CN104484329B - Consumption hot spot method for tracing and device based on comment centre word timing variations analysis - Google Patents
Consumption hot spot method for tracing and device based on comment centre word timing variations analysis Download PDFInfo
- Publication number
- CN104484329B CN104484329B CN201410603951.8A CN201410603951A CN104484329B CN 104484329 B CN104484329 B CN 104484329B CN 201410603951 A CN201410603951 A CN 201410603951A CN 104484329 B CN104484329 B CN 104484329B
- Authority
- CN
- China
- Prior art keywords
- comment
- key
- key vocabularies
- hot spot
- word
- 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.)
- Active
Links
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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of consumption hot spot method for tracing and device based on comment centre word timing variations analysis, the consumption hot spot method for tracing based on comment centre word timing variations analysis, including：The single frequency and repetition frequency degree of vocabulary in objectives comment on commodity are obtained, generates global key vocabularies set；According to the average frequency value of keyword, classify to key vocabularies, obtain global key vocabularies partitioned set；It is temporally segmented for statistical analysis, records local key vocabularies partitioned set；According to global key vocabularies partitioned set and the change information of the key vocabularies partitioned set of part, the point of interest transfer case of comment information is obtained.From the electric business comment data of magnanimity, unified with nature language processing techniques and statistical probability method, it was found that and track consumption hot spot of the buyer to all kinds of commodity, meet the commodity of buyer consumer demand so as to which seller be helped more targetedly to provide, more professional shopping guidance be provided for buyer.
Description
Technical field
The present invention relates to a kind of hot spot treatment technologies of internet arena, especially a kind of to be become based on comment centre word sequential
Change the consumption hot spot method for tracing and device of analysis.
Background technology
As the update and computer network of communication apparatus and technology are in e-commerce, E-Government, amusement, life
Etc. it is universal, the sociability of network is more and more apparent.In daily life, people are spent more and more time in network
On exchanged, mutual dealing.Network comment therein reflects that the respective shopping demand of complete transaction buyer also contributes to
Merchandising buyer shopping selection.
Nowadays network number of reviews is huge on major electric business net purchase platform, and buyer and seller is caused all to be difficult on the whole
Hold consumption hot spot.But either seller or buyer, the influence being all under review to a certain extent.The purpose of this patent is just
It is variation that will be according to the comment centre word of buyer in sequential, tracks the variation of consumption hot spot.For commodity seller,
They can obtain consumption hot spot and the consumption propensity of current buyer in time, so as to more targetedly provide commodity and service；
And for buyer, focus of the complete transaction buyer to this commodity or service is grasped, in selection commodity or the mistake of service
Cheng Zhonghui plays certain booster action, so as to avoid being misled into.Therefore how in internet especially electric business net purchase platform
Buyer's comment in excavate significant and valuable hot spot merchandise news and be likely to become the merchandise news of hot spot and become
It is particularly important.
Invention content
It is a primary object of the present invention to provide a kind of consumption hot spot tracking based on comment centre word timing variations analysis
Method and device can be excavated efficiently in the buyer of electric business net purchase platform comments on, track valuable hot spot merchandise news.
For this purpose, the embodiment of the present invention provides a kind of consumption hot spot tracking side based on comment centre word timing variations analysis
Method, including：
The single frequency and repetition frequency degree of vocabulary in objectives comment on commodity are obtained, generates global key vocabularies set；
According to the average frequency value of keyword, classify to key vocabularies, obtain global key vocabularies partitioned set；
It is temporally segmented for statistical analysis, records local key vocabularies partitioned set；
According to global key vocabularies partitioned set and the change information of the key vocabularies partitioned set of part, comment is obtained
The point of interest transfer case of information.
Optionally, after the vocabulary single frequency and repetition frequency degree that obtain objectives commodity, lexical density and opposite is calculated
The weighted value of information content and vocabulary lists global key vocabularies set.
Optionally, the relative entropy of the vocabulary is calculated using single frequency, the close of the vocabulary is calculated using repetition frequency degree
Degree, using the relative entropy and density of word, calculates the weighted value of the word, and (keyword, weight in the form of key-value pair
Value) it represents, and key-value pair sequence is carried out according to the size of weighted value, the smaller key-value pair of weighted value in key-value pair is neglected, is arranged
Go out global key vocabularies set.
Optionally, using Pareto rules, according to the frequency threshold of setting, global tri- area's keyword set of A, B, C is obtained.
Optionally, segmentation statistical analysis is carried out by the relevant evaluation to different periods, records part in each period
Key vocabularies partitioned set.
Optionally, the corresponding word finder of comment information of end article is obtained first.
The embodiment of the present invention additionally provides a kind of consumption hot spot follow-up mechanism based on comment centre word timing variations analysis,
Including：
Key vocabularies extraction module obtains the single frequency and repetition frequency degree of vocabulary in objectives comment on commodity, generates
Global key vocabularies set；
Global key vocabularies statistical module according to the average frequency value of keyword, classifies to key vocabularies, obtains the overall situation
Key vocabularies partitioned set；
Local key vocabularies statistical module, is temporally segmented for statistical analysis, records local key vocabularies partition set
It closes；
Hot spot comparison module, according to the variation of global key vocabularies partitioned set and the key vocabularies partitioned set of part
Information obtains the point of interest transfer case of comment information.
Optionally, comment vocabulary handling module is further included, obtains the corresponding vocabulary of comment information of end article.
Optionally, after the vocabulary single frequency and repetition frequency degree that obtain objectives commodity, being calculated using single frequency should
The relative entropy of vocabulary calculates the density of the vocabulary using repetition frequency degree, using the relative entropy and density of word, calculates
The weighted value of the word, and (keyword, weighted value) represents in the form of key-value pair, and carries out key assignments according to the size of weighted value
To sequence, the smaller key-value pair of weighted value in key-value pair is neglected, lists global key vocabularies set.
Optionally, the global key vocabularies statistical module, according to the frequency threshold of setting, is obtained using Pareto rules
Global tri- area's keyword set of A, B, C.
Compared with prior art, the present invention at least has the following technical effect that：
This patent is by from the electric business comment data of magnanimity, unified with nature language processing techniques and statistical probability method,
It was found that and track consumption hot spot of the buyer to all kinds of commodity, meet buyer consumer need so as to which seller be helped more targetedly to provide
The commodity asked provide more professional shopping guidance for buyer.
Description of the drawings
Fig. 1 is the flow of the consumption hot spot method for tracing based on comment centre word timing variations analysis of the embodiment of the present invention
Schematic diagram；
Fig. 2 is the structure of the consumption hot spot follow-up mechanism based on comment centre word timing variations analysis of the embodiment of the present invention
Schematic diagram.
Specific embodiment
Many details are elaborated in the following description in order to fully understand the present invention.But the present invention can be with
Much implement different from other manner described here, those skilled in the art can be in the situation without prejudice to intension of the present invention
Under do similar popularization, therefore the present invention is not limited by following public specific embodiment.
The embodiment of the present invention provides firstly a kind of consumption hot spot tracking side based on comment centre word timing variations analysis
The flow diagram of method, please refers to Fig.1, including：
Step S101 obtains the corresponding word finder of comment information of end article；
Step S102 obtains the single frequency and repetition frequency degree of vocabulary in objectives comment on commodity, generates global crucial
Lexical set；
Step S103 according to the average frequency value of keyword, classifies to key vocabularies, obtains global key vocabularies subregion
Set；
Step S104, is temporally segmented for statistical analysis, records local key vocabularies partitioned set；
Step S105 believes according to the variation of global key vocabularies partitioned set and the key vocabularies partitioned set of part
Breath obtains the point of interest transfer case of comment information.
Below by taking the electric business comment information of mobile phone as an example, technical solution of the present invention is illustrated.
Specifically, performing step S101, the corresponding word finder of comment information of end article is obtained.
It obtains first and the comment information of field (field of mobile phones) is corresponded in electric business platform, by way of automatic word segmentation or people
The mode of work point word segments all comment informations.Then by algorithm or artificial judgement, according to part of speech simple filtration
Fall unrelated conjunction, word remaining after filtering is recorded as in the form of vocabulary polymerize
M={ m1,m2,m3,…,mn}。
Step S102 is performed, obtains the single frequency and repetition frequency degree of vocabulary in objectives comment on commodity, is generated global
Key vocabularies set.
The comment information of objectives commodity (mobile phone of certain a a certain model) is analyzed according to the above method, for specific
The comment lexical set of end article is expressed as M1(contain n1A vocabulary), whereinStatistics objectives commodity are commented
By the single frequency and repetition frequency degree of vocabulary, single frequency is that word m occuriComment number, no more than N, N is complete for what is analyzed
Comment on number in portion；Repetition frequency degree refers to word miOccurrence number in the whole comment numbers analyzed, utilizes single frequency meter
The relative entropy of the vocabulary is calculated, the calculating of relative entropy herein is different from the calculating of routine information amount, and difference lies in sample numbers
Analyzed N items comment is only limitted to, and not all word m occursiComment set, calculate the close of the vocabulary using repetition frequency degree
Degree, using the relative entropy and density of word, calculates the weighted value of the word, when the word in lexical set is expressed as mi,
(there is word m in the single frequency occurred in the comment of N itemsiComment number, no more than N) be expressed as fi, repetition frequency degree is expressed as di
(word miOccurrence number in the comment of N items), then PiRepresent the relative entropy of the word, QiRepresent the weighted value of the word；
(keyword, weighted value) records comment vocabulary and the weight under the object in the form of key-value pair, and according to
The size of weighted value is ranked up following form：
{(mi,Qi)}i, wherein { Qi}iMeet Qi＞ QjFor arbitrary i ＜ j
On this basis, the smaller key-value pair of weighted value in key-value pair is neglected, obtains global key vocabularies set, and remember
It records and is：
W={ w1,w2,…,wh, containing h keyword, wherein
In other embodiments, the smaller key-value pair of weighted value in key-value pair can not also be ignored, list global keyword
Collect conjunction.
Step S103 is performed, according to the average frequency value of keyword, classifies to key vocabularies, obtains global key vocabularies
Partitioned set.
For the comment of objectives object, frequency is counted, and calculate averagely for each keyword to the keyword of acquisition
Frequency value is as follows：Keyword wiAverage frequency
Then according to the average frequency value of keyword, classify to key vocabularies, obtain global key vocabularies partitioned set.
In the present embodiment, using Pareto rules, according to the average frequency value of keyword, overall situation ABC analytical tables are drawn,
Table 1 is please referred to, wherein, global keyword set is combined into W={ w1,w2,…,wh}；Wherein p, q, l, m are positive integer.
Table one
Wherein, basic analysis of central issue (analysis of A areas)：Such as there is new keyword W in some period part A areasiOccur,
Illustrate WiAs the basic concern characteristic of buyer consumer, otherwise such as the keyword W in certain overall situation A areajIt is not included in period part A
In area's keyword, then illustrate WjIt is not basic focus of the buyer consumer in the period.
Optional analysis of central issue (analysis of B areas)：Such as there is new keyword W in some period part B areasiOccur, illustrate Wi
As the optional concern characteristic of buyer consumer：Such as keyword WiFor former overall situation A areas keyword, then illustrate buyer to WiConcern
Degree is declining, such as keyword WiFor former overall situation C areas keyword, illustrate buyer to WiAttention rate rise.Such as certain Global B area
Keyword WjIt is not included in period part B areas keyword, then illustrates WjIt is not optional concern of the buyer consumer in the period
Point：Such as WjFor local A areas keyword, then illustrate buyer to WjAttention rate rising, such as WjFor Local C area keyword, explanation is bought
Family is to WjAttention rate declining.
Potential analysis of central issue (analysis of C areas)：Such as there is new keyword W in some period Local C areaiOccur, and Wi
It is not present in global tri- area's keyword set of A, B, C, then illustrates WiAs the potential hot spot of buyer consumer.
A, the frequency threshold in 3rd area of B, C can be respectively set to：>=80%,>=15% and<80%,>=10% and<
15%, global tri- area's keyword set of A, B, C is relatively obtained according to keyword average frequency value and frequency threshold.In view of part
It comments on as comment spam, the threshold value in A areas should not set excessively high.Application when can according to different field comment spam proportion,
Different A areas threshold values is set for different field.
In other embodiments, the setting of the frequency threshold may be other values, and the region quantity being distributed also may be used
With difference.
In other embodiments, sorting technique can also be used, according to the average frequency value of keyword, to key vocabularies point
Class obtains global key vocabularies partitioned set.
Step S104 is performed, is temporally segmented for statistical analysis, records local key vocabularies partitioned set.
To these key vocabularies, be temporally segmented it is for statistical analysis, by different periods (as weekly, monthly, every season
It is degree, annual) relevant evaluation carry out segmentation statistical analysis, record tri- area's keyword of local A, B, C in each period, subregion
Method it is similar with the method for step S103.
In other embodiments, the step S104 and step S103 can be interchanged.
Step S105 is performed, according to the variation of global key vocabularies partitioned set and the key vocabularies partitioned set of part
Information obtains the point of interest transfer case of comment information.
If overall situation keyword W={ w1,w2,…,wh, in certain embodiments, the global keyword subregion of acquisition is：
Global A areas：{w1,w2,w3, Global B area：{w4,w5,w6,w7,w8, global C areas：{w9,w10}
The local keyword subregion of (such as second quarter in 2013) is within some period：
2013Q2 parts A areas：{w1,w2,w5, 2013Q2 parts B areas：{w3,w4,w6,w7,w8, 2013Q2 Local Cs area：
{w9,w10,w11}
Keyword w32013Q2 parts B areas are transferred to from global A areas, show that buyer is to w within the 2013Q2 periods3Pass
Note degree is declining；Keyword w52013Q2 parts A areas are transferred to from Global B area, show that buyer is to w within the 2013Q2 periods5's
Attention rate is rising；Occurs new keyword w in 2013Q2 Local Cs area11, show w11It is potential in the 2013Q2 periods
Hot spot.
Accordingly, the embodiment of the present invention also provides a kind of consumption hot spot based on comment centre word timing variations analysis and tracks dress
It puts, please refers to Fig.2, including：
Vocabulary handling module 10 is commented on, obtains the corresponding word finder of comment information of end article；
Key vocabularies extraction module 20 obtains the single frequency and repetition frequency degree of vocabulary in objectives comment on commodity, production
Raw overall situation key vocabularies set；
Global key vocabularies statistical module 30 according to the average frequency value of keyword, classifies to key vocabularies, obtains the overall situation
Key vocabularies partitioned set；
Local key vocabularies statistical module 40, is temporally segmented for statistical analysis, records local key vocabularies subregion
Set；
Hot spot comparison module 50, according to the change of global key vocabularies partitioned set and the key vocabularies partitioned set of part
Change information, obtain the point of interest transfer case of comment information.
The comment vocabulary handling module 10 obtains the comment information that field is corresponded in electric business platform first, by dividing automatically
The mode of word or the mode manually segmented segment all comment informations, then judge by algorithm or manually, according to
Part of speech simple filtration falls unrelated conjunction, obtains the corresponding word finder of comment information of end article.
The key vocabularies extraction module 20 calculates the relative entropy of the vocabulary using single frequency, utilizes repetition frequency degree
The density of the vocabulary is calculated, using the relative entropy and density of word, calculates the weighted value of the word, and with the shape of key-value pair
Formula (keyword, weighted value) represents, and carries out key-value pair sequence according to the size of weighted value, neglect in key-value pair weighted value compared with
Small key-value pair lists global key vocabularies set.
When the keyword that the overall situation is obtained by global key vocabularies statistical module 30 and local key vocabularies statistical module 40
The change information of remittance partitioned set and the key vocabularies partitioned set of part, using hot spot comparison module 50, according to global pass
The change information of keyword remittance partitioned set and the key vocabularies partitioned set of part, by comparing the change of partitioned set keyword
Change, if there is increase and decrease, from the electric business comment data of magnanimity, unified with nature language processing techniques and statistical probability method, hair
Now and consumption hot spot of the buyer to all kinds of commodity is tracked, meet buyer consumer demand so as to which seller be helped more targetedly to provide
Commodity, provide more professional shopping guidance for buyer.
In several embodiments provided by the present invention, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function can have other dividing mode, such as multiple units or component in actual implementation
It may be combined or can be integrated into another system or some features can be ignored or does not perform.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical unit, you can be located at a place or can also be distributed to multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
That each unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in one and computer-readable deposit
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, is used including some instructions so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) perform the present invention
The part steps of embodiment the method.And aforementioned storage medium includes：USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. it is various
The medium of program code can be stored.
Finally it should be noted that：Although the present invention is disclosed as above with preferred embodiment, it is not for limiting this hair
Bright, any those skilled in the art without departing from the spirit and scope of the present invention, can make possible variation and modification,
Therefore protection scope of the present invention should be subject to the range that the claims in the present invention are defined.
Claims (10)
1. a kind of consumption hot spot method for tracing based on comment centre word timing variations analysis, which is characterized in that including：
The single frequency and repetition frequency degree of vocabulary in objectives comment on commodity are obtained, generates global key vocabularies set；
The comment lexical set of objectives commodity is expressed as Mi, single frequency is that word m occuriComment number, no more than N, N
For the whole comment numbers analyzed；Repetition frequency degree refers to word miOccurrence number in the whole comment numbers analyzed；
According to the average frequency value of keyword, classify to key vocabularies, obtain global key vocabularies partitioned set；
It is temporally segmented for statistical analysis, records local key vocabularies partitioned set；
According to global key vocabularies partitioned set and the change information of the key vocabularies partitioned set of part, comment information is obtained
Point of interest transfer case.
2. the consumption hot spot method for tracing as described in claim 1 based on comment centre word timing variations analysis, feature exist
In after the vocabulary single frequency and repetition frequency degree that obtain objectives commodity, calculating lexical density and relative entropy and word
The weighted value of remittance lists global key vocabularies set.
3. the consumption hot spot method for tracing as claimed in claim 2 based on comment centre word timing variations analysis, feature exist
In calculating the relative entropy of the vocabulary using single frequency, the density of the vocabulary calculated using repetition frequency degree, utilizes word
Relative entropy and density calculate the weighted value of the word, and (keyword, weighted value) represents in the form of key-value pair, and presses
Key-value pair sequence is carried out according to the size of weighted value, the smaller key-value pair of weighted value in key-value pair is neglected, lists global keyword
Collect conjunction.
4. the consumption hot spot method for tracing as described in claim 1 based on comment centre word timing variations analysis, feature exist
In using Pareto rules, according to the frequency threshold of setting, obtaining global tri- area's keyword set of A, B, C.
5. the consumption hot spot method for tracing as described in claim 1 based on comment centre word timing variations analysis, feature exist
In carrying out segmentation statistical analysis by the relevant evaluation to different periods, record key vocabularies local in each period point
Gather in area.
6. the consumption hot spot method for tracing as described in claim 1 based on comment centre word timing variations analysis, feature exist
In, first obtain end article the corresponding word finder of comment information.
7. a kind of consumption hot spot follow-up mechanism based on comment centre word timing variations analysis, which is characterized in that including：
Key vocabularies extraction module obtains the single frequency and repetition frequency degree of vocabulary in objectives comment on commodity, generates global
Key vocabularies set；
The comment lexical set of objectives commodity is expressed as Mi, single frequency is that word m occuriComment number, no more than N, N
For the whole comment numbers analyzed；Repetition frequency degree refers to word miOccurrence number in the whole comment numbers analyzed；
Global key vocabularies statistical module according to the average frequency value of keyword, classifies to key vocabularies, obtains global key
Vocabulary partitioned set；
Local key vocabularies statistical module, is temporally segmented for statistical analysis, records local key vocabularies partitioned set；
Hot spot comparison module is believed according to the variation of global key vocabularies partitioned set and the key vocabularies partitioned set of part
Breath obtains the point of interest transfer case of comment information.
8. the consumption hot spot follow-up mechanism as claimed in claim 7 based on comment centre word timing variations analysis, feature exist
In further including comment vocabulary handling module, obtain the corresponding word finder of comment information of end article.
9. the consumption hot spot follow-up mechanism as claimed in claim 7 based on comment centre word timing variations analysis, feature exist
In after the vocabulary single frequency and repetition frequency degree that obtain objectives commodity, the opposite letter of the vocabulary is calculated using single frequency
Breath amount calculates the density of the vocabulary using repetition frequency degree, using the relative entropy and density of word, calculates the weight of the word
Value, and (keyword, weighted value) represents in the form of key-value pair, and carries out key-value pair sequence according to the size of weighted value, ignores
Fall the smaller key-value pair of weighted value in key-value pair, list global key vocabularies set.
10. the consumption hot spot follow-up mechanism as claimed in claim 7 based on comment centre word timing variations analysis, feature exist
In the overall situation key vocabularies statistical module, according to the frequency threshold of setting, obtains global A, B, C tri- using Pareto rules
Area's keyword set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410603951.8A CN104484329B (en) | 2014-10-31 | 2014-10-31 | Consumption hot spot method for tracing and device based on comment centre word timing variations analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410603951.8A CN104484329B (en) | 2014-10-31 | 2014-10-31 | Consumption hot spot method for tracing and device based on comment centre word timing variations analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104484329A CN104484329A (en) | 2015-04-01 |
| CN104484329B true CN104484329B (en) | 2018-07-06 |
Family
ID=52758870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410603951.8A Active CN104484329B (en) | 2014-10-31 | 2014-10-31 | Consumption hot spot method for tracing and device based on comment centre word timing variations analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104484329B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512111A (en) * | 2015-06-23 | 2016-04-20 | 崔笑言 | Keyword analytical method and application thereof |
| CN109697249A (en) * | 2018-12-07 | 2019-04-30 | 深圳市云歌人工智能技术有限公司 | Search for method, system and the storage medium of target object and issue object |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101645066A (en) * | 2008-08-05 | 2010-02-10 | 北京大学 | Method for monitoring novel words on Internet |
| CN103020851A (en) * | 2013-01-10 | 2013-04-03 | 山东地纬计算机软件有限公司 | Measurement calculation method supporting commodity comment data multidimensional analysis |
| 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 |
| CN103744865A (en) * | 2013-12-18 | 2014-04-23 | 网讯电通股份有限公司 | Mining method for commodity evaluation words of electronic articles and system thereof |
| CN103853763A (en) * | 2012-12-03 | 2014-06-11 | 腾讯科技（深圳）有限公司 | Information acquiring method and device |
| CN104035960A (en) * | 2014-05-08 | 2014-09-10 | 东莞市巨细信息科技有限公司 | Internet information hotspot predicting method |
-
2014
- 2014-10-31 CN CN201410603951.8A patent/CN104484329B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101645066A (en) * | 2008-08-05 | 2010-02-10 | 北京大学 | Method for monitoring novel words on Internet |
| CN103853763A (en) * | 2012-12-03 | 2014-06-11 | 腾讯科技（深圳）有限公司 | Information acquiring method and device |
| CN103020851A (en) * | 2013-01-10 | 2013-04-03 | 山东地纬计算机软件有限公司 | Measurement calculation method supporting commodity comment data multidimensional analysis |
| 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 |
| CN103744865A (en) * | 2013-12-18 | 2014-04-23 | 网讯电通股份有限公司 | Mining method for commodity evaluation words of electronic articles and system thereof |
| CN104035960A (en) * | 2014-05-08 | 2014-09-10 | 东莞市巨细信息科技有限公司 | Internet information hotspot predicting method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104484329A (en) | 2015-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105427129B (en) | Information delivery method and system | |
| TWI777004B (en) | Marketing information push equipment, devices and storage media | |
| CN104035917B (en) | A kind of knowledge mapping management method and system based on semantic space mapping | |
| WO2019214245A1 (en) | Information pushing method and apparatus, and terminal device and storage medium | |
| CN109033200B (en) | Event extraction method, device, equipment and computer readable medium | |
| CN110472154B (en) | Resource pushing method and device, electronic equipment and readable storage medium | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN106506705A (en) | Listener clustering method and device based on location-based service | |
| TW201939400A (en) | Method and device for determining group of target users | |
| CN107689008A (en) | A kind of user insures the method and device of behavior prediction | |
| CN109636482B (en) | Data processing method and system based on similarity model | |
| CN103886068A (en) | Data processing method and device for Internet user behavior analysis | |
| CN105512156B (en) | Click model generation method and device | |
| TWI705411B (en) | Method and device for identifying users with social business characteristics | |
| CN107220745B (en) | Method, system and equipment for identifying intention behavior data | |
| KR20190128246A (en) | Searching methods and apparatus and non-transitory computer-readable storage media | |
| CN106327230A (en) | Abnormal user detection method and device | |
| CN108197795A (en) | The account recognition methods of malice group, device, terminal and storage medium | |
| CN105512300B (en) | information filtering method and system | |
| CN110290467A (en) | The acquisition methods and device of dwell point, shopping centre service range, influence factor | |
| CN109978624A (en) | Information processing method, electronic equipment and computer readable storage medium | |
| CN104484329B (en) | Consumption hot spot method for tracing and device based on comment centre word timing variations analysis | |
| CN113298145A (en) | Label filling method and device | |
| CN105389714A (en) | Method for identifying user characteristic from behavior data | |
| CN104484330B (en) | Comment spam pre-selection method and device based on stepping keyword threshold value combined evaluation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191030 Address after: Room A1244, Building 2889 Baoan Road, Jiading District, Shanghai, 201801 Patentee after: Shanghai light Chen Information Technology Co., Ltd. Address before: Hangzhou City, Zhejiang province 310018 Xiasha Higher Education Park is 18 street. Patentee before: Zhejiang Gongshang University |
|
| TR01 | Transfer of patent right |