CN105930416A - Visualization processing method and system of user feedback information - Google Patents
Visualization processing method and system of user feedback information Download PDFInfo
- Publication number
- CN105930416A CN105930416A CN201610242427.1A CN201610242427A CN105930416A CN 105930416 A CN105930416 A CN 105930416A CN 201610242427 A CN201610242427 A CN 201610242427A CN 105930416 A CN105930416 A CN 105930416A
- Authority
- CN
- China
- Prior art keywords
- word
- visualization
- feedback information
- key word
- theme
- 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
- 238000012800 visualization Methods 0.000 title claims abstract description 98
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 54
- 238000004458 analytical method Methods 0.000 claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 32
- 230000002996 emotional effect Effects 0.000 claims description 30
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000008451 emotion Effects 0.000 claims description 10
- 238000013461 design Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 239000012535 impurity Substances 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 abstract 2
- 230000000694 effects Effects 0.000 description 4
- 241000270322 Lepidosauria Species 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a visualization processing method and system of user feedback information. The method comprises the following steps: obtaining user feedback information data from a server database, and preprocessing the feedback information data; according to a preprocessing result, carrying out subject analysis, and constructing word cloud visualization processing to obtain a visualization word cloud; according to the feedback information, constructing quick inverted sorting index processing for the visualization word cloud to obtain the inverted sorting index of the feedback information; and according to the inverted sorting index, displaying the visualization word cloud of a keyword corresponding to a theme clicked by a user. In the embodiment of the invention, the user feedback information can be quickly obtained through the visualization word cloud, and the use experience feeling of the platform user is improved.
Description
Technical field
The present invention relates to technical field of data processing, particularly relate to the visualization of a kind of field feedback
Processing method and system.
Background technology
Along with the fast development of development of Mobile Internet technology, the intelligentized continuous lifting of mobile phone terminal, more come
The most users, by installing various mobile applications, are very easy to daily life,
And various middle-size and small-size Internet enterprises also has platform and the corresponding mobile terminal APP application of their own.
Along with internet platform and the continuous growth of mobile terminal APP user, substantial amounts of user makes
Unavoidably run into various problem by process, thus major part internet platform and APP apply
Can collect corresponding field feedback, such as popular hands trip platform, along with the number of user's player feedback
Increasing according to the rapid, high volume of amount, this carries out effectively looking in time of platform user feedback problem to an enterprise
See and bring certain difficulty, and the mode often efficiency comparison relying on operation artificial is low, and feed back
Information is that comparison is mixed and disorderly in temporal sequence, and is the every day several ten thousand even growth of hundreds of thousands, but in fact
The problem theme of user feedback can be divided into several classes of minority, thus propose one and quickly have accordingly
The method analyzing user feedback of effect is extremely important.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, the invention provides a kind of user feedback
Information visuallization processing method and system, by visualization word cloud quick obtaining field feedback,
Improve user's experience sense.
In order to solve above-mentioned technical problem, embodiments provide a kind of field feedback can
Depending on changing processing method, described method includes:
From server database, obtain field feedback data, described feedback information data is carried out
Pretreatment；
Carry out building word cloud visualization processing according to pre-processed results, obtain visualization word cloud；
Carry out building the quickly process of falling ranking index to described visualization word cloud according to described feedback information,
Obtain the ranking index of falling of described feedback information；
According to described ranking index, described user is clicked on the described visual word of theme correspondence key word
Cloud shows.
Preferably, described described feedback information data is carried out pretreatment, including:
Described feedback information is carried out and Chinese extraction process, obtain text message；
Described text message carried out word segmentation processing and removes stop words according to disabling vocabulary, obtaining described
The key word of text message.
Preferably, described according to pre-processed results carry out build word cloud visualization processing, including:
Carry out LDA subject analysis according to described pre-processed results, obtain subject analysis result；
According to described pre-processed results, described feedback information is carried out emotional semantic classification process, obtain emotion and divide
Class result；
Carrying out word cloud visualization processing according to described analysis result and described emotional semantic classification result, acquisition can
Depending on changing word cloud.
Preferably, described carry out LDA subject analysis according to described pre-processed results, including:
The key word of text message is carried out word frequency statistics out, obtains statistical result；
It is randomly assigned a theme, as initial subject for each key word；
Described initial subject is processed, obtains the LDA analysis matrix of theme-key word.
Preferably, described according to described pre-processed results, described feedback information is carried out emotional semantic classification process,
Including:
According to described pre-processed results, feedback information is divided into positive feedback, negative feedback and meaningless three classes
Emotion tendency；
Feedback information is carried out traversal processing, the probability of the affiliated classification of each word in statistics feedback information；
The probability size of the affiliated classification according to word each in feedback information, obtains described feedback information
Sentiment orientation.
Preferably, described carry out word cloud visualization processing according to described analysis result and described classification results,
Including:
Constantly adjust theme number according to described analysis result, determine theme number；
Obtain each key word determining that theme is corresponding, described key word is carried out word frequency sequence；According to
Clooating sequence determines the size of key word；
Emotional semantic classification according to described key word determines the color of described key word；
According to user focus, keyword is carried out dynamic position adjustment, obtain visualization word cloud.
Preferably, described carrying out described visualization word cloud according to described feedback information builds the quick row of falling
Sequence index processes, including:
Design a dictionary, use described dictionary to deposit the key word that described feedback information is corresponding；
Scanning user feedback data list, accesses the record of feedback information of described user one by one；
Create, with described record of feedback information, the table of falling ranking index according to described visualization word cloud, obtain institute
State the ranking index of falling of feedback information；
Preferably, described user is clicked on theme correspondence key word by ranking index of falling described in described basis
Described visualization word cloud shows, including:
Theme-key word analysis matrix data is obtained according to described visualization word cloud；
According to described theme-key word analysis matrix data, obtain described each theme and use word frequency the highest
K key word carry out subject description.
The corresponding key word clicking on user carries out backstage quick-searching and falls ranking index, quickly searches also
Read and according to time sequence show.
It addition, the embodiment of the present invention additionally provides the visualization processing system of a kind of field feedback,
Described system includes
Pretreatment module: for obtaining field feedback data from server database, to described
Feedback information data carries out pretreatment；
Visualization processing module: for carrying out building word cloud visualization processing according to pre-processed results, obtain
Take visualization word cloud；
The module of falling ranking index: for described visualization word cloud being built according to described feedback information
The quickly process of falling ranking index, obtains the ranking index of falling of described feedback information；
Display module: for according to described fall ranking index described user clicked on theme correspondence key word
Described visualization word cloud show.
Preferably, described visualization processing module includes:
LDA analytic unit: for carrying out LDA subject analysis according to described pre-processed results, obtain and divide
Analysis result；
Emotional semantic classification unit: divide for described feedback information being carried out emotion according to described pre-processed results
Class processes, and obtains emotional semantic classification result；
Visualization processing unit: for carrying out word according to described analysis result and described emotional semantic classification result
Cloud visualization processing, obtains visualization word cloud.
In embodiments of the present invention, by the data message in background data base is carried out visualization processing,
And the visualization word cloud gone back after this visualization processing and data message are set up ranking index, with
When family is retrieved, the visualization word cloud of the correspondence that sorted out by input key word, user can be quick
Obtain feedback information, improve user's experience sense.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below by right
In embodiment or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that,
Accompanying drawing in describing below is only some embodiments of the present invention, for those of ordinary skill in the art
From the point of view of, on the premise of not paying creative work, it is also possible to obtain the attached of other according to these accompanying drawings
Figure.
Fig. 1 is the schematic flow sheet of the visible processing method of the field feedback of the embodiment of the present invention；
Fig. 2 is the schematic flow sheet of the structure word cloud visualization processing of the embodiment of the present invention；
Fig. 3 is the visualization word cloud effect schematic diagram after the user of the embodiment of the present invention inputs key word；
Fig. 4 is that the structure composition of the visualization processing system of the field feedback of the embodiment of the present invention shows
It is intended to.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is entered
Row clearly and completely describes, it is clear that described embodiment is only a part of embodiment of the present invention,
Rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
Have and make the every other embodiment obtained under creative work premise, broadly fall into present invention protection
Scope.
Fig. 1 is the schematic flow sheet of the visible processing method of the field feedback of the embodiment of the present invention,
As it is shown in figure 1, the method includes:
S11: obtain field feedback data from server database, this feedback information data is entered
Row pretreatment；
S12: carry out building word cloud visualization processing according to pre-processed results, obtains visualization word cloud；
S13: carry out building the quickly process of falling ranking index to this visualization word cloud according to this feedback information,
Obtain the ranking index of falling of this feedback information；
S14: fall ranking index according to this and this user is clicked on the visualization word cloud of theme correspondence key word enter
Row display.
S11 is described further:
Data in server database are crawled by the mode using data reptile to process, and obtain and use
The feedback information data at family；Impurity removal near to this feedback information and Chinese extraction process, obtain text
Information；Text information is carried out word segmentation processing, obtains the key word of text information.
Further, use data reptile to crawl the data base on server is carried out data, obtain
The feedback information data of user, uses a feedback information of identifier mark one user, right
This feedback information carries out Impurity removal process, is to remove the non-legible information such as image in feedback information,
UTF-8 (Unicode) coding range using Chinese carries out Chinese for/u4e00-/u9fa5 to feedback information
Extraction process, extracts the text message of feedback information.
Text message is carried out word segmentation processing, obtains the key word of text information；Load internet word
Allusion quotation and load internet disable dictionary；The DAG (directed acyclic graph) of sentence is built from dictionary；Right
Dictionary do not includes vocabulary, uses the Viterbi algorithm of HMM model to carry out participle；Include word
After converging and not including the whole participle of vocabulary, dynamic programming is used to find DAG (directed acyclic graph)
Maximum of probability path, thus realize word segmentation processing, obtain the key word of text message.
S12 is described further:
Carry out LDA subject analysis according to pre-processed results and obtain analysis result and according to pre-processed results pair
This feedback information carries out emotional semantic classification process, obtains emotional semantic classification result；Finally according to this analysis result
Carry out word cloud visualization processing with this emotional semantic classification result, obtain visualization word cloud.
Further, Fig. 2 is the schematic flow sheet of the structure word cloud visualization processing of the embodiment of the present invention,
As in figure 2 it is shown, the flow process of this step includes:
S121: carry out LDA subject analysis according to this pre-processed results, obtains analysis result；
S122: according to this pre-processed results, this feedback information is carried out emotional semantic classification process, obtain emotion
Classification results；
S123: carry out word cloud visualization processing according to this analysis result and this emotional semantic classification result, obtains
Visualization word cloud.
S121 is described further:
The key word of text message is carried out word frequency statistics, obtains statistical result；For each key word with
Machine sets a theme, as initial subject；This initial subject is processed, obtains theme-key
The LDA analysis matrix of word.
Further, every text message d in the text message set that pretreatment is got, obtain
Keyword set W={w of every text message d1,w2,…,wx}；To in every text message d
Key word does word frequency statistics, obtains p (wi|d)；For each key word w in keyword set Wi,
It is randomly assigned a theme t, as initial subject；By Gibbs Sampling formula, resampling
Each key word wiAffiliated theme t, and in key word update until Gibbs Sampling restrain；
Obtaining the probability matrix of " theme-key word " after convergence, this is exactly LDA matrix, and document-
The probability matrix of theme is also getable, after statistics, just can obtain the probability distribution of document-theme；
Determine LDA subject analysis result.
S122 is described further:
According to this pre-processed results, feedback information is divided into positive feedback, negative feedback and meaningless three classes
Emotion is inclined to；Feedback information is carried out traversal processing, the affiliated classification of each word in statistics feedback information
Probability；The probability size of the affiliated classification according to word each in feedback information, obtains this feedback information
Sentiment orientation.
Further, load pre-processed results, the most markd to the platform in these pre-processed results
Field feedback obtain training set, to every new feedback information according to training set be divided into positive feedback,
The emotion tendency of negative feedback and meaningless three classes；Every field feedback as a text message,
The each word that can obtain statistics after having traveled through all of marked field feedback set belongs to every
Probability P (the w of individual classi|category)；For a given new field feedback, this user feedback
Whether information is positive feedback (commendation) or negative feedback (reflection problem) or insignificant, can be according to shellfish
This theorem of leaf calculates the probability of certain classification belonging to this user feedback i.e.
P (Category | Document)=P (Document | Category) * P (Category)/P (Document),
P (Document | Category) is i.e. the probability P (wi | category) of each key word in this feedback information
Product, P (Category) is probability that field feedback belongs to certain classification, it is simply that such feedback is total
Number is divided by feedback sum, and P (Document) is considered as a constant；According to every field feedback
The probability size of affiliated each classification i.e. can obtain the Sentiment orientation of this field feedback, completes emotion
Classify and record to data base.
S123 is described further:
Carry out word cloud visualization processing according to this analysis result and this emotional semantic classification result, obtain visualization
Word cloud；Constantly adjust theme number according to this analysis result, determine theme number；Obtain and each determine
The key word that theme is corresponding, carries out word frequency sequence to this key word；Key word is determined according to clooating sequence
Size；Determine the size of key word and described emotional semantic classification result according to clooating sequence, obtain this pass
Keyword size and color classification；According to user focus, keyword being carried out dynamic position adjustment, acquisition can
Depending on changing word cloud.
Further, constantly adjust the number of theme according to this analysis result, come by actual effect
Determine final theme number；When determining final theme number, then determine that these determine number of topics
These key words are ranked up processing, its ordering principle by the key word that each theme in mesh is corresponding
It is the sequence that carries out of the size of word frequency according to above-mentioned calculating, determines pass according to the order result of sequence
The size of keyword；Emotional semantic classification according to this key word determines the color of this key word, and color can have
Three primary colors combines, color the deepest dark expression this key word more negative feedback, and color the lightest expression closes
Keyword is the most meaningless, color the most bright-coloured expression key word more positive feedback；According to user focus to keyword
Carry out dynamic position adjustment, obtain visualization word cloud.
S13 is described further:
Design a dictionary, use this dictionary to deposit the key word that described feedback information is corresponding；Scanning is used
Family feedback data list, accesses the record of feedback information of this user one by one；According to this visualization word cloud with
This record of feedback information creates the table of falling ranking index, obtains the ranking index of falling of this feedback information.
Further, read the pretreated feedback information of user, design a dictionary and deposit whole use
The unique key set of words of all key words of family feedback information；Rescan a field feedback
Data list, accesses the record of field feedback one by one；According to this visualization word cloud and this feedback letter
Breath record creates inverted index table, each word as a record of table, simultaneously after record this word and go out
Now which bar record of which user, uses customer identification number uniquely to identify a user, uses
This record id identifies the unique feedback information of this user, deposits in json mode, scanning process
Expand whole piece record successively, thus obtain the ranking index of falling of feedback information.
S14 is described further:
Fall ranking index according to this this user clicks on this visualization word cloud of theme correspondence key word to carry out
Display.
Further, theme-key word analysis matrix data is obtained according to this visualization word cloud；According to this
Theme-key word analysis matrix data, obtains this theme and uses K the key word that word frequency is the highest to lead
Topic describes.The corresponding key word clicking on user carries out backstage quick-searching and falls ranking index, checks quickly soon
Look for and read and according to time sequence show.
Fig. 3 is the visualization word cloud effect schematic diagram after the user of the embodiment of the present invention inputs key word,
As it is shown on figure 3, user is after input searching motif, obtain the key of its correspondence according to this searching motif
The visualization word cloud of word and the source of this key word.
Fig. 4 is that the structure composition of the visualization processing system of the field feedback of the embodiment of the present invention shows
Being intended to, as shown in Figure 4, this system includes:
Pretreatment module 11: for obtaining field feedback data from server database, to this
Feedback information data carries out pretreatment；
Visualization processing module 12: for carrying out subject analysis according to pre-processed results and building each master
The word cloud visualization processing of topic, obtains visualization word cloud；
The module of falling ranking index 13: for carrying out building soon to this visualization word cloud according to this feedback information
The speed process of falling ranking index, obtains the ranking index of falling of this feedback information；
Display module 14: be somebody's turn to do for this user being clicked on theme correspondence key word according to ranking index
Visualization word cloud shows.
Preferably, this pretreatment module 11 includes:
Word processing unit: for this feedback information being carried out Impurity removal and Chinese extraction process, obtain
Take text message；
Participle unit: for text message being carried out word segmentation processing, obtain the key word of text message.
Preferably, this visualization processing module 12 includes:
LDA analytic unit: for carrying out LDA subject analysis according to this pre-processed results, obtain and analyze
Result；
Emotional semantic classification unit: for this feedback information being carried out at emotional semantic classification according to this pre-processed results
Reason, obtains emotional semantic classification result；
Visualization processing unit: can for carrying out word cloud according to this analysis result and this emotional semantic classification result
Process depending on change, obtain visualization word cloud.
Preferably, this LDA analytic unit includes:
Statistics subelement: for the key word of text message is carried out word frequency statistics out, obtain statistics
Result；
Random assortment subelement: for being randomly assigned a theme for each key word, as initial main
Topic；
Process subelement: for this initial subject is processed, obtain the LDA of theme-key word
Analysis matrix.
Preferably, this emotional semantic classification unit includes:
Emotion divides subelement: for according to this pre-processed results feedback information is divided into positive feedback,
The emotion tendency of negative feedback and meaningless three classes；
Traversal subelement: for feedback information being carried out traversal processing, each word in statistics feedback information
The probability of affiliated classification；
Classification subelement: for the probability size of the affiliated classification according to word each in feedback information, obtain
Take the Sentiment orientation of this feedback information.
Preferably, this visualization processing unit includes:
Adjust subelement: for constantly adjusting theme number according to this analysis result, determine theme number；
Size acquisition unit: for obtaining each key word determining that theme is corresponding, key word is carried out
Word frequency sorts；The size of key word is determined according to clooating sequence；
Color determines unit: for determining the color of key word according to the emotional semantic classification of key word；
Visualization word cloud acquiring unit: keyword is carried out dynamic position for moving according to user focus
Adjust, obtain visualization word cloud.
Preferably, should the module of falling ranking index 13 include:
Dictionary design cell: for one dictionary of design, use this dictionary to deposit this feedback information corresponding
Key word；
Scanning user feedback data list, accesses the record of feedback information of this user one by one；
Create, with this record of feedback information, the table of falling ranking index according to visualization word cloud, obtain this feedback letter
The ranking index of breath；
Preferably, this display module 14 includes:
Information acquisition unit: for obtaining theme-key word analysis matrix data according to visualization word cloud；
Subject description unit: for according to this theme-key word analysis matrix data, obtain each theme
K the key word using its word frequency the highest carries out subject description.
Display unit: the corresponding key word for clicking on user carries out backstage quick-searching and sorts rope
Draw, quickly search and reading according to time sequence shows.
Specifically, the operation principle of the system related functions module of the embodiment of the present invention can be found in method in fact
Execute the associated description of example, repeat no more here.
In embodiments of the present invention, by the data message in background data base is carried out visualization processing,
And the visualization word cloud gone back after this visualization processing and data message are set up ranking index, with
When family is retrieved, the visualization word cloud of the correspondence that sorted out by input key word, user can be quick
Obtain feedback information, improve user's experience sense.
One of ordinary skill in the art will appreciate that in the various methods of above-described embodiment is all or part of
Step can be by program and completes to instruct relevant hardware, and this program can be stored in a calculating
In machine readable storage medium storing program for executing, storage medium may include that read only memory (ROM, Read Only
Memory), random access memory (RAM, Random Access Memory), disk or CD
Deng.
It addition, the visualization processing of above a kind of field feedback that the embodiment of the present invention is provided
Method and system are described in detail, and specific case used herein is to the principle of the present invention and reality
The mode of executing is set forth, the explanation of above example be only intended to help to understand the method for the present invention and
Its core concept；Simultaneously for one of ordinary skill in the art, according to the thought of the present invention,
All will change in detailed description of the invention and range of application, in sum, this specification content is not
It is interpreted as limitation of the present invention.
Claims (10)
1. the visible processing method of a field feedback, it is characterised in that described method includes:
From server database, obtain field feedback data, described feedback information data is carried out pretreatment；
Carry out building theme word cloud visualization processing according to pre-processed results, obtain visualization word cloud；
According to described feedback information, described visualization word cloud is carried out subject analysis the structure quickly process of falling ranking index, obtain the ranking index of falling of described feedback information；
According to described fall ranking index described user clicked on the described visualization word cloud of theme correspondence key word show.
Visible processing method the most according to claim 1, it is characterised in that described described feedback information data is carried out pretreatment, including:
Described feedback information is carried out Impurity removal and Chinese extraction process, obtains text message；
Described text message is carried out word segmentation processing, obtains the key word of described text message.
Visible processing method the most according to claim 1, it is characterised in that described according to pre-processed results carry out build word cloud visualization processing, including:
Carry out LDA subject analysis according to described pre-processed results, obtain analysis result；
According to described pre-processed results, described feedback information is carried out emotional semantic classification process, obtain emotional semantic classification result；
Carry out word cloud visualization processing according to described analysis result and described emotional semantic classification result, obtain visualization word cloud.
Visible processing method the most according to claim 3, it is characterised in that described carry out LDA subject analysis according to described pre-processed results, including:
The key word of text message is carried out word frequency statistics, obtains statistical result；
It is randomly assigned a theme, as initial subject for each key word；
Described initial subject is processed, obtains the LDA analysis matrix of theme-key word.
Visible processing method the most according to claim 3, it is characterised in that described according to described pre-processed results, described feedback information is carried out emotional semantic classification process, including:
According to described pre-processed results, feedback information is divided into the emotion tendency of positive feedback, negative feedback and meaningless three classes；
Feedback information is carried out traversal processing, the probability of the affiliated classification of each word in statistics feedback information；
The probability size of the affiliated classification according to word each in feedback information, obtains the Sentiment orientation of described feedback information.
Visible processing method the most according to claim 3, it is characterised in that described carry out word cloud visualization processing according to described analysis result and described classification results, including:
Constantly adjust theme number according to described analysis result, determine theme number；
Obtain each key word determining that theme is corresponding, described key word is carried out word frequency sequence；The size of key word is determined according to clooating sequence；
Emotional semantic classification according to described key word determines the color of described key word；
According to user focus, keyword is carried out dynamic position adjustment, obtain visualization word cloud.
Visible processing method the most according to claim 1, it is characterised in that described carrying out described visualization word cloud according to described feedback information builds the quickly process of falling ranking index, including:
Design a dictionary, use described dictionary to deposit the key word that described feedback information is corresponding；
Scanning user feedback data list, accesses the record of feedback information of described user one by one；
Create, with described record of feedback information, the table of falling ranking index according to described visualization word cloud, obtain the ranking index of falling of described feedback information.
Visible processing method the most according to claim 1, it is characterised in that described user is clicked on the described visualization word cloud of theme correspondence key word and shows by ranking index of falling described in described basis, including:
Theme-key word analysis matrix data is obtained according to described visualization word cloud；
According to described theme-key word analysis matrix data, obtain described theme and use K the key word that word frequency is the highest to carry out subject description.
The corresponding key word clicking on user carries out backstage quick-searching and falls ranking index, quickly searches and reads and according to time sequence shows.
9. the visualization processing system of a field feedback, it is characterised in that described system includes
Pretreatment module: for obtaining field feedback data from server database, described feedback information data is carried out pretreatment；
Visualization processing module: for carrying out subject analysis according to pre-processed results and building word cloud visualization processing, obtains visualization word cloud；
The module of falling ranking index: for carrying out building the quickly process of falling ranking index to described visualization word cloud according to described feedback information, obtains the ranking index of falling of described feedback information；
Display module: for according to described fall ranking index described user clicked on the described visualization word cloud of theme correspondence key word show.
Visualization processing system the most according to claim 9, it is characterised in that described visualization processing module includes:
LDA analytic unit: for carrying out LDA subject analysis according to described pre-processed results, obtain analysis result；
Emotional semantic classification unit: for described feedback information being carried out emotional semantic classification process according to described pre-processed results, obtain emotional semantic classification result；
Visualization processing unit: for carrying out word cloud visualization processing according to described analysis result and described emotional semantic classification result, obtains visualization word cloud.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610242427.1A CN105930416A (en) | 2016-04-19 | 2016-04-19 | Visualization processing method and system of user feedback information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610242427.1A CN105930416A (en) | 2016-04-19 | 2016-04-19 | Visualization processing method and system of user feedback information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105930416A true CN105930416A (en) | 2016-09-07 |
Family
ID=56838337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610242427.1A Pending CN105930416A (en) | 2016-04-19 | 2016-04-19 | Visualization processing method and system of user feedback information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105930416A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943941A (en) * | 2017-11-23 | 2018-04-20 | 珠海金山网络游戏科技有限公司 | It is a kind of can iteration renewal rubbish text recognition methods and system |
| CN107992565A (en) * | 2017-11-29 | 2018-05-04 | 北京锐安科技有限公司 | A kind of method and system of Optimizing Search engine |
| CN108172304A (en) * | 2017-12-18 | 2018-06-15 | 广州七乐康药业连锁有限公司 | A kind of medical information visible processing method and system based on user's medical treatment feedback |
| CN109299226A (en) * | 2018-10-25 | 2019-02-01 | 北京奇艺世纪科技有限公司 | A kind of data processing method and system |
| CN111191449A (en) * | 2019-12-26 | 2020-05-22 | 航天信息股份有限公司 | Tax feedback information processing method and device |
| CN111985210A (en) * | 2020-08-26 | 2020-11-24 | 北京机电工程总体设计部 | Editable document theme visualization construction method based on word cloud technology |
| CN112036158A (en) * | 2020-09-01 | 2020-12-04 | 北京金堤征信服务有限公司 | Word cloud data distribution processing method and device |
| CN112949305A (en) * | 2021-05-13 | 2021-06-11 | 平安科技（深圳）有限公司 | Negative feedback information acquisition method, device, equipment and storage medium |
| CN112989200A (en) * | 2021-03-31 | 2021-06-18 | 珠海必要工业科技股份有限公司 | Commodity use information providing method and comment information-based associated information improving method |
| CN113190611A (en) * | 2021-04-16 | 2021-07-30 | 量子数聚（北京）科技有限公司 | Data display method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080072145A1 (en) * | 2006-09-19 | 2008-03-20 | Blanchard John A | Method and apparatus for customizing the display of multidimensional data |
| CN103309869A (en) * | 2012-03-09 | 2013-09-18 | 阿里巴巴集团控股有限公司 | Method and system for recommending display keyword of data object |
| CN103425755A (en) * | 2013-07-31 | 2013-12-04 | 王永恒 | Method based on microblogs for analyzing audience rating situations of television programs |
| CN103793481A (en) * | 2014-01-16 | 2014-05-14 | 中国科学院软件研究所 | Microblog word cloud generating method based on user interest mining and accessing supporting system |
-
2016
- 2016-04-19 CN CN201610242427.1A patent/CN105930416A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080072145A1 (en) * | 2006-09-19 | 2008-03-20 | Blanchard John A | Method and apparatus for customizing the display of multidimensional data |
| CN103309869A (en) * | 2012-03-09 | 2013-09-18 | 阿里巴巴集团控股有限公司 | Method and system for recommending display keyword of data object |
| CN103425755A (en) * | 2013-07-31 | 2013-12-04 | 王永恒 | Method based on microblogs for analyzing audience rating situations of television programs |
| CN103793481A (en) * | 2014-01-16 | 2014-05-14 | 中国科学院软件研究所 | Microblog word cloud generating method based on user interest mining and accessing supporting system |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107943941B (en) * | 2017-11-23 | 2021-10-15 | 珠海金山网络游戏科技有限公司 | Junk text recognition method and system capable of being updated iteratively |
| CN107943941A (en) * | 2017-11-23 | 2018-04-20 | 珠海金山网络游戏科技有限公司 | It is a kind of can iteration renewal rubbish text recognition methods and system |
| CN107992565B (en) * | 2017-11-29 | 2020-11-03 | 北京锐安科技有限公司 | Method and system for optimizing search engine |
| CN107992565A (en) * | 2017-11-29 | 2018-05-04 | 北京锐安科技有限公司 | A kind of method and system of Optimizing Search engine |
| CN108172304B (en) * | 2017-12-18 | 2021-04-02 | 广州七乐康药业连锁有限公司 | Medical information visualization processing method and system based on user medical feedback |
| CN108172304A (en) * | 2017-12-18 | 2018-06-15 | 广州七乐康药业连锁有限公司 | A kind of medical information visible processing method and system based on user's medical treatment feedback |
| CN109299226A (en) * | 2018-10-25 | 2019-02-01 | 北京奇艺世纪科技有限公司 | A kind of data processing method and system |
| CN111191449A (en) * | 2019-12-26 | 2020-05-22 | 航天信息股份有限公司 | Tax feedback information processing method and device |
| CN111985210A (en) * | 2020-08-26 | 2020-11-24 | 北京机电工程总体设计部 | Editable document theme visualization construction method based on word cloud technology |
| CN111985210B (en) * | 2020-08-26 | 2023-08-15 | 北京机电工程总体设计部 | Method for constructing editable document theme visualization based on word cloud technology |
| CN112036158A (en) * | 2020-09-01 | 2020-12-04 | 北京金堤征信服务有限公司 | Word cloud data distribution processing method and device |
| CN112036158B (en) * | 2020-09-01 | 2023-11-03 | 北京金堤征信服务有限公司 | Word cloud data distribution processing method and device |
| CN112989200A (en) * | 2021-03-31 | 2021-06-18 | 珠海必要工业科技股份有限公司 | Commodity use information providing method and comment information-based associated information improving method |
| CN112989200B (en) * | 2021-03-31 | 2024-06-07 | 珠海必要工业科技股份有限公司 | Method for providing commodity use information and method for improving associated information based on comment information |
| CN113190611A (en) * | 2021-04-16 | 2021-07-30 | 量子数聚（北京）科技有限公司 | Data display method and device |
| CN112949305A (en) * | 2021-05-13 | 2021-06-11 | 平安科技（深圳）有限公司 | Negative feedback information acquisition method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105930416A (en) | Visualization processing method and system of user feedback information | |
| CN106503055B (en) | A kind of generation method from structured text to iamge description | |
| CN106055673B (en) | A kind of Chinese short text sensibility classification method based on text feature insertion | |
| CN109299271B (en) | Training sample generation method, text data method, public opinion event classification method and related equipment | |
| CN106776574B (en) | User comment text mining method and device | |
| CN108984530A (en) | A kind of detection method and detection system of network sensitive content | |
| CN108073568A (en) | keyword extracting method and device | |
| US10366117B2 (en) | Computer-implemented systems and methods for taxonomy development | |
| CN101645083B (en) | Acquisition system and method of text field based on concept symbols | |
| CN104331506A (en) | Multiclass emotion analyzing method and system facing bilingual microblog text | |
| KR101713558B1 (en) | Method of classification and analysis of sentiment in social network service | |
| CN102096680A (en) | Method and device for analyzing information validity | |
| CN107491435A (en) | Method and device based on Computer Automatic Recognition user feeling | |
| CN104361037B (en) | Microblogging sorting technique and device | |
| CN104899335A (en) | Method for performing sentiment classification on network public sentiment of information | |
| CN112883734A (en) | Block chain security event public opinion monitoring method and system | |
| CN110910175A (en) | Tourist ticket product portrait generation method | |
| CN114077705A (en) | Method and system for portraying media account on social platform | |
| CN109214445A (en) | A kind of multi-tag classification method based on artificial intelligence | |
| CN109101487A (en) | Conversational character differentiating method, device, terminal device and storage medium | |
| CN111754208A (en) | Automatic screening method for recruitment resumes | |
| CN116882414B (en) | Automatic comment generation method and related device based on large-scale language model | |
| CN115860283B (en) | Contribution degree prediction method and device based on knowledge worker portrait | |
| CN110413985B (en) | Related text segment searching method and device | |
| CN109543049B (en) | Method and system for automatically pushing materials according to writing characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160907 |