CN103164424A - Method and device for acquiring time-efficient words - Google Patents

Method and device for acquiring time-efficient words Download PDF

Info

Publication number
CN103164424A
CN103164424A CN2011104138816A CN201110413881A CN103164424A CN 103164424 A CN103164424 A CN 103164424A CN 2011104138816 A CN2011104138816 A CN 2011104138816A CN 201110413881 A CN201110413881 A CN 201110413881A CN 103164424 A CN103164424 A CN 103164424A
Authority
CN
China
Prior art keywords
searching
time range
statistical time
word
key 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.)
Granted
Application number
CN2011104138816A
Other languages
Chinese (zh)
Other versions
CN103164424B (en
Inventor
郭瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201110413881.6A priority Critical patent/CN103164424B/en
Publication of CN103164424A publication Critical patent/CN103164424A/en
Application granted granted Critical
Publication of CN103164424B publication Critical patent/CN103164424B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The invention discloses a method and a device for acquiring time-efficient words. The method includes: acquiring search times of each search keyword in each unit time interval in a statistic time interval; determining search time stability of each search keyword in the statistic time interval according to the search times of each search keyword in each unit time interval in the statistic time interval; and determining the time-efficient words corresponding to the statistic time interval in each search keyword according to the search time stability. By means of the method for acquiring the time-efficient words, complexity in acquiring the time-efficient words can be reduced, and acquiring efficiency can be improved.

Description

A kind of acquisition methods of ageing word and device
Technical field
The application relates to networking technology area, particularly relates to a kind of acquisition methods and device of ageing word.
Background technology
Along with the develop rapidly of every profession and trade technology and increasing gradually of shopping website commodity, and the continuing to bring out of a large amount of group buying websites, shopping website represents to user's commodity and service more and more.And shopping website directly represents the commodity to the user, great majority are nonsensical concerning the user, some timeliness that perhaps is directed to the user requires weak search, and as " popular clothing ", " trend clothes " etc., the intention difference of returning to Search Results and user is often very large.Therefore, the excavation of ageing word becomes more and more important.Ageing word generally includes hot word, seasonal word, property in red-letter day word etc.The characteristics of hot word are, from beginning sometime unexpected appearance, and search rate (searching times in the unit period) is very high, and in the time before this time search rate close to 0.The characteristics of the words such as seasonal word, property in red-letter day word are, within the corresponding season in every year or the search rate before and after red-letter day very high and stable, and search rate is unstable within other periods.
For the excavation of ageing word, need to carry out complex calculations to the inquiry log of magnanimity and the Query Information of various dimensions, when this makes storage space and calculating, needed internal memory and time have been subject to great challenge.The present method of obtaining ageing word by calculating adopts distributed computing system, calculates by statistical methods such as machine learning.
In realizing the application's process, the inventor finds, there are the following problems at least for prior art: along with the continuous growth of Query Information data volume, calculate by statistical methods such as machine learning, requirement to hardware is more and more higher, shared time of computation process is also more and more longer, and the restriction due to hardware or time, space even causes algorithm infeasible.
Summary of the invention
The application's purpose is, a kind of acquisition methods and device of ageing word is provided, and obtains efficient with the complexity and the raising that reduce ageing word acquisition process, and for this reason, the embodiment of the present application adopts following technical scheme:
A kind of acquisition methods of ageing word comprises:
Obtain constituent parts searching times period in of each searching key word in statistical time range;
The searching times of constituent parts in the period according to searching key word in statistical time range determined the searching times degree of stability of described searching key word in described statistical time range;
According to described searching times degree of stability, determine the ageing word corresponding with described statistical time range in each searching key word.
A kind ofly use the ageing word that method as above obtains and carry out the method that merchandise news is thrown in, the method comprises, according to the ageing word that obtains, merchandise news is thrown in.
A kind of ageing word deriving means comprises:
Acquisition module is used for obtaining each searching key word at the searching times of constituent parts in the period of statistical time range;
The first determination module is used for according to constituent parts searching times period in of searching key word at statistical time range, determines the searching times degree of stability of described searching key word in described statistical time range;
The second determination module is used for according to described searching times degree of stability, determines the ageing word corresponding with described statistical time range in each searching key word.
In the application's embodiment, server obtains constituent parts searching times period in of each searching key word in statistical time range, the searching times of constituent parts in the period according to searching key word in statistical time range, determine the searching times degree of stability of searching key word in statistical time range, again according to the searching times degree of stability of determining, determine the ageing word corresponding with statistical time range in each searching key word, can effectively reduce the complexity of ageing word acquisition process and improve and obtain efficient.Certainly, arbitrary product of enforcement the application's embodiment might not need to reach simultaneously above-described all advantages.
Description of drawings
One of schematic flow sheet of the ageing word acquisition methods that Fig. 1 provides for the embodiment of the present application;
Two of the schematic flow sheet of the ageing word acquisition methods that Fig. 2 provides for the embodiment of the present application;
The structural representation of the ageing word deriving means that Fig. 3 provides for the embodiment of the present application.
Embodiment
Below in conjunction with the accompanying drawing in the application, the technical scheme in the application is carried out clear, complete description, obviously, described embodiment is a part of embodiment of the application, rather than whole embodiment.Based on the embodiment in the application, the every other embodiment that those of ordinary skills obtain under the prerequisite of not making creative work belongs to the scope that the application protects.
In the embodiment of the present application, server obtains constituent parts searching times period in of each searching key word in statistical time range, the searching times of constituent parts in the period according to searching key word in statistical time range, determine the searching times degree of stability of searching key word in statistical time range, again according to the searching times degree of stability of determining, determine the ageing word corresponding with statistical time range in each searching key word, obtain efficient with the complexity and the raising that reduce ageing word acquisition process.
As shown in Figure 1, the flow process of the acquisition methods of the ageing word that it provides for the embodiment of the present application specifically comprises the following steps:
Step 101, server are obtained constituent parts searching times period in of each searching key word in statistical time range.
Server can be added up each user's inquiry log in advance.After webpage inputted search statement, server obtains the search statement of user input, then search statement is carried out word segmentation processing as the user, and search statement is divided into one by one searching key word and the time of corresponding recording user search operation.Like this, server just can get searching record and the corresponding time of each searching key word.Server can also further be classified to searching key word, for example, classification can comprise the brand word (as help red slave, peace is stepped on etc.), commodity word (as down jackets, woollen overcoat), model word (as X010, Z899 etc.) etc.After classification, server can only be added up (for example, only the commodity word being added up) to a certain class word, and what finally get accordingly is also ageing word in this class word.
Server can according to searching record and the corresponding time of each searching key word, obtain interior searching times of constituent parts period in statistical time range.Server can carry out record at the searching times of constituent parts in the period to searching key word, concrete record format can be: word (word) time 1 (time 1) frequency 1 (frequency 1), time 2 frequency 2...time n frequency n, can come record by form, as shown in table 1.
Table 1
Word 20110201 20110202 20110228
Mobile phone 1182345 1102346 1082348
One-piece dress 17802345 17202386 12802845
…… …… …… …… ……
Server can be added up a plurality of statistical time ranges according to concrete statistical demand, for example, server can obtain interior searching times of constituent parts period in adjacent a plurality of statistical time ranges, also can obtain interior searching times of constituent parts period in several statistical time ranges fixing in every year.
Wherein, the unit period is be used to the minimum time section of carrying out the searching times statistics, its length can set in advance according to concrete statistics needs, as one day, a week, one month etc., for example in table 1, take in the sky as the unit interval section, word " mobile phone " was on February 1st, 2011, searching times be 1182345, the rest may be inferred.Statistical time range was comprised of a plurality of unit period, and length can set in advance according to concrete statistics needs, as a week, one month, a season, 1 year etc.When carrying out the obtaining of hot word, the characteristics that can uprush in conjunction with hot word search rate (being the searching times in the unit period) can be set to a shorter value unit period, as 1 day, and with statistical time range corresponding be set to for 1 week or 1 month.When carrying out the obtaining of seasonal word, can be in conjunction with the characteristics of seasonal word with seasonal variations, the unit period is set to week or two weeks, and statistical time range is set to a season.When carrying out the obtaining of property in red-letter day word, can be according to concrete characteristics setting unit period in red-letter day and statistical time range.
Step 102, server be the searching times of constituent parts in the period in statistical time range according to searching key word, determines the searching times degree of stability of searching key word in statistical time range.Wherein, the searching times degree of stability is used for the reaction searching times in each unit situation of change in the period of statistical time range.It is strong that searching times in the constituent parts period changes Shaoxing opera, and the searching times degree of stability is lower; Searching times in the constituent parts period changes milder, and the searching times degree of stability is higher.
Definite method of the searching times degree of stability of searching key word in statistical time range can be as follows:
Method one
At first, server is the searching times of constituent parts in the period in statistical time range and the total searching times of this searching key word in statistical time range according to searching key word, determines constituent parts searching probability period in of this searching key word in statistical time range.
Server can be with searching key word constituent parts searching times addition in the period in statistical time range, obtain the total searching times in statistical time range, then use searching times in the constituent parts period divided by total searching times, obtain this searching key word at the searching probability of constituent parts in the period.Specifically can adopt the form of doing the searching probability vector of dimension with the time, be recorded in the searching probability in the constituent parts period in statistical time range.For example, the length of statistical time range is 7 days, and the length of unit period is 1 day, and the searching probability of each unit period is respectively 0.1,0.15,0.13,0.26,0.18,0.13,0.05, corresponding searching probability vector is { 0.1,0.15,0.13,0.26,0.18,0.13,0.05}.
Then, server is determined the information entropy of searching key word in described statistical time range according to searching key word constituent parts searching probability in the period in statistical time range, and with described information entropy as the searching times degree of stability.Wherein, information entropy is the value for the identification information amount, and the probability that certain information occurs is more unstable, and corresponding information entropy is lower, and the more stable information entropy of probability of occurrence is higher, so can represent the searching times degree of stability with information entropy.The computing formula of information entropy is as follows:
H(x)=E[I(xi)]=E[log(1/p(xi))]=-∑p(xi)log(p(xi))(i=1,2,..n)
Wherein, in formula, the end of logarithm, determined to calculate the unit of the information entropy of gained.The most frequently used is take 2 the end of as, and unit is bit (bit); Employing is take e the end of as, and unit is Nat (Nat); Can also adopt other the end and unit, and can carry out unit and mutually convert.
Continue to use above-mentioned example, the computing information entropy is:
-(0.1*log0.1+0.15*log0.15+0.13*log0.13+0.26*log0.26+0.18*log0.18+0.13*log0.13+0.05*log0.05)。
Method two
At first, server is the searching times of constituent parts in the period in statistical time range according to searching key word, determines the mean value of the searching times of searching key word in statistical time range, is denoted as the first mean value.Hop count in the time of specifically can the searching times addition in the period is again divided by the unit in statistical time range with constituent parts.
Then, calculate the searching times of the constituent parts of searching key word in statistical time range in the period and the absolute value of the difference of the first mean value.
Again, calculate the mean value of above-mentioned absolute difference, be denoted as the second mean value, and with the ratio of the first mean value and the second mean value as the searching times degree of stability.
Step 103, server are determined the ageing word corresponding with statistical time range according to the searching times degree of stability in each searching key word.
Concrete, in obtaining the process of hot word, because hot word has the advantages that search rate is uprushed, therefore its searching times degree of stability in corresponding statistical time range will inevitably be lower.So server can determine that the searching times degree of stability in statistical time range is the ageing word corresponding with statistical time range less than the searching key word of certain numerical value (can be denoted as first threshold).Wherein, because the algorithm of searching times degree of stability is various, corresponding its unit and the order of magnitude are also comparatively various, and under different situations, the requirement to the searching times degree of stability of hot word is also different, thus first threshold can be as the case may be and specific algorithm set in advance.
In specific implementation process, can take the method for obtaining and preserving according to predetermined period to obtaining of hot word.For example, can be set to a week cycle, server can carry out once week about hot word and obtain, and the week before the time point that will obtain is as statistical time range, and the hot word that will get is preserved.
For the valid period of hot word, can take Preset Time length to limit, perhaps also can judge according to the search rate of corresponding hot word, if namely the search rate of corresponding hot word is lower than frequency threshold, this hot word after period in be no longer hot word.
Concrete, in the process of obtaining the words such as seasonal word, property in red-letter day word, because this class word has within corresponding season or the search rate before and after red-letter day is stable, and within other periods the unsettled characteristics of search rate, compare therefore can obtain the searching times degree of stability of searching key word in a plurality of (two or three) adjacent statistical time range.So server can judge, if the searching times degree of stability of searching key word in statistical time range is greater than the searching times degree of stability in adjacent statistical time range, and the difference of the searching times degree of stability in statistical time range and the searching times degree of stability in adjacent statistical time range determines that greater than certain numerical value (can be denoted as Second Threshold) this searching key word is the ageing word corresponding with this statistical time range.
Wherein, because the algorithm of searching times degree of stability is various, corresponding its unit or the order of magnitude are also comparatively various, and under different situations, the requirement to the searching times degree of stability of the words such as seasonal word is also different, thus Second Threshold can be as the case may be and specific algorithm set in advance.
In specific implementation process, for obtaining of seasonal word, the searching times degree of stability in former years corresponding season and adjacent season can be compared, also the searching times degree of stability in the period of equal length in period of having experienced corresponding season then and the upper season (for example can be compared, by the end of having entered the time in one month summer now, can select in spring one month as with pass by the statistical time range that this month compare summer).
Server can adopt the mode of form to preserve ageing word, and is as shown in table 2.
Table 2
Figure BSA00000634708600071
Annotate: Mei Mei, June 26 20 days to 2011 June in 2011 popular name.
After execution of step 103, server has got corresponding ageing word, server can be kept in ageing word database corresponding with statistical time range with the ageing word that gets, and can show the user by the ageing word that the residing statistical time range of current time is corresponding.
Concrete, server can show recent hot word or the words such as seasonal word, property in red-letter day word to the user in webpage.Like this, the user can search for according to corresponding ageing word, obtains the information of the commodity more relevant to demand, to save the user search time, reduces the search burden of server.
In another embodiment of the application, server can be thrown in merchandise news according to the ageing word that the application's said method gets.
(carry out according to user search request the process that merchandise news is thrown in as server) in an implementation process, server is after the searching request that receiving terminal sends, can first obtain according to this searching request the merchandise news for the treatment of displaying merchandise, then improve the displaying priority for the treatment of displaying merchandise that has ageing word in merchandise news, then throw according to the merchandise news that the displaying priority for the treatment of displaying merchandise is treated displaying merchandise.for example, the user is in the process of carrying out commercial articles searching, send searching request by terminal to server, searching key word wherein is " fashion dress ornament ", after server receives this searching request, obtain corresponding Search Results (namely treating displaying merchandise), if be winter at that time, and this season, corresponding seasonal word comprised " down jackets ", " woollen overcoat ", " leather and fur ", server is in treating displaying merchandise, the displaying priority for the treatment of displaying merchandise that has these ageing words in merchandise news is increased default numerical value, and determine to treat putting in order of displaying merchandise according to the displaying priority after adjusting, carrying out corresponding merchandise news throws in.
In another implementation process (as the process that server receives login or the browse request rear line carries out the merchandise news input), server can be thrown in the merchandise news with ageing word.Concrete, when the user signed in to server, server can with the form of Recommendations, have the merchandise news of ageing word to user's input.For example, current hot word comprises " iphone4 ", " mac book ", server can the pop-up window after user's Website login in, the information of throwing in merchandise news the commodity of words such as comprising " iphone4 ", " mac book " to the user.
The embodiment of the present application, server obtains constituent parts searching times period in of each searching key word in statistical time range, the searching times of constituent parts in the period according to searching key word in statistical time range, determine the searching times degree of stability of searching key word in statistical time range, again according to the searching times degree of stability of determining, determine the ageing word corresponding with statistical time range in each searching key word, can reduce the complexity of ageing word acquisition process and improve and obtain efficient.
As shown in Figure 2, the acquisition methods of the ageing word that it provides for the embodiment of the present application in concrete application scenarios flow process, specifically comprise the following steps:
Step 201, server stores user's inquiry log, this inquiry log are the user searches for the search statement of time input and corresponding search time.
Step 202, server carries out word segmentation processing to search statement, and search statement is resolved into a plurality of searching key words, according to the unit period, each searching key word is carried out searching probability and adds up, and obtains the searching probability vector of constituent parts in the period in statistical time range.
Step 203, server calculates the information entropy of searching key word in statistical time range according to the searching probability vector.In the process that hot word obtains, statistical time range can be selected week to one month, and the unit period can be selected one day; In the process that seasonal word obtains, statistical time range can be selected a season, and the unit period can be selected a week.
Step 204, server are determined the ageing word in searching key word according to the information entropy of each searching key word in statistical time range.When obtaining hot word, can determine that information entropy is hot word less than the searching key word of first threshold; When obtaining seasonal word, can choose the information entropy of adjacent statistical time range and the information entropy of current statistical time range compares, if the information entropy of current statistical time range is greater than the information entropy of adjacent statistical time range, and difference determines that greater than Second Threshold this searching key word is seasonal word.
Step 205, server are carried out the displaying of merchandise news according to ageing word, and ageing word is showed the user.
The embodiment of the present application, server obtains constituent parts searching times period in of each searching key word in statistical time range, the searching times of constituent parts in the period according to searching key word in statistical time range, determine the searching times degree of stability of searching key word in statistical time range, again according to the searching times degree of stability of determining, determine the ageing word corresponding with statistical time range in each searching key word, can reduce the complexity of ageing word acquisition process and improve and obtain efficient.
Based on identical technical conceive, the embodiment of the present application also provides a kind of ageing word deriving means, and as shown in Figure 3, this device can comprise:
Acquisition module 310 is used for obtaining each searching key word at the searching times of constituent parts in the period of statistical time range;
The first determination module 320 is used for according to constituent parts searching times period in of searching key word at statistical time range, determines the searching times degree of stability of described searching key word in described statistical time range;
The second determination module 330 is used for according to described searching times degree of stability, determines the ageing word corresponding with described statistical time range in each searching key word.
Preferably, described the first determination module 320 specifically is used for:
The searching times of constituent parts in the period according to searching key word in statistical time range, and the total searching times of described searching key word in statistical time range are determined constituent parts searching probability period in of described searching key word in described statistical time range;
According to described searching key word constituent parts searching probability in the period in described statistical time range, determine the information entropy of described searching key word in described statistical time range, and with described information entropy as described searching times degree of stability.
Preferably, described the second determination module 330 specifically is used for:
Determine that the searching times degree of stability in described statistical time range is the ageing word corresponding with described statistical time range less than the searching key word of first threshold; Perhaps,
Determine that searching times degree of stability in statistical time range is greater than the searching times degree of stability in adjacent statistical time range, and the difference of the searching times degree of stability in statistical time range and searching times degree of stability in described adjacent statistical time range is greater than Second Threshold, searching key word be the ageing word corresponding with this statistical time range.
Preferably, also comprise display module, be used for the ageing word that the residing statistical time range of current time is corresponding and show the user.
Provide a kind of merchandise news delivery device that is connected with the described ageing word deriving means of above-described embodiment at another embodiment of the application, comprise: the information putting module is used for according to the ageing word that described ageing word deriving means obtains, merchandise news being thrown in.
Preferably, also comprise receiver module, be used for the searching request that receiving terminal sends, and obtain the merchandise news for the treatment of displaying merchandise according to described searching request;
Described information putting module specifically is used for:
Improve the displaying priority for the treatment of displaying merchandise that has described ageing word in merchandise news;
Treat the merchandise news of displaying merchandise throws according to the displaying priority for the treatment of displaying merchandise.
Preferably, described information putting module is specifically thrown in for the merchandise news that will have described ageing word.
The embodiment of the present application, server obtains constituent parts searching times period in of each searching key word in statistical time range, the searching times of constituent parts in the period according to searching key word in statistical time range, determine the searching times degree of stability of searching key word in statistical time range, again according to the searching times degree of stability of determining, determine the ageing word corresponding with statistical time range in each searching key word, can reduce the complexity of ageing word acquisition process and improve and obtain efficient.
It will be appreciated by those skilled in the art that the module in the device in embodiment can be distributed in the device of embodiment according to the embodiment description, also can carry out respective change and be arranged in the one or more devices that are different from the present embodiment.The module of above-described embodiment can be merged into a module, also can further split into a plurality of submodules.
Above-mentioned the embodiment of the present application sequence number does not represent the quality of embodiment just to description.
Through the above description of the embodiments, those skilled in the art can be well understood to the application and can realize by the mode that software adds essential general hardware platform, can certainly pass through hardware, but in a lot of situation, the former is better embodiment.Based on such understanding, the part that the application's technical scheme contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in a storage medium, comprise that some instructions are with so that a station terminal equipment (can be mobile phone, personal computer, server, the perhaps network equipment etc.) carry out the described method of each embodiment of the application.
The above is only the application's preferred implementation; should be pointed out that for those skilled in the art, under the prerequisite that does not break away from the application's principle; can also make some improvements and modifications, these improvements and modifications also should be looked the application's protection domain.

Claims (10)

1. the acquisition methods of an ageing word, is characterized in that, comprising:
Obtain constituent parts searching times period in of each searching key word in statistical time range;
The searching times of constituent parts in the period according to searching key word in statistical time range determined the searching times degree of stability of described searching key word in described statistical time range;
According to described searching times degree of stability, determine the ageing word corresponding with described statistical time range in each searching key word.
2. the method for claim 1, is characterized in that, described according to searching key word the searching times of constituent parts in the period in statistical time range, determine the searching times degree of stability of described searching key word in described statistical time range, be specially:
Searching times and the described searching key word total searching times in statistical time range of constituent parts according to searching key word in statistical time range in the period determined constituent parts searching probability period in of described searching key word in described statistical time range;
According to described searching key word constituent parts searching probability in the period in described statistical time range, determine the information entropy of described searching key word in described statistical time range, and with described information entropy as described searching times degree of stability.
3. the method for claim 1, is characterized in that, and is described according to described searching times degree of stability, determines to be specially the ageing word corresponding with described statistical time range in each searching key word:
Determine that the searching times degree of stability in described statistical time range is the ageing word corresponding with described statistical time range less than the searching key word of first threshold; Perhaps,
Determine that searching times degree of stability in statistical time range is greater than the searching times degree of stability in adjacent statistical time range, and the difference of the searching times degree of stability in statistical time range and searching times degree of stability in described adjacent statistical time range is greater than Second Threshold, searching key word be the ageing word corresponding with this statistical time range.
4. the method for claim 1, it is characterized in that, described according to described searching times degree of stability, determine the ageing word corresponding with described statistical time range in each searching key word after, also comprise: the ageing word that the residing statistical time range of current time is corresponding shows the user.
5. the ageing word that obtains of an application such as the described method of claim 1-4 any one carries out the method that merchandise news is thrown in, and it is characterized in that, according to the ageing word that obtains, merchandise news is thrown in.
6. method as claimed in claim 5, is characterized in that, also comprises: the searching request that receiving terminal sends, and obtain the merchandise news for the treatment of displaying merchandise according to described searching request;
The ageing word that described basis is obtained is thrown in merchandise news, is specially:
Improve the displaying priority for the treatment of displaying merchandise that has described ageing word in merchandise news;
Treat the merchandise news of displaying merchandise throws according to the displaying priority for the treatment of displaying merchandise.
7. method as claimed in claim 5, is characterized in that, the ageing word that described basis is obtained is thrown in merchandise news, is specially:
The merchandise news that will have described ageing word is thrown in.
8. an ageing word deriving means, is characterized in that, comprising:
Acquisition module is used for obtaining each searching key word at the searching times of constituent parts in the period of statistical time range;
The first determination module is used for according to constituent parts searching times period in of searching key word at statistical time range, determines the searching times degree of stability of described searching key word in described statistical time range;
The second determination module is used for according to described searching times degree of stability, determines the ageing word corresponding with described statistical time range in each searching key word.
9. device as claimed in claim 8, is characterized in that, described the first determination module specifically is used for:
Searching times and the described searching key word total searching times in statistical time range of constituent parts according to searching key word in statistical time range in the period determined constituent parts searching probability period in of described searching key word in described statistical time range;
According to described searching key word constituent parts searching probability in the period in described statistical time range, determine the information entropy of described searching key word in described statistical time range, and with described information entropy as described searching times degree of stability.
10. device as claimed in claim 8, is characterized in that, described the second determination module specifically is used for:
Determine that the searching times degree of stability in described statistical time range is the ageing word corresponding with described statistical time range less than the searching key word of first threshold; Perhaps,
Determine that searching times degree of stability in statistical time range is greater than the searching times degree of stability in adjacent statistical time range, and the difference of the searching times degree of stability in statistical time range and searching times degree of stability in described adjacent statistical time range is greater than Second Threshold, searching key word be the ageing word corresponding with this statistical time range.
CN201110413881.6A 2011-12-13 2011-12-13 Method and device for acquiring time-efficient words Active CN103164424B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110413881.6A CN103164424B (en) 2011-12-13 2011-12-13 Method and device for acquiring time-efficient words

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110413881.6A CN103164424B (en) 2011-12-13 2011-12-13 Method and device for acquiring time-efficient words

Publications (2)

Publication Number Publication Date
CN103164424A true CN103164424A (en) 2013-06-19
CN103164424B CN103164424B (en) 2017-05-10

Family

ID=48587519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110413881.6A Active CN103164424B (en) 2011-12-13 2011-12-13 Method and device for acquiring time-efficient words

Country Status (1)

Country Link
CN (1) CN103164424B (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104217033A (en) * 2014-09-29 2014-12-17 北京奇虎科技有限公司 Search method and device based on timeliness
CN104346354A (en) * 2013-07-29 2015-02-11 阿里巴巴集团控股有限公司 Method and device for providing recommendation word
WO2018157332A1 (en) * 2017-03-01 2018-09-07 深圳市博信诺达经贸咨询有限公司 Statistical method and system applied to big data
CN109947713A (en) * 2017-10-31 2019-06-28 北京国双科技有限公司 A kind of monitoring method and device of log
CN109976984A (en) * 2017-12-27 2019-07-05 Tcl集团股份有限公司 The statistical method and device of user data
CN110750682A (en) * 2018-07-06 2020-02-04 武汉斗鱼网络科技有限公司 Title hot word automatic metering method, storage medium, electronic equipment and system
CN111435374A (en) * 2019-01-11 2020-07-21 百度在线网络技术(北京)有限公司 Display device and method for searching statistical data
CN111488516A (en) * 2019-01-28 2020-08-04 北京字节跳动网络技术有限公司 Searching method and device based on aging words
CN112445892A (en) * 2019-09-02 2021-03-05 百度在线网络技术(北京)有限公司 Method and device for determining brand mentioning rate, electronic equipment and storage medium
CN115757923A (en) * 2023-01-09 2023-03-07 北京创新乐知网络技术有限公司 Method and device for determining search hot words, computer equipment and storage medium
CN116894118A (en) * 2023-09-08 2023-10-17 腾讯科技(深圳)有限公司 Data searching method, device, equipment and storage medium

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923544A (en) * 2009-06-15 2010-12-22 北京百分通联传媒技术有限公司 Method for monitoring and displaying Internet hot spots

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101923544A (en) * 2009-06-15 2010-12-22 北京百分通联传媒技术有限公司 Method for monitoring and displaying Internet hot spots

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李渝勤等: "面向互联网舆情的热词分析技术", 《第六届全国信息检索学术会议论文集》 *

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10423664B2 (en) 2013-07-29 2019-09-24 Alibaba Group Holding Limited Method and system for providing recommended terms
CN104346354A (en) * 2013-07-29 2015-02-11 阿里巴巴集团控股有限公司 Method and device for providing recommendation word
CN104346354B (en) * 2013-07-29 2017-12-01 阿里巴巴集团控股有限公司 It is a kind of that the method and device for recommending word is provided
CN104217033B (en) * 2014-09-29 2017-11-07 北京奇虎科技有限公司 Based on ageing searching method and device
CN104217033A (en) * 2014-09-29 2014-12-17 北京奇虎科技有限公司 Search method and device based on timeliness
WO2018157332A1 (en) * 2017-03-01 2018-09-07 深圳市博信诺达经贸咨询有限公司 Statistical method and system applied to big data
CN109947713B (en) * 2017-10-31 2021-08-10 北京国双科技有限公司 Log monitoring method and device
CN109947713A (en) * 2017-10-31 2019-06-28 北京国双科技有限公司 A kind of monitoring method and device of log
CN109976984A (en) * 2017-12-27 2019-07-05 Tcl集团股份有限公司 The statistical method and device of user data
CN110750682A (en) * 2018-07-06 2020-02-04 武汉斗鱼网络科技有限公司 Title hot word automatic metering method, storage medium, electronic equipment and system
CN110750682B (en) * 2018-07-06 2022-08-16 武汉斗鱼网络科技有限公司 Title hot word automatic metering method, storage medium, electronic equipment and system
CN111435374A (en) * 2019-01-11 2020-07-21 百度在线网络技术(北京)有限公司 Display device and method for searching statistical data
CN111435374B (en) * 2019-01-11 2023-04-25 百度在线网络技术(北京)有限公司 Display device and method for searching statistical data
CN111488516A (en) * 2019-01-28 2020-08-04 北京字节跳动网络技术有限公司 Searching method and device based on aging words
CN112445892A (en) * 2019-09-02 2021-03-05 百度在线网络技术(北京)有限公司 Method and device for determining brand mentioning rate, electronic equipment and storage medium
CN112445892B (en) * 2019-09-02 2023-09-29 百度在线网络技术(北京)有限公司 Method, device, electronic equipment and storage medium for determining brand mention rate
CN115757923A (en) * 2023-01-09 2023-03-07 北京创新乐知网络技术有限公司 Method and device for determining search hot words, computer equipment and storage medium
CN116894118A (en) * 2023-09-08 2023-10-17 腾讯科技(深圳)有限公司 Data searching method, device, equipment and storage medium
CN116894118B (en) * 2023-09-08 2023-12-22 腾讯科技(深圳)有限公司 Data searching method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN103164424B (en) 2017-05-10

Similar Documents

Publication Publication Date Title
CN103164424A (en) Method and device for acquiring time-efficient words
US11580168B2 (en) Method and system for providing context based query suggestions
KR101700585B1 (en) On-line product search method and system
CN104143005B (en) A kind of related search system and method
WO2016107523A1 (en) Access path analysis method and apparatus for website
US20140025701A1 (en) Query expansion
CN105631707A (en) Advertisement click rate estimation method based on decision tree, application recommendation method and device
US11061948B2 (en) Method and system for next word prediction
CN105989373B (en) The acquisition device-fingerprint method and device realized using training pattern
CN105095625B (en) Clicking rate prediction model method for building up, device and information providing method, system
CN103226393A (en) Input method and equipment
CN106779825A (en) A kind of item recommendation method, device and electronic equipment
CN113412608B (en) Content pushing method and device, server and storage medium
CN103870553B (en) A kind of input resource supplying method and system
US10146872B2 (en) Method and system for predicting search results quality in vertical ranking
US20150169606A1 (en) Contextual based search suggestion
CN103309869A (en) Method and system for recommending display keyword of data object
CN105894310A (en) Personalized recommendation method
CN104572717A (en) Information searching method and device
CN106126589A (en) Resume searching method and device
CN106817390B (en) User data sharing method and device
CN105183464A (en) Information display method and device and electronic equipment
CN103020141A (en) Method and equipment for providing searching results
CN105138536B (en) Mobile social networking data fragmentation method based on Directed Hypergraph
CN103810210B (en) Search result display methods and device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 1182783

Country of ref document: HK

GR01 Patent grant
GR01 Patent grant
REG Reference to a national code

Ref country code: HK

Ref legal event code: GR

Ref document number: 1182783

Country of ref document: HK