CN109284373A - The acquisition methods and device of product up-gradation strategy based on text mining driving - Google Patents
The acquisition methods and device of product up-gradation strategy based on text mining driving Download PDFInfo
- Publication number
- CN109284373A CN109284373A CN201811036716.1A CN201811036716A CN109284373A CN 109284373 A CN109284373 A CN 109284373A CN 201811036716 A CN201811036716 A CN 201811036716A CN 109284373 A CN109284373 A CN 109284373A
- Authority
- CN
- China
- Prior art keywords
- product attribute
- product
- satisfaction
- classification
- emotion
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
Abstract
The present invention provides the acquisition methods and device of a kind of product up-gradation strategy based on text mining driving.A kind of acquisition methods of the product up-gradation strategy based on text mining driving, comprising: for each product attribute in the product attribute terminology bank constructed in advance, obtain the satisfaction and importance of the product attribute；Based on pre-set SIPA model, the classification of the product attribute is obtained according to the satisfaction of the product attribute and importance；Corresponding relationship based on classification and escalation policy obtains escalation policy according to the classification.As it can be seen that the mode for obtaining product review in the present embodiment is simple, sample size is big, can reduce the amount of labour for obtaining and commenting content.Also, the timeliness of online comment is relatively high, therefore the escalation policy obtained also has that timeliness is good, the high feature of validity.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of product up-gradation strategies based on text mining driving
Acquisition methods and device.
Background technique
Currently, to obtain the satisfaction and importance of product attribute, related personnel needs design seismic wave questionnaire or arranges to visit
The forms such as what is said or talked about, are then filled in questionnaires by user or interview record to obtain satisfaction and importance.Later, based on satisfaction and important
Property, utilize the upgrading of IPA (Importance-performance Analysis, importance-performance degree) model analysis product
Strategy.
Then, draw up a questionnaire, questionnaire or user's interview require to expend a large amount of human cost and time cost, and
Sample size is small, and timeliness is poor, and satisfied effect is often not achieved in the product up-gradation strategy made.
Summary of the invention
For the defects in the prior art, the present invention provides a kind of product up-gradation strategies based on text mining driving
Acquisition methods and device, escalation policy for solving to obtain by questionnaire or interview mode in the prior art it is ineffective
The problem of.
In a first aspect, the embodiment of the invention provides a kind of acquisition sides of product up-gradation strategy based on text mining driving
Method, comprising:
For each product attribute in the product attribute terminology bank constructed in advance, obtain the product attribute satisfaction and
Importance；
Based on pre-set SIPA model, the product category is obtained according to the satisfaction of the product attribute and importance
The classification of property；
Corresponding relationship based on classification and escalation policy obtains escalation policy according to the classification.
Optionally, pre-set product occurs terminology bank and passes through following steps acquisition, comprising:
Using pre-set POS part of speech analysis method, the name that frequency of occurrence is more than pre-set frequency threshold value is obtained
Word or noun phrase obtain the product term candidate collection of target product；
The non-product attribute term that the product term candidate is concentrated is rejected by crowdsourcing form；
Merge the product attribute term that the product term candidate after rejecting non-product attribute term is concentrated according to thesaurus,
Obtain product attribute terminology bank.
Optionally, the satisfaction for obtaining product attribute includes:
Obtain at least one comment sentence including the product attribute relational terms；
For every comment sentence, the feeling polarities of the product attribute are differentiated according to sentiment dictionary method；The emotion
Polarity includes at least positive emotion polarity and negative emotion polarity；
Accounting of the positive emotion polarity in all feeling polarities in the product attribute is obtained, the product attribute is obtained
Satisfaction.
Optionally, the importance for obtaining the product attribute includes:
Call the orderly preference pattern of training in advance；
The positive emotion of the product attribute and negative emotion are input to the orderly preference pattern, obtain the product
The important coefficient of attribute positive emotion and negative emotion.
Optionally, the orderly preference pattern are as follows:
In formula, xk=(xk,l,pos,xk,l,neg), indicate kth position client to the positive emotion and negative emotion of product attribute；
ykIndicate that the grade given a mark to product, grade 1 indicate low point, equal part in the expression of grade 2, grade 3 indicates high score；β=(βl,pos,
βl,neg), indicate the positive emotion of product attribute and the important coefficient of negative emotion.
Optionally, it is based on pre-set SIPA model, institute is obtained according to the satisfaction of the product attribute and importance
The classification for stating product attribute includes:
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be first etc.
Grade and the product attribute satisfaction be the tertiary gradient, then the product attribute belongs to the first classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be first etc.
Grade and the product attribute satisfaction be the fourth estate, then the product attribute belongs to the second classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to third classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 4th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be first etc.
Grade and the satisfaction of the product attribute are the tertiary gradient, then the product attribute belongs to the 5th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be first etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 6th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the tertiary gradient, then the product attribute belongs to the 7th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 8th classification.
Optionally, described if the satisfaction of the product attribute is more than or equal to pre-set satisfaction threshold value
Satisfaction is the tertiary gradient；
If the satisfaction of the product attribute is less than the satisfaction threshold value, the satisfaction is the fourth estate.
Optionally, if the important coefficient of the positive emotion is more than or equal to pre-set coefficient threshold, institute
Stating important coefficient is the first estate；
If the important coefficient of the positive emotion is less than the coefficient threshold, the important coefficient is second etc.
Grade.
Optionally, satisfaction threshold value is 0.75, and/or, coefficient threshold 0.015.
Second aspect, the embodiment of the invention provides a kind of acquisition dresses of product up-gradation strategy based on text mining driving
It sets, comprising:
First obtains module, each product attribute for being directed in the product attribute terminology bank constructed in advance, described in acquisition
The satisfaction and importance of product attribute；
Second obtains module, for being based on pre-set SIPA model, according to the satisfaction of the product attribute and again
The property wanted obtains the classification of the product attribute；
Strategy obtains module, for the corresponding relationship based on classification and escalation policy, obtains upgrading plan according to the classification
Slightly.
As shown from the above technical solution, product attribute terminology bank can be constructed in the embodiment of the present invention in advance, passes through product
Each available associated online product review of product attribute, i.e., obtain product review in the present embodiment in attribute terminology bank
Mode it is simple, sample size is big, can reduce obtain comment content the amount of labour.Then, by described in acquisition in the present embodiment
The satisfaction and importance of product attribute, and be based on pre-set SIPA model, according to the satisfaction of the product attribute and
Importance obtains the classification of the product attribute；Corresponding relationship based on classification and escalation policy, obtains according to the classification and rises
Grade strategy.Since the timeliness of online comment is relatively high, the escalation policy obtained also has timeliness good, and validity is high
Feature.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these figures.
Fig. 1 is a kind of acquisition methods of product up-gradation strategy based on text mining driving provided in an embodiment of the present invention
Flow diagram；
Fig. 2 is the flow diagram of building product attribute terminology bank provided in an embodiment of the present invention；
Fig. 3 is the flow diagram provided in an embodiment of the present invention for obtaining product attribute satisfaction；
Fig. 4 is the process signal of the important coefficient provided in an embodiment of the present invention for obtaining following emotion and negative emotion
Figure；
Fig. 5 is the schematic diagram of SIPA model provided in an embodiment of the present invention；
Fig. 6 is the frame of the acquisition device of the product up-gradation strategy provided in an embodiment of the present invention based on text mining driving
Figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is the stream of the acquisition methods for the product up-gradation strategy based on text mining driving that one embodiment of the invention provides
Journey schematic diagram.Referring to Fig. 1, should include: based on the acquisition methods for the product up-gradation strategy that text mining drives
101, for each product attribute in the product attribute terminology bank constructed in advance, obtain the satisfaction of the product attribute
Degree and importance.
102, it is based on pre-set SIPA model, the production is obtained according to the satisfaction of the product attribute and importance
The classification of product attribute.
103, the corresponding relationship based on classification and escalation policy obtains escalation policy according to the classification.
As it can be seen that the mode for obtaining product review in the present embodiment is simple, sample size is big, can reduce to obtain and comment content
The amount of labour.Also, the timeliness of online comment is relatively high, therefore the escalation policy obtained also has that timeliness is good, and validity is high
The characteristics of.
With reference to the accompanying drawings and examples to the product up-gradation plan provided in an embodiment of the present invention based on text mining driving
Each step of acquisition methods slightly is described in detail.
Firstly, introducing 101, for each product attribute in the product attribute terminology bank constructed in advance, the product is obtained
The step of satisfaction and importance of attribute.
In the present embodiment, product attribute terminology bank can be constructed in advance.Referring to fig. 2, firstly, utilizing pre-set POS
Part of speech analysis method obtains noun or noun phrase that frequency of occurrence is more than pre-set frequency threshold value, obtains target production
Product term candidate collection (the corresponding step 201) of product.Wherein, the purpose that frequency threshold value is arranged is, filters out and frequently occurs
Product attribute, therefore frequency threshold value can be adjusted according to concrete scene, such as 5-10 times, be not limited thereto.Then, originally
Embodiment rejects non-product attribute term (the corresponding step 202) that the product term candidate is concentrated by crowdsourcing form.Later,
The present embodiment merges the product attribute term that the product term candidate after rejecting non-product attribute term is concentrated according to thesaurus,
Obtain product attribute terminology bank (corresponding step 203).
In the present embodiment, the satisfaction of available each product attribute, referring to Fig. 3, comprising: firstly, being directed to product category
Property terminology bank in each product attribute, selection includes at least one comment sentence (corresponding step of the product attribute relational terms
301).Secondly, being directed to every comment sentence, the feeling polarities of the product attribute are differentiated according to sentiment dictionary method；The feelings
Feel polarity and includes at least positive emotion polarity and negative emotion polarity (corresponding step 302).Finally, difference statistical product attribute
Positive emotion polarity and the polar quantity of negative emotion, obtain product attribute in positive emotion polarity in all feeling polarities
Accounting obtains satisfaction (the corresponding step 303) of the product attribute.Satisfaction formula is as follows:
In formula, Performance (xil) indicate i-th of product first of attribute satisfaction, Pos (xil) indicate i-th
First of polar number of attribute positive emotion of a product, Neg (xil) indicate i-th of product first of attribute negative emotion pole
The number of property.
In the present embodiment, the satisfaction of available each product attribute, referring to fig. 4, comprising:
Firstly, call training in advance orderly preference pattern (corresponding step 401), formula are as follows:
In formula, xk=(xk,l,pos,xk,l,neg), indicate kth position client to the positive emotion and negative emotion of product attribute；
ykIndicate that the grade given a mark to product, grade 1 indicate low point, equal part in the expression of grade 2, grade 3 indicates high score；β=(βl,pos,
βl,neg), indicate the positive emotion of product attribute and the important coefficient of negative emotion.
Then, the positive emotion of product attribute and negative emotion are input to the orderly preference pattern in the present embodiment,
Obtain important coefficient (the corresponding step 402) of product attribute positive emotion and negative emotion.In this way, passing through sample in the present embodiment
Notebook data training obtains the important coefficient β of product attribute positive emotion and negative emotionl,posAnd βl,neg。
Secondly, introducing 102, it is based on pre-set SIPA model, according to the satisfaction and importance of the product attribute
The step of obtaining the classification of the product attribute.
In the present embodiment, it is based on pre-set SIPA model, is obtained and is produced according to the satisfaction of product attribute and importance
The classification of product attribute, comprising:
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be first etc.
Grade and the product attribute satisfaction be the tertiary gradient, then the product attribute belongs to the first classification.
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be first etc.
Grade and the product attribute satisfaction be the fourth estate, then the product attribute belongs to the second classification.
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to third classification.
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 4th classification.
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be first etc.
Grade and the satisfaction of the product attribute are the tertiary gradient, then the product attribute belongs to the 5th classification.
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be first etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 6th classification.
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the tertiary gradient, then the product attribute belongs to the 7th classification.
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be second etc.
Grade and the satisfaction of the product attribute are the fourth estate, then the product attribute belongs to the 8th classification.
In one embodiment, if the satisfaction of the product attribute is more than or equal to pre-set satisfaction threshold value,
Then the satisfaction is the tertiary gradient；If the satisfaction of the product attribute is less than the satisfaction threshold value, the satisfaction
For the fourth estate.Wherein, satisfaction threshold value can be 0.75.
In another embodiment, if the important coefficient of the positive emotion is more than or equal to pre-set coefficient threshold
Value, then the important coefficient is the first estate；If the important coefficient of the positive emotion is less than the coefficient threshold, institute
Stating important coefficient is the second grade.Wherein, coefficient threshold can be 0.015.
Again, 103 are introduced, the corresponding relationship based on classification and escalation policy obtains escalation policy according to the classification
Step.
In the present embodiment, the corresponding relationship of classification and escalation policy can be preset, and may include:
First kind product attribute is client's expectation type demand, and customer satisfaction is high, then escalation policy, which can be, " needs to hold
Continuous innovation, reinforces advantage ".
Second class product attribute is client's expectation type demand, but customer satisfaction is low, then escalation policy, which can be, " needs
It is preferential to improve, shorten gap ".
Third class product attribute is client's glamour type demand, and customer satisfaction is high, then escalation policy can be " need with
Track market, keeps on top ".
4th class product attribute is client's glamour type demand, and customer satisfaction is low, then escalation policy can be " in fund
Under sufficiency, reinforce innovation, establish advantage ".
5th class product attribute is client's basic model demand, and customer satisfaction is high, then escalation policy, which can be, " takes guarantor
Attitude is kept, is innovated with caution ".
6th class product attribute is client's basic model demand, and customer satisfaction is low, then escalation policy, which can be, " needs weight
Point improves, and reduces and complains ".
7th class product attribute is client's indifference abnormal shape demand, and customer satisfaction is high, then escalation policy, which can be, " keeps
Performance avoids excessively putting into ".
8th class product attribute is client's indifference abnormal shape demand, and customer satisfaction is low, then escalation policy can be " low
It under the conditions of investment, is suitably modified for complaint ".
Combined with specific embodiments below with scene to the product up-gradation strategy provided by the invention based on text mining driving
Acquisition methods make exemplary description.
Firstly, the present embodiment collects the online product review of product and its competing product to be analyzed, comprising: auspicious GS4 is passed, it is flourish
Prestige RX5, Chang'an CS75, distant view SUV breathe out not H6, and BYD Song wins and gets over and precious fine horse 560.
Then, the feature of online product review, available 13 critical product attributes are provided in the present embodiment.To each production
The feeling polarities of product attribute are analyzed, and count the satisfaction of each product attribute, and the results are shown in Table 1.
Table 1 passes the satisfaction of each product attribute of auspicious GS4
In the present embodiment, by solving orderly preference pattern, the positive emotion and negative emotion of each product attribute are obtained
Importance size and conspicuousness, the results are shown in Table 2:
Table 2, the importance of the positive negative emotion of product attribute
| Product attribute | Coefficient | Std.Eroor | p-value |
| Appearance-front | 0.0223 | 0.0073 | *** |
| Appearance-is negative | -0.0878 | 0.0279 | *** |
| Oil consumption-front | 0.0196 | 0.0113 | * |
| Oil consumption-is negative | -0.0227 | 0.0104 | ** |
| Space-front | 0.0815 | 0.0073 | *** |
| Space-is negative | 0.0050 | 0.0124 | 0.686 |
| Configuration-front | 0.0097 | 0.0090 | 0.281 |
| Configuration-is negative | -0.0334 | 0.0259 | * |
| Power-front | 0.0202 | 0.0089 | ** |
| Power-is negative | -0.0779 | 0.0110 | *** |
| Price-front | 0.0327 | 0.0250 | * |
| Price-is negative | -0.0056 | 0.0115 | * |
| Interior trim-front | 0.0280 | 0.0097 | ** |
| Interior trim-is negative | -0.0411 | 0.0183 | *** |
| Skylight-front | 0.0770 | 0.0132 | *** |
| Skylight-is negative | -0.0082 | 0.0231 | 0.723 |
| Comfortably-front | 0.0387 | 0.0131 | *** |
| Comfortably-negative | -0.0208 | 0.0291 | 0.476 |
| Workmanship-front | 0.0111 | 0.0190 | 0.558 |
| Workmanship-is negative | -0.0204 | 0.0250 | 0.416 |
| Materials-front | 0.0884 | 0.0173 | *** |
| Materials-are negative | -0.0395 | 0.0228 | * |
| Seat-front | 0.0120 | 0.0213 | 0.573 |
| Seat-is negative | -0.0275 | 0.0222 | * |
| Safety-front | 0.0157 | 0.0177 | 0.375 |
| Safety-is negative | -0.0482 | 0.0289 | * |
Finally, the present embodiment passes through the SIPA model of fusion product attribute feeling polarities, by Chang'an CS75's referring to Fig. 5
13 product attributes are divided into 8 classifications, formulate escalation policy respectively, the results are shown in Table 3.
Table 3, the product attribute classification for passing auspicious GS4 and its escalation policy
| Attribute classification | Product attribute | Escalation policy |
| The first kind | Appearance；Oil consumption | Continuous Innovation reinforces advantage |
| Second class | Power；Interior trim；Materials | It is preferential to improve, shorten gap |
| Third class | Space；Comfortably | Market is tracked, is kept on top |
| 4th class | Price；Skylight | Reinforce innovation, establishes advantage |
| 5th class | Configuration | Entrenched attitudes are innovated with caution |
| 6th class | Seat；Safety | Emphasis improves, and reduces and complains |
| 7th class | - | Retention property avoids excessively |
| 8th class | Workmanship | Under low investment, it is suitably modified |
As it can be seen that in the present embodiment, the online product review analysis product up-gradation strategy in social media can use, it can be with
It obtains in real time, obtains and be easy, time cost and human cost can be reduced.Also, sample size is sufficiently large and validity is strong, has
Conducive to the accuracy for promoting classification and escalation policy.
Fig. 6 is the frame of the acquisition device for the product up-gradation strategy based on text mining driving that one embodiment of the invention provides
Figure.Referring to Fig. 6, the acquisition device of the product up-gradation strategy based on text mining driving includes:
First obtains module 601, for obtaining institute for each product attribute in the product attribute terminology bank constructed in advance
State the satisfaction and importance of product attribute；
Second obtains module 602, for being based on pre-set SIPA model, according to the satisfaction of the product attribute and
Importance obtains the classification of the product attribute；
Strategy obtains module 602, for the corresponding relationship based on classification and escalation policy, obtains and upgrades according to the classification
Strategy.
It should be noted that the acquisition dress of the product up-gradation strategy provided in an embodiment of the present invention based on text mining driving
Setting with the above method is one-to-one relationship, and the implementation detail of the above method is equally applicable to above-mentioned apparatus, and the present invention is implemented
Example is no longer described in detail above system.
In specification of the invention, numerous specific details are set forth.It is to be appreciated, however, that the embodiment of the present invention can be with
It practices without these specific details.In some instances, well known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this specification.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (10)
1. a kind of acquisition methods of the product up-gradation strategy based on text mining driving characterized by comprising
For each product attribute in the product attribute terminology bank constructed in advance, the satisfaction of the product attribute and important is obtained
Property；
Based on pre-set SIPA model, the product attribute is obtained according to the satisfaction of the product attribute and importance
Classification；
Corresponding relationship based on classification and escalation policy obtains escalation policy according to the classification.
2. acquisition methods according to claim 1, which is characterized in that pre-set product generation terminology bank passes through following
Step obtains, comprising:
Using pre-set POS part of speech analysis method, obtain noun that frequency of occurrence is more than pre-set frequency threshold value or
Person's noun phrase obtains the product term candidate collection of target product；
The non-product attribute term that the product term candidate is concentrated is rejected by crowdsourcing form；
Merge the product attribute term that the product term candidate after rejecting non-product attribute term is concentrated according to thesaurus, obtains
Product attribute terminology bank.
3. acquisition methods according to claim 1, which is characterized in that the satisfaction for obtaining product attribute includes:
Obtain at least one comment sentence including the product attribute relational terms；
For every comment sentence, the feeling polarities of the product attribute are differentiated according to sentiment dictionary method；The feeling polarities
Including at least positive emotion polarity and negative emotion polarity；
Accounting of the positive emotion polarity in all feeling polarities in the product attribute is obtained, expiring for the product attribute is obtained
Meaning degree.
4. acquisition methods according to claim 3, which is characterized in that the importance for obtaining the product attribute includes:
Call the orderly preference pattern of training in advance；
The positive emotion of the product attribute and negative emotion are input to the orderly preference pattern, obtain the product attribute
The important coefficient of positive emotion and negative emotion.
5. acquisition methods according to claim 4, which is characterized in that the orderly preference pattern are as follows:
In formula, xk=(xk,l,pos,xk,l,neg), indicate kth position client to the positive emotion and negative emotion of product attribute；ykIt indicates
To the grade of product marking, grade 1 indicates low point, and equal part in the expression of grade 2, grade 3 indicates high score；β=(βl,pos,βl,neg),
Indicate the positive emotion of product attribute and the important coefficient of negative emotion.
6. acquisition methods according to claim 1, which is characterized in that pre-set SIPA model is based on, according to described
The classification that the satisfaction and importance of product attribute obtain the product attribute includes:
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be the first estate and
The satisfaction of the product attribute is the tertiary gradient, then the product attribute belongs to the first classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be the first estate and
The satisfaction of the product attribute is the fourth estate, then the product attribute belongs to the second classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be the second grade and
The satisfaction of the product attribute is the fourth estate, then the product attribute belongs to third classification；
If the important coefficient of the positive emotion be the first estate, the negative emotion important coefficient be the second grade and
The satisfaction of the product attribute is the fourth estate, then the product attribute belongs to the 4th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be the first estate and
The satisfaction of the product attribute is the tertiary gradient, then the product attribute belongs to the 5th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be the first estate and
The satisfaction of the product attribute is the fourth estate, then the product attribute belongs to the 6th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be the second grade and
The satisfaction of the product attribute is the tertiary gradient, then the product attribute belongs to the 7th classification；
If the important coefficient of the positive emotion be the second grade, the negative emotion important coefficient be the second grade and
The satisfaction of the product attribute is the fourth estate, then the product attribute belongs to the 8th classification.
7. acquisition methods according to claim 6, which is characterized in that if the satisfaction of the product attribute is greater than or waits
In pre-set satisfaction threshold value, then the satisfaction is the tertiary gradient；
If the satisfaction of the product attribute is less than the satisfaction threshold value, the satisfaction is the fourth estate.
8. acquisition methods according to claim 6, which is characterized in that if the important coefficient of the positive emotion be greater than or
Person is equal to pre-set coefficient threshold, then the important coefficient is the first estate；
If the important coefficient of the positive emotion is less than the coefficient threshold, the important coefficient is the second grade.
9. acquisition methods according to claim 7 or 8, which is characterized in that satisfaction threshold value is 0.75, and/or, coefficient threshold
Value is 0.015.
10. a kind of acquisition device of the product up-gradation strategy based on text mining driving characterized by comprising
First obtains module, for obtaining the product for each product attribute in the product attribute terminology bank constructed in advance
The satisfaction and importance of attribute；
Second obtains module, for being based on pre-set SIPA model, according to the satisfaction and importance of the product attribute
Obtain the classification of the product attribute；
Strategy obtains module, for the corresponding relationship based on classification and escalation policy, obtains escalation policy according to the classification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811036716.1A CN109284373A (en) | 2018-09-06 | 2018-09-06 | The acquisition methods and device of product up-gradation strategy based on text mining driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811036716.1A CN109284373A (en) | 2018-09-06 | 2018-09-06 | The acquisition methods and device of product up-gradation strategy based on text mining driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109284373A true CN109284373A (en) | 2019-01-29 |
Family
ID=65183653
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811036716.1A Pending CN109284373A (en) | 2018-09-06 | 2018-09-06 | The acquisition methods and device of product up-gradation strategy based on text mining driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284373A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414811A (en) * | 2019-07-18 | 2019-11-05 | 合肥工业大学 | Generate the product Promotion Strategy acquisition methods and system of content online based on user |
| CN113239701A (en) * | 2021-05-07 | 2021-08-10 | 京东数字科技控股股份有限公司 | Data analysis processing method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399916A (en) * | 2013-07-31 | 2013-11-20 | 清华大学 | Internet comment and opinion mining method and system on basis of product features |
| CN105550269A (en) * | 2015-12-10 | 2016-05-04 | 复旦大学 | Product comment analyzing method and system with learning supervising function |
| CN106708868A (en) * | 2015-11-16 | 2017-05-24 | 中国移动通信集团北京有限公司 | Method and system for analyzing internet data |
| CN107862343A (en) * | 2017-11-28 | 2018-03-30 | 南京理工大学 | The rule-based and comment on commodity property level sensibility classification method of neutral net |
| CN107908753A (en) * | 2017-11-20 | 2018-04-13 | 合肥工业大学 | Customer demand method for digging and device based on social media comment data |
| CN107943909A (en) * | 2017-11-17 | 2018-04-20 | 合肥工业大学 | User demand trend method for digging and device, storage medium based on comment data |
-
2018
- 2018-09-06 CN CN201811036716.1A patent/CN109284373A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103399916A (en) * | 2013-07-31 | 2013-11-20 | 清华大学 | Internet comment and opinion mining method and system on basis of product features |
| CN106708868A (en) * | 2015-11-16 | 2017-05-24 | 中国移动通信集团北京有限公司 | Method and system for analyzing internet data |
| CN105550269A (en) * | 2015-12-10 | 2016-05-04 | 复旦大学 | Product comment analyzing method and system with learning supervising function |
| CN107943909A (en) * | 2017-11-17 | 2018-04-20 | 合肥工业大学 | User demand trend method for digging and device, storage medium based on comment data |
| CN107908753A (en) * | 2017-11-20 | 2018-04-13 | 合肥工业大学 | Customer demand method for digging and device based on social media comment data |
| CN107862343A (en) * | 2017-11-28 | 2018-03-30 | 南京理工大学 | The rule-based and comment on commodity property level sensibility classification method of neutral net |
Non-Patent Citations (1)
| Title |
|---|
| 希尔等: "《计量经济学原理第4版》", 28 February 2013 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414811A (en) * | 2019-07-18 | 2019-11-05 | 合肥工业大学 | Generate the product Promotion Strategy acquisition methods and system of content online based on user |
| CN113239701A (en) * | 2021-05-07 | 2021-08-10 | 京东数字科技控股股份有限公司 | Data analysis processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Digital economy development, industrial structure upgrading and green total factor productivity: Empirical evidence from China’s cities | |
| Kwon et al. | Topic modeling and sentiment analysis of online review for airlines | |
| CN103646088B (en) | Product comment fine-grained emotional element extraction method based on CRFs and SVM | |
| US20160092793A1 (en) | Pharmacovigilance systems and methods utilizing cascading filters and machine learning models to classify and discern pharmaceutical trends from social media posts | |
| CN106503049A (en) | A kind of microblog emotional sorting technique for merging multiple affection resources based on SVM | |
| Chen et al. | Analysis of user needs on downloading behavior of English vocabulary APPs based on data mining for online comments | |
| Li et al. | Mining public opinion on transportation systems based on social media data | |
| Tejedor et al. | Exo journalism: a conceptual approach to a hybrid formula between journalism and artificial intelligence | |
| Wang | The feature extraction based on texture image information for emotion sensing in speech | |
| Chang et al. | Applying text mining, clustering analysis, and latent dirichlet allocation techniques for topic classification of environmental education journals | |
| CN109284373A (en) | The acquisition methods and device of product up-gradation strategy based on text mining driving | |
| CN108009248A (en) | A kind of data classification method and system | |
| Li et al. | Text mining of user-generated content (ugc) for business applications in e-commerce: A systematic review | |
| Borrajo-Millán et al. | Sentiment Analysis to Measure Quality and Build Sustainability in Tourism Destinations | |
| Parhat et al. | A robust morpheme sequence and convolutional neural network-based Uyghur and Kazakh short text classification | |
| Tu et al. | A feature fusion model with data augmentation for speech emotion recognition | |
| Ackert et al. | Homeownership for all: An American narrative | |
| Pang et al. | The Impact of the Digital Economy on Transformation and Upgrading of Industrial Structure: A Perspective Based on the “Poverty Trap” | |
| Seo et al. | Perceptions of customers as sustained competitive advantages of global marketing airline alliances: A hybrid text mining approach | |
| CN103678720B (en) | Method and device for processing user feedback data | |
| Zhao et al. | A Study of the Impact of Cultural Characteristics on Consumers’ Behavioral Intention for Mobile Payments: A Comparison between China and Korea | |
| Stier | Partisan framing of political debates on Twitter | |
| Qu et al. | Online-Review-Driven Products Ranking: A Hybrid Approach | |
| Chernyavskaya et al. | What russian university stands for: Analyzing socially embedded vision and values | |
| Bi et al. | Chinese-style fiscal decentralization, ecological attention of Government, and regional energy intensity |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190129 |