[specific embodiment]
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram for the information processing method that one embodiment of the invention provides.As shown in Figure 1, this method packet
It includes:
101, the historical search amount data of pending data object are obtained.
102, according to above-mentioned historical search amount data, user's attention rate variation tendency of pending data object is obtained.
103, according to above-mentioned user's attention rate variation tendency, reference policy information is generated.
104, above-mentioned reference policy information is exported, to instruct user to handle data object to be processed.
The present embodiment provides a kind of information processing methods, can be executed by information processing unit, to be based on data object
Historical search amount data instruct user to handle data object, a kind of new instruct user to data object to provide
The mode handled.
Illustrate first, the data object for needing that user is instructed to handle is known as pending data object by the present embodiment.
The present embodiment does not limit the form of pending data object, such as can be merchandise items, such as mobile phone, computer, books, clothes
Or cosmetics etc., it can also be the stage property in types of applications, be also possible to various financial products, such as stock or fund etc..
With the development of search engine technique, it is interested that user can search for news, information or user by search engine
The information such as data object.Wherein, by analyzing search log, and the mark of combined data object, such as title, generation
Code etc., can obtain volumes of searches of the arbitrary data object in arbitrary period, may be simply referred to as historical search amount data.With to be processed
It, then can be by analyzing search log for data object is stock, and the title and code of stock to be processed are combined,
Volumes of searches data of the every stock in arbitrary period can be obtained.For example, the stock of the stock markets of Shanghai code 600036 of China Merchants Bank
In the volumes of searches data that on June 8,20 days to 2015 October in 2014 is daily, as shown in Figure 2.
Volumes of searches data of the pending data object in a certain period reflect the pending data object to a certain extent
The degree paid close attention to by user, referred to as user's attention rate.Present inventor considers that one is asked in actual application
Topic: whether these volumes of searches data can be converted to the reference policy information when pending data object is handled user.
To solve this problem, inventor has carried out a series of researchs to mass data object, the main history for studying different data object
Correlation between volumes of searches data and the history service data of the data object.
By taking stock as an example, the history service data of stock are primarily referred to as historical stock price.Inventor passed through in October, 2014
- 2015 years on the 20th June 8, correlation of the Shanghai and Shenzhen A-share between the totally 2733 stock amount of scanning for data and share price are divided
Analysis, it is found that the volumes of searches of 97.4% stock is positively correlated with share price, average correlation 0.607.Higher positive correlation card
Stock invester is illustrated to contact the attention rate and share price of personal share there is very strong, when personal share stock price rising, volumes of searches is generally also
It can rise accordingly.It can be seen that volumes of searches data can give user's guidance of agiotage as stock price information, therefore
User can be instructed to trade security based on historical search amount data.
By the research of the correlation between the historical search amount data and history service data to mass data object, hair
Bright people's discovery: there is certain correlation between the historical search amount data of data object and history service data.Then, this implementation
Example can generate reference policy information, based on the historical search amount data of pending data object to instruct user to number to be processed
It is handled according to object.
Specifically, information processing unit obtain pending data object historical search amount data after, can basis
The historical search amount data of pending data object obtain user's attention rate variation tendency of pending data object;According to
User's attention rate variation tendency of data object is handled, reference policy information is generated, exports the reference policy information later, to refer to
User is led to handle data object to be processed.
It is worth noting that according to the difference of pending data object, it may be necessary to the history that different historical periods generate
Volumes of searches data.For example, it may be the historical search amount data that historical juncture A is generated to historical juncture B this historical period, or
Person is also possible to the historical search amount data that historical juncture A is generated to this historical period of current time.
From the foregoing, it can be seen that the present embodiment generates reference policy information using the historical search amount data of data object, it is different
In history service data in the prior art, a kind of new mode for instructing user to handle data object is provided, it is full
Sufficient user demand.
In an optional embodiment, in the historical search amount data according to pending data object, number to be processed is obtained
Before user's attention rate variation tendency of object, historical search amount data can also be filtered, to remove non-effective
The volumes of searches data generated in historical period.Still by taking stock as an example, stock is general only to trade on weekdays, then working day can
The referred to as day of trade, and in Saturday day and legal festivals and holidays generally without transaction, therefore can be described as with the legal festivals and holidays day Saturday non-
The day of trade.Wherein, compared with the volumes of searches in nontransaction day, concern of the user to stock can more be highlighted in the volumes of searches of the day of trade
Therefore degree can remove the volumes of searches data generated in nontransaction day, only retain from used historical search amount data
In the volumes of searches data that the day of trade generates, be conducive to the precision for improving volumes of searches data, and then improve the finger of reference policy information
Lead precision.
Further, it for the more intuitive user's attention rate variation tendency for indicating pending data object, can use
Different indexs handles the historical search amount data of data object to be processed, ties to obtain concise clearly show
Fruit.
Wherein, a kind of index is index rolling average (Exponential Moving Average, EMA):
Based on EMA index, a kind of historical search amount data according to pending data object obtain pending data object
User's attention rate variation tendency embodiment, comprising:
The historical search amount data generated within the first setting period are carried out to refer to EMA processing, it is to be processed to obtain reflection
First EMA line of user's attention rate variation tendency of data object, and to the historical search amount generated within the second setting period
Data carry out EMA processing, to obtain the 2nd EMA line of user's attention rate variation tendency of reflection pending data object, wherein
The length of first setting period less than the second setting period length, which means that the first EMA line can regard short-term EMA line as,
2nd EMA line can regard long-term EMA line as.
In the present embodiment, moving average analysis is using the principle of statistically rolling average, to daily volumes of searches
Data average processing, to eliminate accidental fluctuation.EMA line is to use moving average analysis method, will be in one period
The average value of historical search amount data is linked to be curve, for showing the fluctuation situation of historical search amount, and then reflects that user treats
Handle the attention rate situation of change and variation tendency of data object.
Since the time is closer to current time, the information content of historical search amount data should be bigger, and index is mobile flat
Equal line considers this point, and successively decreasing to weight with exponential form carries out rolling average, and calculation formula is as follows:
EMA(N)t=k*Pt+(1-k)*EMA(N)t-1 (1)
Wherein, EMA (N) is indicatedtIndicate the EMA value of t moment;EMA(N)t-1Indicate the EMA value at t-1 moment;N is to produce
The time span of raw historical search amount data, such as N days or N hours etc.;K is Smoothness Index.The EMA value at each moment is drawn
System forms EMA line.
By taking stock as an example, Fig. 3 a shows the corresponding first EMA line of historical search amount data and the 2nd EMA line of stock, figure
3a clearly shows the situation of change and trend of historical search amount data.In fig. 3 a, the first EMA line is dotted line, when being that N takes 12
Equal line;2nd EMA line is solid line, is equal line when N takes 26.In addition, Fig. 3 b shows the volatility signal of the branch stock
Figure.Fig. 3 a is compared with Fig. 3 b as it can be seen that the first EMA line and the 2nd EMA line and volatility trend are substantially consistent, is met
The conclusion with positive correlation of foregoing description.
Based on EMA index, a kind of user's attention rate variation tendency according to pending data object generates reference policy letter
The embodiment of breath, comprising:
If the first EMA line passes through the 2nd EMA line from lower to upper, the reference that instruction user obtains pending data object is generated
Policy information;
If the first EMA line passes through the 2nd EMA line from top to bottom, the reference that instruction user produces pending data object is generated
Policy information.
By taking stock as an example, the first EMA line passes through the 2nd EMA line from lower to upper, it is meant that share price goes up, and can then suggest
User buys in the branch stock, then generates the reference policy information that instruction user buys in the branch stock;If the first EMA line on toward
Under pass through the 2nd EMA line, it is meant that falling stock prices can then suggest that user sells the branch stock, then generate instruction user
Sell the reference policy information of the branch stock.For stock, reference policy information be primarily referred to as buying in or sell stock when
Machine signal.
Another index is: exponential smoothing similarities and differences rolling average (Moving Average Convergence
Divergence, MACD):
Based on MACD index, a kind of historical search amount data according to pending data object obtain pending data pair
The embodiment of user's attention rate variation tendency of elephant, comprising:
MACD processing is carried out to the historical search amount data of data object to be processed, reflects pending data object to obtain
User's attention rate variation tendency MACD line.
Wherein, MACD index is mainly based upon to point for polymerizeing with separating situation between short-term EMA line and long-term EMA line
Analysis, MACD index had both considered the tendency of data fluctuations, while can also characterize the degree of strength of fluctuation.In the present embodiment,
MACD is used in historical search amount data, output can show whether pending data object (can by user's concern
Indicated by the size of its MACD value), while can also show the variation tendency of its user's attention rate, i.e., user's attention rate by
Gradual change is strong or dies down.
Wherein, the specific calculating process of MACD value is as follows:
Calculate short-term EMA1 and long-term EMA2;Calculating about EMA1 and long-term EMA2 can be found in above-mentioned formula (1);
Calculate deviation value DIFF=EMA1-EMA2;
Calculate the EMA value of DIFF, i.e. DEA value;
Calculate MACD value=2* (DIFF-DEA).
Curve is drawn based on calculated each MACD value, obtains MACD line.For MACD line, column can choose
The height of line, columnar alignment indicates MACD value.Still by taking stock as an example, reflect the MACD line of user's attention rate variation tendency of stock such as
Shown in Fig. 4.
Based on MACD index, a kind of user's attention rate variation tendency according to pending data object generates reference policy
A kind of embodiment of information, comprising:
If above-mentioned MACD line generates the reference policy information that instruction user obtains pending data object from just becoming negative;
If MACD line is become just, generating the reference policy information that instruction user produces pending data object from negative.
By taking stock as an example, if above-mentioned MACD line from just becoming negative (i.e. in Fig. 4 from dark color become light color), indicate stock by
Attention rate is weaker, it is meant that share price will drop, therefore can suggest that user sells the branch stock, then generate instruction user and sell
The reference policy information of the branch stock;If MACD line becomes positive (i.e. becoming dark from light color in Fig. 4) from negative, indicate stock by
Attention rate is stronger, it is meant that share price will rise, therefore can suggest that user buys in the branch stock, then generates instruction user and buys in this
The reference policy information of branch stock.
Another index is: relatively strong and weak index (Relative Strength Index, RSI):
Based on RSI index, a kind of historical search amount data according to pending data object obtain pending data object
User's attention rate variation tendency embodiment, including
RSI processing is carried out to the historical search amount data of data object to be processed, reflects pending data object to obtain
User's attention rate variation tendency the first RSI line.
In the present embodiment, RSI index is used in historical search amount data, to show pending data object
The strong and weak situation and variation tendency of user's attention rate.
The specific calculating process of RSI index is as follows:
The historical search amount data generated in continuous n+1 days including the same day are first found out, with daily historical search
Amount data subtract historical search amount data on the one, available n difference;The sum of the positive number in n difference is calculated, as
A, and the absolute value for the sum of calculating the negative in n difference, as B;(2) calculate RSI value according to the following equation.
RSI=A/ (A+B) (2)
By above-mentioned formula (2) it is found that the amplitude Zhan that RSI index, which is actually, indicates that historical search amount data fluctuate upwards is total
The percentage of fluctuation, ratio mean that more greatly user's attention rate is stronger, and ratio is smaller to mean that user's attention rate is weaker.
Based on above-mentioned RSI index, a kind of user's attention rate variation tendency according to pending data object generates and refers to plan
The slightly embodiment of information, comprising:
If the first RSI line is greater than the first upper limit threshold line, the reference plan that instruction user produces pending data object is generated
Slightly information;
If the first RSI line generates the reference policy that instruction user buys in pending data object less than the first lower limit thresholding
Information.
Above-mentioned first upper limit thresholding and the first lower limit thresholding are generally different, but can also be identical.For example, first upper limit
Thresholding is 70%, and the first lower limit thresholding can be 30%, but not limited to this.
By taking stock as an example, when in the historical search amount data for RSI index being used in stock, value shows personal share
User's attention rate strong and weak situation: when the RSI value of historical search amount data is excessively high, be greater than default first upper limit door
Limit, illustrates that user's attention rate of personal share is very high, currently has excessive investor and buy in, later may be that the share price is charged
Final stage, and lead to the failure of later period share price kinetic energy, it is to see empty signal, then suggests that user sells the stock, then generates
Indicate that user sells the reference policy information of the branch stock;Otherwise similarly.
In the above-described embodiment, the reference policy information for instructing user to handle data object to be processed in generation
When, this parameter of historical search amount data is only accounted for, but not limited to this.For example, can by historical search amount data with wait locate
The history service data of reason data object are combined, and comprehensively consider historical search amount data and history service data, generation refer to
Lead the reference policy information that user handles data object to be processed.
Based on a kind of above-mentioned, user's attention rate variation tendency according to pending data object, reference policy information is generated
Embodiment, comprising:
According to the history service data of pending data object, the business datum variation for obtaining pending data object becomes
Gesture;
Analysis is associated to user's attention rate variation tendency and business datum variation tendency, to generate reference policy letter
Breath.
It, equally can be using above-mentioned each in the embodiment for comprehensively considering historical search amount data and history service data
Index handles the historical search amount data and history service data of data object to be processed, concise clear to obtain
Displaying as a result, to it is more intuitive indicate pending data object user's attention rate variation tendency and business datum variation
Trend.
In one embodiment, can based on MACD index to the historical search amount data of data object to be processed and
History service data are handled, referred to as MACD interleaved scheme.Then, a kind of historical search amount according to pending data object
Data, the process for obtaining user's attention rate variation tendency of pending data object include: to carry out to the historical search amount data
MACD processing, to obtain the MACD line of reflection user's attention rate variation tendency.Correspondingly, a kind of according to pending data object
History service data, obtain pending data object business datum variation tendency process include: to history service data into
Row MACD processing, to obtain the DIFF line and DEA line of reflection business datum variation tendency.
Based on above-mentioned, a kind of pair of user's attention rate variation tendency and business datum variation tendency are associated analysis, with life
Include: at the process of reference policy information
MACD line, DIFF line and DEA line are compared;
If wearing DEA line on DIFF line, and MACD line is positive or MACD line is become just by negative, and DIFF line is located on DEA line
Side generates the reference policy information that instruction user obtains pending data object;
If wearing DEA line under DIFF line, and MACD is negative or MACD line is by just becoming negative, and DIFF line is located under DEA line
Side generates the reference policy information that instruction user produces pending data object.
By taking stock as an example, Fig. 5 show in the MACD line of user's attention rate variation tendency of reflection stock and anti-is shown
Reflect the DIFF line and DEA line of the change of stock price trend.In Fig. 5, columnar alignment indicates that MACD, dotted line indicate share price DEA line, solid line table
Show share price DIFF line.According to above-mentioned principle, a dealing timing signals section is found in Fig. 5, it can be found that using the MACD
Interleaved scheme successfully avoids many invalid dealing timing signals points, improves the essence of reference policy information generated
Degree is conducive to that user is preferably instructed to carry out stock exchange.Meanwhile Fig. 3 b shows the change of stock price curve of the branch stock.It will
Fig. 5 as it can be seen that MACD line, DIFF line and DEA line and volatility trend are substantially consistent, meets foregoing description compared with Fig. 3 b
The conclusion with positive correlation.
In one embodiment, can based on RSI index to the historical search amount data of data object to be processed and
History service data are handled, referred to as RSI interleaved scheme.Then, a kind of historical search amount according to pending data object
Data, the process for obtaining user's attention rate variation tendency of pending data object include: to carry out RSI to historical search amount data
Processing, to obtain the first RSI line of reflection user's attention rate variation tendency.Correspondingly, a kind of according to pending data object
History service data, obtain pending data object business datum variation tendency process include: to history service data into
Row RSI processing, to obtain the 2nd RSI line of reflection business datum variation tendency.
Based on above-mentioned, a kind of pair of user's attention rate variation tendency and business datum variation tendency are associated analysis, with life
Include: at the process of reference policy information
If the first RSI line is greater than the first upper limit thresholding, and the 2nd RSI line is greater than the second upper limit thresholding, generates instruction user
Produce the reference policy information of pending data object;
If the first RSI line is less than the first lower limit thresholding, and the 2nd RSI line generates instruction user less than the second lower limit thresholding
Buy in the reference policy information of pending data object.
By taking stock as an example, Fig. 6 shows the first RSI line and reflection share price of user's attention rate variation tendency of reflection stock
2nd RSI line of variation tendency.In Fig. 6, dotted line indicates volumes of searches RSI line, i.e. the first RSI line;Solid line indicates share price RSI,
That is the 2nd RSI line.One dealing timing signals section is shown, which can also successfully screen in Fig. 6
Point when reasonably selecting out is conducive to that user is instructed to trade security.Meanwhile Fig. 3 b shows the change of stock price song of the branch stock
Line.Fig. 6 is compared with Fig. 3 b as it can be seen that the first RSI line, the 2nd RSI line and volatility trend are substantially consistent, is met aforementioned
The conclusion with positive correlation of description.
User is instructed to treat place it is worth noting that can not only provide using MACD interleaved scheme and RSI interleaved scheme
The reference policy information that reason data object is handled, and the precision of reference policy information can be improved, be conducive to user
Processing is carried out to data object to be processed, accuracy or the higher instruction of precision are provided, is conducive to user and reasonably treat place
Reason data object is handled.
To illustrate that MACD interleaved scheme and RSI interleaved scheme have the advantage that, with technical scheme below the application
For in stock application, by setting measurement index, and illustrate by experimental data the beneficial effect of technical scheme.
It in an experiment, is that totally 2733 stocks observe this Shen as the statistics of bulk sample this progress applicable cases using Shanghai and Shenzhen A-share
It please two kinds of interleaved scheme bring beneficial effects.
Firstly, the concept in definition dealing period.The application will issue a new signal of buying and start, until next adjacent
Until selling signal, as a dealing period.Based on dealing two measurement indexs of period definition:
Index 1: effectively reducing the personal share ratio (do not include equal) of dealing periodicity, i.e., with the existing guidance based on share price
Scheme is compared, and the percentage of stock sum is accounted for using the number of share of stock that above-mentioned interleaved scheme can reduce the dealing period.
Index 2: the personal share ratio (not including equal) of earning rate is effectively improved in the sample phase, that is, is calculated in the entire sample phase
The number of share of stock that section earning rate improves accounts for the ratio of stock sum.
Above-mentioned two index is counted, result shown in table 1 is obtained.
Table 1
|
RSI intersects |
MACD intersects |
Index 1 (%) |
31.77 |
89.3 |
Index 2 (%) |
27.71 |
41.36 |
As shown in Table 1 it is found that compared with the existing scheme for instructing user to trade security based on share price, using the intersection side RSI
Case, can make 31.77% stock reduce dealing periodicity, and can make 27.71% stock section earning rate
It improves.As shown in Table 1 it is found that compared with the existing scheme for instructing based on share price user to trade security, using MACD interleaved scheme,
89.3% stock can be made to reduce dealing periodicity, and the section earning rate of 41.36% stock can be made to increase.
In addition, the application also defines the concept of opposite winning rate, i.e., existing use is greater than using the winning rate that interleaved scheme generates
The number of share of stock for the winning rate that share price generates and the ratio of stock sum.The present embodiment is only considered as interleaved scheme and adopts compared to existing
The case where being promoted with share price scheme winning rate do not consider in the case of identical for two schemes winning rate, but not limited to this.
Winning rate is referred to, to every stock be respectively adopted interleaved scheme and it is existing instructed using the scheme of share price,
Obtain winning rate of the stock under different schemes.In the instruction course of every kind of scheme, to the Dealing Signal issued each time, I
Observe the stock 5 days thereafter earning rate situations, and roughly " will buy 5 days earning rates after signal issues to be positive " and " sell letter
Number issue after 5 days earning rates be negative " statistics for victory, otherwise be negative.Then, all victory of the stock and all negative numbers are counted,
And then the final winning rate of the stock is obtained divided by total degree with the number of victory.Above-mentioned opposite winning rate is counted, 2 institute of table is obtained
Show result.
Table 2
|
RSI intersects |
MACD intersects |
Opposite winning rate % |
48.43 |
45.50 |
As shown in Table 2 it is found that compared with the existing scheme for instructing user to trade security based on share price, using the intersection side RSI
Case can be such that the winning rate of 48.43% stock is promoted;Using MACD scheme, the winning rate of 45.50% stock can be made to have
It is promoted.
The comparison effect for observing different indexs above, it can be found that the application combines volumes of searches data and stock price information
It uses, there is preferable improvement really, on the one hand can reduce the frequency of dealing timing signals, on the other hand will not throw
The investment return of money person, or even there is certain may be because to filter out wrong dealing timing signals and promote investment return.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
Fig. 7 is the structural schematic diagram for the information processing unit that one embodiment of the invention provides.As shown in fig. 7, the device packet
Include: first, which obtains module 71, second, obtains module 72, generation module 73 and output module 74.
First obtains module 71, for obtaining the historical search amount data of pending data object.
Second obtains module 72, for obtaining the historical search amount data that module 71 obtains according to first, obtains to be processed
User's attention rate variation tendency of data object.
Generation module 73 generates for obtaining user's attention rate variation tendency that module 72 obtains according to second and refers to plan
Slightly information.
Output module 74, for exporting the reference policy information of the generation of generation module 73, to instruct user to above-mentioned wait locate
Reason data object is handled.
In an optional embodiment, as shown in figure 8, the device further include: filtering module 75.
Filtering module 75 obtains the historical search amount number that module 71 obtains according to first for obtaining module 72 second
According to, obtain pending data object user's attention rate variation tendency before, to first obtain module 71 obtain historical search
Amount data are filtered, to remove the volumes of searches data generated in non-effective historical period.
In an optional embodiment, generation module 73 is particularly used in:
According to the history service data of pending data object, the business datum variation for obtaining pending data object becomes
Gesture;
Analysis is associated to user's attention rate variation tendency and business datum variation tendency, to generate reference policy letter
Breath.
In one embodiment, the second acquisition module 72 is particularly used in: MACD processing is carried out to historical search amount data,
To obtain the MACD line of reflection user's attention rate variation tendency.
Correspondingly, generation module 73 is further specifically used for:
MACD processing is carried out to history service data, to obtain the DIFF line and DEA line of reflection business datum variation tendency;
MACD line, DIFF line and DEA line are compared;
If wearing DEA line on DIFF line, and MACD line is positive or MACD line is become just by negative, and DIFF line is located on DEA line
Side generates the reference policy information that instruction user obtains pending data object;
If wearing DEA line under DIFF line, and MACD is negative or MACD line is by just becoming negative, and DIFF line is located under DEA line
Side generates the reference policy information that instruction user produces pending data object.
In one embodiment, the second acquisition module 72 is particularly used in: RSI processing is carried out to historical search amount data,
To obtain the first RSI line of reflection user's attention rate variation tendency.
Correspondingly, generation module 73 is further specifically used for:
RSI processing is carried out to history service data, to obtain the 2nd RSI line of reflection business datum variation tendency;
If the first RSI line is greater than the first upper limit thresholding, and the 2nd RSI line is greater than the second upper limit thresholding, generates instruction user
Produce the reference policy information of pending data object;
If the first RSI line is less than the first lower limit thresholding, and the 2nd RSI line generates instruction user less than the second lower limit thresholding
Buy in the reference policy information of pending data object.
In an optional embodiment, the second acquisition module 72 is particularly used in: to what is generated within the first setting period
Historical search amount data carry out index rolling average EMA processing, to obtain the first EMA of reflection user's attention rate variation tendency
Line, and EMA processing is carried out to the historical search amount data generated within the second setting period, become with obtaining reflection user's attention rate
2nd EMA line of change trend, the length of the first setting period set the length of period less than second.
Correspondingly, generation module 73 is specifically used for:
If the first EMA line passes through the 2nd EMA line from lower to upper, the reference that instruction user obtains pending data object is generated
Policy information;
If the first EMA line passes through the 2nd EMA line from top to bottom, the reference that instruction user produces pending data object is generated
Policy information.
In an optional embodiment, the second acquisition module 72 is particularly used in: carrying out MACD to historical search amount data
Processing, to obtain the MACD line of reflection user's attention rate variation tendency.
Correspondingly, generation module 73 is specifically used for:
If MACD line generates the reference policy information that instruction user obtains pending data object from just becoming negative;
If MACD line is become just, generating the reference policy information that instruction user produces pending data object from negative.
In an optional embodiment, the second acquisition module 72 is particularly used in: being carried out at RSI to historical search amount data
Reason, to obtain the first RSI line of user's attention rate variation tendency of reflection pending data object.
Correspondingly, generation module 73 is specifically used for:
If the first RSI line is greater than the first upper limit thresholding, the reference policy that instruction user produces pending data object is generated
Information;
If the first RSI line generates the reference policy that instruction user buys in pending data object less than the first lower limit thresholding
Information.
The present embodiment does not limit the form of pending data object, such as can be merchandise items, for example, mobile phone, computer,
Books, clothes or cosmetics etc. can also be the stage property in types of applications, be also possible to various financial products, for example, stock or
Fund etc..
Information processing unit provided in this embodiment, the historical search amount data based on pending data object, obtain to
The user's attention rate variation tendency for handling data object generates reference policy information, output according to user's attention rate variation tendency
The reference policy information, to instruct user to handle the pending data object.It can be seen that letter provided in this embodiment
Breath processing unit can instruct user to handle data object based on the historical search amount data for being different from history service data,
A kind of new mode for instructing user to handle data object is provided, user demand is met.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method 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 logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.