according to first group of neologisms
The word segmentation result of the comment is inputted any one comment for specified object by the word segmentation result of each item comment of elephant
In prediction model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained, and according to each
Viewpoint part in the word segmentation result of the corresponding comment of a viewpoint classification determines that specified object inclines in the emotion of each viewpoint classification
To thus, it is possible to carry out fine-grained sentiment analysis, the accurate feelings for specifying object in each viewpoint classification that determine to specified object
Sense tendency, can help business personnel to understand users to the comment angle of specified object and pass judgement on attitude, sufficiently excavate and comment
By the value of information.
According to below with reference to the accompanying drawings to detailed description of illustrative embodiments, the other feature and aspect of the disclosure will become
It is clear.
Detailed description of the invention
Comprising in the description and constituting the attached drawing of part of specification and specification together illustrates the disclosure
Exemplary embodiment, feature and aspect, and for explaining the principles of this disclosure.
Fig. 1 shows the flow chart of the comment and analysis method according to one embodiment of the disclosure.
Fig. 2 shows determine to comment on corresponding sight by prediction model in the comment and analysis method according to one embodiment of the disclosure
Point classification, and the schematic diagram of the viewpoint part in the word segmentation result of comment.
Fig. 3 shows an illustrative flow chart of the comment and analysis method according to one embodiment of the disclosure.
Fig. 4 shows an illustrative flow chart of the comment and analysis method and step S14 according to one embodiment of the disclosure.
Fig. 5, which is shown, determines specified object in each viewpoint classification in the comment and analysis method according to one embodiment of the disclosure
The schematic diagram of Sentiment orientation.
Fig. 6 a to Fig. 6 c shows movie or television play class video in the comment and analysis method according to one embodiment of the disclosure and exists
The schematic diagram of the Sentiment orientation of each viewpoint classification.
Fig. 7 a and Fig. 7 b show in the comment and analysis method according to one embodiment of the disclosure variety class video in each viewpoint
The schematic diagram of the Sentiment orientation of classification.
Fig. 8 shows an illustrative flow chart of the comment and analysis method and step S11 according to one embodiment of the disclosure.
Fig. 9 shows the block diagram of the comment and analysis device according to one embodiment of the disclosure.
Figure 10 shows an illustrative block diagram of the comment and analysis device according to one embodiment of the disclosure.
Figure 11 is a kind of block diagram of device 800 for comment and analysis shown according to an exemplary embodiment.
Figure 12 is a kind of block diagram of device 1900 for comment and analysis shown according to an exemplary embodiment.
Specific embodiment
Various exemplary embodiments, feature and the aspect of the disclosure are described in detail below with reference to attached drawing.It is identical in attached drawing
Appended drawing reference indicate element functionally identical or similar.Although the various aspects of embodiment are shown in the attached drawings, remove
It non-specifically points out, it is not necessary to attached drawing drawn to scale.
Dedicated word " exemplary " means " being used as example, embodiment or illustrative " herein.Here as " exemplary "
Illustrated any embodiment should not necessarily be construed as preferred or advantageous over other embodiments.
In addition, giving numerous details in specific embodiment below to better illustrate the disclosure.
It will be appreciated by those skilled in the art that without certain details, the disclosure equally be can be implemented.In some instances, for
Method, means, element and circuit well known to those skilled in the art are not described in detail, in order to highlight the purport of the disclosure.
Fig. 1 shows the flow chart of the comment and analysis method according to one embodiment of the disclosure.As shown in Figure 1, this method includes
Step S11 to step S14.
In step s 11, first group of neologisms is extracted from each item comment for specified object.
Wherein, specified object can refer to any object for needing to carry out comment and analysis.For example, specified object can be view
Frequently, audio, news, personage, event or product etc..
In the present embodiment, it can be commented using new words extraction technology in the related technology from for specified all of object
First group of neologisms is extracted in.Wherein, first group of neologisms can the corresponding neologisms of specified object.
In step s 12, according to first group of neologisms, word segmentation processing is carried out to each item comment for specified object, is obtained
For the word segmentation result of each item comment of specified object.
In one possible implementation, can using first group of neologisms as the dictionary segmented to specified object,
Word segmentation processing is carried out to each item comment for specified object.
It in one possible implementation, can before carrying out word segmentation processing to each item comment for specified object
To be pre-processed to each item comment for specified object, to improve the accuracy and efficiency of comment and analysis.
As an example of the implementation, carrying out pretreatment to each item comment for specified object may include:
Delete the designated character in each item comment for specified object.For example, the forwarding character in the comment such as microblogging can be deleted.
As another example of the implementation, carrying out pretreatment to each item comment for specified object be can wrap
It includes: the complex form of Chinese characters in each item comment for specified object is converted into simplified Chinese character.
As another example of the implementation, carrying out pretreatment to each item comment for specified object be can wrap
It includes: deleting the duplicate comment for specified object.
In step s 13, for any one comment for specified object, by the word segmentation result input prediction of the comment
In model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained.
In the present embodiment, prediction model can be used for predicting that each item comments on corresponding viewpoint classification and the comment of each item
Word segmentation result in viewpoint part.For example, whether each word that can be predicted in the word segmentation result of each item comment belongs to sight
Point part can predict the word and belong to the beginning of viewpoint part, viewpoint portion in the case where some word belongs to viewpoint part
The ending of the centre or viewpoint part divided.
Fig. 2 shows determine to comment on corresponding sight by prediction model in the comment and analysis method according to one embodiment of the disclosure
Point classification, and the schematic diagram of the viewpoint part in the word segmentation result of comment.As shown in Fig. 2, bilstm+ can be used
Softmax structured training prediction model.Wherein it is possible to using 3 layers of bilstm structure.
In step S14, according to the viewpoint part in the word segmentation result of the corresponding comment of each viewpoint classification, determine specified
Sentiment orientation of the object in each viewpoint classification.
The present embodiment is by extracting first group of neologisms from each item comment for specified object, according to first group of neologisms,
Word segmentation processing is carried out to each item comment for specified object, obtains the word segmentation result of each item comment for specified object, it is right
In any one comment for specified object, it is corresponding that the comment in the word segmentation result input prediction model of the comment, will be obtained
Viewpoint classification and the comment word segmentation result in viewpoint part, and according to the corresponding comment of each viewpoint classification point
Viewpoint part in word result, determine specified object in the Sentiment orientation of each viewpoint classification, thus, it is possible to specified object into
The fine-grained sentiment analysis of row is accurate to determine that specified object in the Sentiment orientation of each viewpoint classification, help business personnel
Users are understood to the comment angle of specified object and pass judgement on attitude, sufficiently excavate the value of comment information.
Fig. 3 shows an illustrative flow chart of the comment and analysis method according to one embodiment of the disclosure.As shown in figure 3,
This method may include step S31 to step S38.
In step S31, for any one training object that training data is concentrated, commented from each item for training object
Second group of neologisms is extracted in.
Wherein, training data concentration may include a large amount of training objects, and training object can be video, audio, news, people
Object, event or product etc., are not limited thereto.
In the present embodiment, it can be commented using new words extraction technology in the related technology from each item for training object
Second group of neologisms is extracted in.Wherein, second group of neologisms can refer to the corresponding neologisms of trained object.
In step s 32, according to second group of neologisms, word segmentation processing is carried out to each item comment for training object, is obtained
For the word segmentation result of each item comment of training object.
In one possible implementation, can using second group of neologisms as to the dictionary that segments of training object,
Word segmentation processing is carried out to each item comment for training object.
It in one possible implementation, can before carrying out word segmentation processing to each item comment for training object
To be pre-processed to each item comment for training object, to improve the accuracy and efficiency of comment and analysis.
As an example of the implementation, carrying out pretreatment to each item comment for training object may include:
Delete the designated character in each item comment for training object.For example, the forwarding character in the comment such as microblogging can be deleted.
As another example of the implementation, carrying out pretreatment to each item comment for training object be can wrap
It includes: the complex form of Chinese characters in each item comment for training object is converted into simplified Chinese character.
As another example of the implementation, carrying out pretreatment to each item comment for training object be can wrap
It includes: deleting the duplicate comment for training object.
In step S33, for for any one of object comment of training, according to the corresponding viewpoint classification of the comment,
And the viewpoint part in the word segmentation result of the comment, each word in the word segmentation result of the comment is labeled, is somebody's turn to do
Comment on corresponding annotation results.
In one possible implementation, corresponding according to the comment for any one comment for training object
Viewpoint classification and the comment word segmentation result in viewpoint part, in the word segmentation result of the comment each word carry out
Mark, obtains the corresponding annotation results of the comment, comprising: for any one comment for training object, according to the comment
Each word in the word segmentation result of the comment is labeled as the beginning of viewpoint part, in viewpoint part by corresponding viewpoint classification
Between, the ending of viewpoint part or be not belonging to viewpoint part, obtain the corresponding annotation results of the comment.
In step S34, corresponding annotation results training prediction model is commented on according to each item for training object.
For example, a certain item comment of a certain trained object is " being really delithted with the artistic skills of female master ", the participle knot of the comment
Fruit be " it is genuine t very t like t female it is main t t artistic skills ".Viewpoint part in the word segmentation result be " like t female it is main t drill
Skill ".Each word in the word segmentation result is labeled, obtain the corresponding annotation results of the comment be " O tO tS (performer-
B) tS (performer-M) tO tS (performer-E) ".Wherein, " O " indicates that the word is not belonging to viewpoint part, " S (performer-B) ", " S
" S " in (performer-M) " and " S (performer-E) " indicates that the word belongs to viewpoint part, " S (performer-B) ", " S (performer-M) " and
" performer " in " S (performer-E) " indicates that the corresponding viewpoint classification in the viewpoint part is performer's class, " B " in " S (performer-B) "
Indicate the beginning of the viewpoint part, " M " in " S (performer-M) " indicates the centre of the viewpoint part, in " S (performer-E) "
" E " indicates the ending of the viewpoint part.By word segmentation result " it is genuine t very t like t female it is main t t artistic skills " be converted to
Word2vec data obtain the corresponding word2vec data of word segmentation result.Wherein, the corresponding word2vec data packet of word segmentation result
Include " genuine " corresponding word2vec data, " very " corresponding word2vec data, " liking " corresponding word2vec data,
" female master " corresponding word2vec data, " " corresponding word2vec data, and " artistic skills " corresponding word2vec data.
By annotation results " O tO tS (performer-B) tS (performer-M) tO tS (performer-E) " be converted to for disaggregated model
Onehot coded data obtains the corresponding onehot coded data of annotation results.Wherein, the corresponding onehot coding of annotation results
Data include " O " corresponding onehot coded data, and " O " corresponding onehot coded data, " S (performer-B) " is corresponding
Onehot coded data, " S (performer-M) " corresponding onehot coded data, " O " corresponding onehot coded data, and " S
The corresponding onehot coded data of (performer-E) ".Using the corresponding word2vec data of word segmentation result as the input of prediction model,
Using the corresponding onehot coded data of annotation results as the output of prediction model, prediction model can be trained.
In step s 35, first group of neologisms is extracted from each item comment for specified object.
Wherein, the description to step S11 is seen above to step S35.
In step S36, according to first group of neologisms, word segmentation processing is carried out to each item comment for specified object, is obtained
For the word segmentation result of each item comment of specified object.
Wherein, the description to step S12 is seen above to step S36.
In step S37, for any one comment for specified object, by the word segmentation result input prediction of the comment
In model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained.
Wherein, the description to step S13 is seen above to step S37.
In step S38, according to the viewpoint part in the word segmentation result of the corresponding comment of each viewpoint classification, determine specified
Sentiment orientation of the object in each viewpoint classification.
Wherein, the description to step S14 is seen above to step S38.
Fig. 4 shows an illustrative flow chart of the comment and analysis method and step S14 according to one embodiment of the disclosure.Such as figure
Shown in 4, step S14 may include step S141 to step S144.
In step s 141, for any one viewpoint classification, according to the word segmentation result of the corresponding comment of viewpoint classification
In viewpoint part, determine that each item comments on corresponding viewpoint and extracts result.
For example, the corresponding viewpoint of a certain comment " being really delithted with the artistic skills of female master " extract result be " O tO tS (performer-
B) tS (performer-M) tO tS (performer-E) ".
In step S142, each item is commented on into corresponding viewpoint extraction result and is converted to two-dimensional matrix.
It in one possible implementation, can should by Text-CNN algorithm for any one viewpoint classification
It is two-dimensional matrix that the viewpoint of the corresponding each item comment of viewpoint classification, which extracts result by word2vec model conversion,.
In step S143, two-dimensional matrix is inputted in convolutional neural networks, and passes through the maximum pond of convolutional neural networks
Change the matching characteristic that layer extracts all convolution kernels.
In step S144, determine specified object in the Sentiment orientation of the viewpoint classification according to matching characteristic.
In the present embodiment, convolutional neural networks can carry out the ratio point of Sentiment orientation to the syntactic analysis result of extraction
Analysis, to obtain specified object in the Sentiment orientation of the viewpoint classification.
It in one possible implementation, can be by full connection after the matching characteristic for obtaining all convolution kernels
Layer and softmax obtain specified object in the Sentiment orientation of the viewpoint classification.
Fig. 5, which is shown, determines specified object in each viewpoint classification in the comment and analysis method according to one embodiment of the disclosure
The schematic diagram of Sentiment orientation.As shown in figure 5, can determine matching characteristic according to the maximum value after each convolution nuclear convolution.It is specified
Object can be positive, negative sense or neutrality in the Sentiment orientation of each viewpoint classification.
Fig. 6 a to Fig. 6 c shows movie or television play class video in the comment and analysis method according to one embodiment of the disclosure and exists
The schematic diagram of the Sentiment orientation of each viewpoint classification.Wherein, it is " whole in viewpoint classification to show movie or television play class video by Fig. 6 a
The schematic diagram of the Sentiment orientation of evaluation " and " performer "；Fig. 6 b show movie or television play class video in viewpoint classification " plot " and
The schematic diagram of the Sentiment orientation of " production "；Fig. 6 c shows movie or television play class video in viewpoint classification " visual sound effect " and " field
The schematic diagram of the Sentiment orientation in face ".
Fig. 7 a and Fig. 7 b show in the comment and analysis method according to one embodiment of the disclosure variety class video in each viewpoint
The schematic diagram of the Sentiment orientation of classification.Wherein, Fig. 7 a shows variety class video in viewpoint classification " overall evaluation " and " personage "
The schematic diagram of Sentiment orientation；Fig. 7 b shows variety class video showing in viewpoint classification " link setting " and the Sentiment orientation of " production "
It is intended to.
Fig. 8 shows an illustrative flow chart of the comment and analysis method and step S11 according to one embodiment of the disclosure.Such as figure
Shown in 8, step S11 may include step S111 and step S112.
In step S111, adjacent text cutting is carried out to each item comment for specified object, obtains cutting result.
In one possible implementation, the OffsetAttribute class of Lucene TokenStream can be used,
Adjacent text cutting is carried out to the comment for specified object, obtains cutting result.
In step S112, according to the solidification degree and freedom degree of cutting result, from each item comment for specified object
Extract neologisms.
In the present embodiment, cutting result can be calculated according to the method for calculating solidification degree and freedom degree in the related technology
In each word solidification degree and freedom degree.
In one possible implementation, first threshold can be greater than in the solidification degree of the word A in cutting result, and certainly
In the case where being greater than second threshold by degree, word A is determined as neologisms.
Fig. 9 shows the block diagram of the comment and analysis device according to one embodiment of the disclosure.As shown in figure 9, the device includes:
One extraction module 91, for extracting first group of neologisms from each item comment for specified object；First participle module 92, is used for
According to first group of neologisms, word segmentation processing is carried out to each item comment for specified object, obtains commenting for each item of specified object
The word segmentation result of opinion；Prediction module 93, for any one comment for being directed to specified object, by the word segmentation result of the comment
In input prediction model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained；It determines
Module 94 determines specified object each for the viewpoint part in the word segmentation result according to the corresponding comment of each viewpoint classification
The Sentiment orientation of a viewpoint classification.
Figure 10 shows an illustrative block diagram of the comment and analysis device according to one embodiment of the disclosure.It is as shown in Figure 10:
In one possible implementation, the device further include: the second extraction module 95, for for training dataset
In any one training object, from for training object each item comment in extract second group of neologisms；Second word segmentation module 96,
For carrying out word segmentation processing to each item comment for training object, obtaining for each of training object according to second group of neologisms
The word segmentation result of item comment；Labeling module 97, for being corresponded to according to the comment for any one comment for training object
Viewpoint classification and the comment word segmentation result in viewpoint part, in the word segmentation result of the comment each word carry out
Mark, obtains the corresponding annotation results of the comment；Training module 98, for corresponding according to each item comment for training object
Annotation results train prediction model.
In one possible implementation, labeling module 97 is used for: for being commented on for any one of training object,
According to the corresponding viewpoint classification of the comment, each word in the word segmentation result of the comment is labeled as the beginning of viewpoint part, is seen
The ending of the centre, viewpoint part of point part is not belonging to viewpoint part, obtains the corresponding annotation results of the comment.
In one possible implementation, determining module 94 includes: the first determining submodule 941, for for any
One viewpoint classification determines that each item comment corresponds to according to the viewpoint part in the word segmentation result of the corresponding comment of viewpoint classification
Viewpoint extract result；Transform subblock 942 is converted to two-dimensional matrix for each item to be commented on corresponding viewpoint extraction result；
First extracting sub-module 943 for inputting two-dimensional matrix in convolutional neural networks, and passes through the maximum pond of convolutional neural networks
Change the matching characteristic that layer extracts all convolution kernels；Second determines submodule 944, for determining that specified object exists according to matching characteristic
The Sentiment orientation of the viewpoint classification.
In one possible implementation, the first extraction module 91 includes: cutting submodule 911, for for finger
Each item comment for determining object carries out adjacent text cutting, obtains cutting result；Second extracting sub-module 912, for according to cutting
As a result solidification degree and freedom degree extract neologisms from each item comment for specified object.
The present embodiment is by extracting first group of neologisms from each item comment for specified object, according to first group of neologisms,
Word segmentation processing is carried out to each item comment for specified object, obtains the word segmentation result of each item comment for specified object, it is right
In any one comment for specified object, it is corresponding that the comment in the word segmentation result input prediction model of the comment, will be obtained
Viewpoint classification and the comment word segmentation result in viewpoint part, and according to the corresponding comment of each viewpoint classification point
Viewpoint part in word result, determine specified object in the Sentiment orientation of each viewpoint classification, thus, it is possible to specified object into
The fine-grained sentiment analysis of row is accurate to determine that specified object in the Sentiment orientation of each viewpoint classification, help business personnel
Users are understood to the comment angle of specified object and pass judgement on attitude, sufficiently excavate the value of comment information.
Figure 11 is a kind of block diagram of device 800 for comment and analysis shown according to an exemplary embodiment.For example, dress
Setting 800 can be mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical treatment
Equipment, body-building equipment, personal digital assistant etc..
Referring to Fig.1 1, device 800 may include following one or more components: processing component 802, memory 804, power supply
Component 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 802 may include that one or more processors 820 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more modules, just
Interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, it is more to facilitate
Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in device 800.These data are shown
Example includes the instruction of any application or method for operating on device 800, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 may include power management system
System, one or more power supplys and other with for device 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 808 includes a front camera and/or rear camera.When device 800 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when device 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 804 or via communication set
Part 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor module 814 can detecte the state that opens/closes of device 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor module 814 can be with 800 1 components of detection device 800 or device
Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800
Temperature change.Sensor module 814 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 814 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating
The memory 804 of machine program instruction, above-mentioned computer program instructions can be executed above-mentioned to complete by the processor 820 of device 800
Method.
Figure 12 is a kind of block diagram of device 1900 for comment and analysis shown according to an exemplary embodiment.For example,
Device 1900 may be provided as a server.Referring to Fig.1 2, it further comprises one that device 1900, which includes processing component 1922,
A or multiple processors and memory resource represented by a memory 1932, can be by processing component 1922 for storing
The instruction of execution, such as application program.The application program stored in memory 1932 may include one or more every
One corresponds to the module of one group of instruction.In addition, processing component 1922 is configured as executing instruction, to execute the above method.
Device 1900 can also include that a power supply module 1926 be configured as the power management of executive device 1900, and one
Wired or wireless network interface 1950 is configured as device 1900 being connected to network and input and output (I/O) interface
1958.Device 1900 can be operated based on the operating system for being stored in memory 1932, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
In the exemplary embodiment, a kind of non-volatile computer readable storage medium storing program for executing is additionally provided, for example including calculating
The memory 1932 of machine program instruction, above-mentioned computer program instructions can be executed by the processing component 1922 of device 1900 to complete
The above method.
The disclosure can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the disclosure.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing disclosure operation can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the disclosure
Face.
Referring herein to according to the flow chart of the method, apparatus (system) of the embodiment of the present disclosure and computer program product and/
Or block diagram describes various aspects of the disclosure.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the disclosure
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.
The presently disclosed embodiments is described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or technological improvement to the technology in market for best explaining each embodiment, or lead this technology
Other those of ordinary skill in domain can understand each embodiment disclosed herein.
Claims (12)
1. a kind of comment and analysis method characterized by comprising
First group of neologisms is extracted from each item comment for specified object；
According to first group of neologisms, word segmentation processing is carried out to each item comment for the specified object, is obtained for described
The word segmentation result of each item comment of specified object；
For any one comment for the specified object, by the word segmentation result input prediction model of the comment, obtain
To the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment；
According to the viewpoint part in the word segmentation result of the corresponding comment of each viewpoint classification, determine the specified object in each sight
The Sentiment orientation of point classification.
2. the method according to claim 1, wherein in the word segmentation result input prediction model by the comment
Before, the method also includes:
For any one training object that training data is concentrated, second is extracted from each item comment for the trained object
Group neologisms；
According to second group of neologisms, word segmentation processing is carried out to each item comment for the trained object, is obtained for described
The word segmentation result of each item comment of training object；
For any one comment for the trained object, according to the corresponding viewpoint classification of the comment and institute's commentary
Viewpoint part in the word segmentation result of opinion is labeled each word in the word segmentation result of the comment, obtains the comment
Corresponding annotation results；
The corresponding annotation results training prediction model is commented on according to each item for the trained object.
3. according to the method described in claim 2, it is characterized in that, for for any one of trained object comment,
According to the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment, the comment is divided
Each word in word result is labeled, and obtains the corresponding annotation results of the comment, comprising:
For any one comment for the trained object, according to the corresponding viewpoint classification of the comment, by the comment
Word segmentation result in each word be labeled as the beginning of viewpoint part, the centre of viewpoint part, the ending of viewpoint part or not
Belong to viewpoint part, obtains the corresponding annotation results of the comment.
4. the method according to claim 1, wherein according to the word segmentation result of the corresponding comment of each viewpoint classification
In viewpoint part, determine the specified object in the Sentiment orientation of each viewpoint classification, comprising:
For any one viewpoint classification, according to the viewpoint part in the word segmentation result of the corresponding comment of the viewpoint classification, really
Fixed each item comments on corresponding viewpoint and extracts result；
Each item is commented on into corresponding viewpoint extraction result and is converted to two-dimensional matrix；
The two-dimensional matrix is inputted in convolutional neural networks, and institute is extracted by the maximum pond layer of the convolutional neural networks
There is the matching characteristic of convolution kernel；
Determine the specified object in the Sentiment orientation of the viewpoint classification according to the matching characteristic.
5. the method according to claim 1, wherein extracting first group from each item comment for specified object
Neologisms, comprising:
Adjacent text cutting is carried out to each item comment for specified object, obtains cutting result；
According to the solidification degree and freedom degree of the cutting result, neologisms are extracted from each item comment for specified object.
6. a kind of comment and analysis device characterized by comprising
First extraction module, for extracting first group of neologisms from each item comment for specified object；
First participle module, for being segmented to each item comment for the specified object according to first group of neologisms
Processing obtains the word segmentation result commented on for each item of the specified object；
Prediction module, for for any one comment for the specified object, the word segmentation result of the comment to be inputted
In prediction model, the viewpoint part in the corresponding viewpoint classification of the comment and the word segmentation result of the comment is obtained；
Determining module determines the finger for the viewpoint part in the word segmentation result according to the corresponding comment of each viewpoint classification
Object is determined in the Sentiment orientation of each viewpoint classification.
7. device according to claim 6, which is characterized in that described device further include:
Second extraction module, any one training object for being concentrated for training data, from for the trained object
Second group of neologisms is extracted in each item comment；
Second word segmentation module, for being segmented to each item comment for the trained object according to second group of neologisms
Processing obtains the word segmentation result commented on for each item of the trained object；
Labeling module, for commenting on corresponding viewpoint class according to described for any one comment for the trained object
Viewpoint part not and in the word segmentation result of the comment is labeled each word in the word segmentation result of the comment,
Obtain the corresponding annotation results of the comment；
Training module, for commenting on the corresponding annotation results training prediction mould according to each item for the trained object
Type.
8. device according to claim 7, which is characterized in that the labeling module is used for:
For any one comment for the trained object, according to the corresponding viewpoint classification of the comment, by the comment
Word segmentation result in each word be labeled as the beginning of viewpoint part, the centre of viewpoint part, the ending of viewpoint part or not
Belong to viewpoint part, obtains the corresponding annotation results of the comment.
9. device according to claim 6, which is characterized in that the determining module includes:
First determines submodule, is used for for any one viewpoint classification, according to the participle of the corresponding comment of the viewpoint classification
As a result the viewpoint part in determines that each item comments on corresponding viewpoint and extracts result；
Transform subblock is converted to two-dimensional matrix for each item to be commented on corresponding viewpoint extraction result；
First extracting sub-module for inputting the two-dimensional matrix in convolutional neural networks, and passes through the convolutional Neural net
The maximum pond layer of network extracts the matching characteristic of all convolution kernels；
Second determines submodule, for determining that the specified object inclines in the emotion of the viewpoint classification according to the matching characteristic
To.
10. device according to claim 6, which is characterized in that first extraction module includes:
Submodule is cut, for carrying out adjacent text cutting to each item comment for specified object, obtains cutting result；
Second extracting sub-module, for the solidification degree and freedom degree according to the cutting result, from each item for specified object
Neologisms are extracted in comment.
11. a kind of comment and analysis device characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to method described in any one of perform claim requirement 1 to 5.
12. a kind of non-volatile computer readable storage medium storing program for executing, is stored thereon with computer program instructions, which is characterized in that institute
It states and realizes method described in any one of claim 1 to 5 when computer program instructions are executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810134597.7A CN110134938A (en) | 2018-02-09 | 2018-02-09 | Comment and analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810134597.7A CN110134938A (en) | 2018-02-09 | 2018-02-09 | Comment and analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110134938A true CN110134938A (en) | 2019-08-16 |
Family
ID=67568004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810134597.7A Pending CN110134938A (en) | 2018-02-09 | 2018-02-09 | Comment and analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110134938A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340329A (en) * | 2020-02-05 | 2020-06-26 | 科大讯飞股份有限公司 | Actor assessment method and device and electronic equipment |
| CN111859146A (en) * | 2020-07-30 | 2020-10-30 | 网易（杭州）网络有限公司 | Information mining method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080249764A1 (en) * | 2007-03-01 | 2008-10-09 | Microsoft Corporation | Smart Sentiment Classifier for Product Reviews |
| CN104933130A (en) * | 2015-06-12 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Comment information marking method and comment information marking device |
| CN105320960A (en) * | 2015-10-14 | 2016-02-10 | 北京航空航天大学 | Voting based classification method for cross-language subjective and objective sentiments |
| CN106649260A (en) * | 2016-10-19 | 2017-05-10 | 中国计量大学 | Product feature structure tree construction method based on comment text mining |
| CN107133214A (en) * | 2017-05-05 | 2017-09-05 | 中国计量大学 | A kind of product demand preference profiles based on comment information are excavated and its method for evaluating quality |
-
2018
- 2018-02-09 CN CN201810134597.7A patent/CN110134938A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080249764A1 (en) * | 2007-03-01 | 2008-10-09 | Microsoft Corporation | Smart Sentiment Classifier for Product Reviews |
| CN104933130A (en) * | 2015-06-12 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Comment information marking method and comment information marking device |
| CN105320960A (en) * | 2015-10-14 | 2016-02-10 | 北京航空航天大学 | Voting based classification method for cross-language subjective and objective sentiments |
| CN106649260A (en) * | 2016-10-19 | 2017-05-10 | 中国计量大学 | Product feature structure tree construction method based on comment text mining |
| CN107133214A (en) * | 2017-05-05 | 2017-09-05 | 中国计量大学 | A kind of product demand preference profiles based on comment information are excavated and its method for evaluating quality |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340329A (en) * | 2020-02-05 | 2020-06-26 | 科大讯飞股份有限公司 | Actor assessment method and device and electronic equipment |
| CN111340329B (en) * | 2020-02-05 | 2024-02-20 | 科大讯飞股份有限公司 | Actor evaluation method and device and electronic equipment |
| CN111859146A (en) * | 2020-07-30 | 2020-10-30 | 网易（杭州）网络有限公司 | Information mining method and device and electronic equipment |
| CN111859146B (en) * | 2020-07-30 | 2024-02-23 | 网易（杭州）网络有限公司 | Information mining method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103918247B (en) | Intelligent mobile phone sensor logic based on background environment | |
| EP3852044A1 (en) | Method and device for commenting on multimedia resource | |
| CN109614613A (en) | The descriptive statement localization method and device of image, electronic equipment and storage medium | |
| CN110266879A (en) | Broadcast interface display methods, device, terminal and storage medium | |
| CN107948708A (en) | Barrage methods of exhibiting and device | |
| CN110781305A (en) | Text classification method and device based on classification model and model training method | |
| CN109887515B (en) | Audio processing method and device, electronic equipment and storage medium | |
| CN110175223A (en) | A kind of method and device that problem of implementation generates | |
| CN109729435A (en) | The extracting method and device of video clip | |
| CN111241822A (en) | Emotion discovery and dispersion method and device under input scene | |
| CN108833939A (en) | Generate the method and device of the poster of video | |
| CN108985176A (en) | image generating method and device | |
| CN108038102A (en) | Recommendation method, apparatus, terminal and the storage medium of facial expression image | |
| WO2019212729A1 (en) | Generating response based on user's profile and reasoning on contexts | |
| CN110209877A (en) | Video analysis method and device | |
| CN108924644A (en) | Video clip extracting method and device | |
| CN108062364A (en) | Information displaying method and device | |
| CN108540850A (en) | Barrage display methods and device | |
| CN110532956A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN107943550A (en) | Method for showing interface and device | |
| CN107797741A (en) | Method for showing interface and device | |
| CN110188871A (en) | Operation method, device and Related product | |
| CN108833952A (en) | The advertisement placement method and device of video | |
| CN110232181A (en) | Comment and analysis method and device | |
| CN110134938A (en) | Comment and analysis method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200426 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 100080 Beijing Haidian District city Haidian street A Sinosteel International Plaza No. 8 block 5 layer A, C Applicant before: Youku network technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |
|
| RJ01 | Rejection of invention patent application after publication |