CN109214919A - A kind of information recommendation method, device, equipment and medium - Google Patents
A kind of information recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN109214919A CN109214919A CN201810994930.1A CN201810994930A CN109214919A CN 109214919 A CN109214919 A CN 109214919A CN 201810994930 A CN201810994930 A CN 201810994930A CN 109214919 A CN109214919 A CN 109214919A
- Authority
- CN
- China
- Prior art keywords
- industry
- component stock
- alternative
- various industries
- stock
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of information recommendation method, device, equipment and medium, it is applied to Internet technical field, it is lower that there are accuracy solving the problems, such as information recommendation method in the prior art.Specifically: it calls industry data analysis process the first historical trading data corresponding to various industries to analyze, obtains there are multiple industries of Herd Behavior and alternately industry;Call type data analysis process analyzes each alternative corresponding second historical trading data of industry, obtains the number for the specified type component stock that each alternative industry respectively contains;According to the number for the specified type component stock that each alternative industry respectively contains, chooses popular industry and show.In this way, according to Herd Behavior and comprising the number of specified type component stock choose popular industry so that the popular industry selected had both met current industry Investment Trend, sets requirement is also complied with, to improve the accuracy that popular industry is recommended.
Description
Technical field
The present invention relates to Internet technical field more particularly to a kind of information recommendation method, device, equipment and media.
Background technique
With the continuous development of Internet technology, personalized recommendation becomes the research hotspot of every field.It is led in security
Realize that intelligence is selected stocks, intelligence examines the functions such as stock, the recommendation of popular industry is met the tendency of to provide a user equity investment reference in domain
And it gives birth to.
Currently, most of hot topic industry recommended method is all solely to be moved in turn using historical return ranking or history
Rule etc., to predict popular industry and recommend user, the accuracy rate that will cause the popular industry for recommending user not high is asked
Topic.
Summary of the invention
The embodiment of the invention provides a kind of information recommendation method, device, equipment and media, to solve in the prior art
Popular industry recommended method there is a problem of that accuracy is lower.
Specific technical solution provided in an embodiment of the present invention is as follows:
The embodiment of the invention provides a kind of information recommendation methods, comprising:
When receiving information recommendation request, various industries corresponding first are inquired from historical transactional information database
Historical trading data;
It calls industry data analysis process the first historical trading data corresponding to various industries to analyze, obtains
There are multiple industries of Herd Behavior and alternately industry;
Corresponding second historical trading data of each alternative industry is inquired from historical transactional information database;
Call type data analysis process analyzes each alternative corresponding second historical trading data of industry,
Obtain the number for the specified type component stock that each alternative industry respectively contains;
According to the number for the specified type component stock that each alternative industry respectively contains, heat is chosen from each alternative industry
Door industry is simultaneously shown.
In information recommendation method provided in an embodiment of the present invention, call industry data analysis process to various industries respectively
Corresponding first historical trading data is analyzed, and is obtained there are multiple industries of Herd Behavior and alternately industry, including
Industry data analysis process is called to execute following operation:
According to corresponding first historical trading data of various industries, determine that various industries are each within first time
Self-corresponding industry is averaged daily earning rate sequence and business income rate absolute deviation sequence;
Be averaged daily earning rate sequence and business income rate absolute deviation sequence of the corresponding industry of various industries is carried out
Analysis obtains the mapping that the corresponding industry of various industries is averaged between daily earning rate and business income rate absolute deviation and closes
System;
From various industries, the industry alternately industry that corresponding mapping relations are Nonlinear Mapping relationship is chosen.
In information recommendation method provided in an embodiment of the present invention, according to corresponding first historical trading of various industries
Data, determine various industries corresponding industry within first time be averaged daily earning rate sequence and business income rate it is exhausted
To biased sequence, comprising:
The first historical trading data corresponding to various industries is analyzed, obtain various industries respectively contain it is each
Component stock daily earning rate sequence of a component stock within first time;
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time,
Determine that various industries corresponding industry within first time is averaged daily earning rate sequence;And
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time
And corresponding industry is averaged daily earning rate sequence, determines various industries corresponding industry within first time
Earning rate absolute deviation sequence.
In information recommendation method provided in an embodiment of the present invention, it is averaged day income to the corresponding industry of various industries
Rate sequence and business income rate absolute deviation sequence are analyzed, and are obtained the corresponding industry of various industries and are averaged daily earning rate
With the mapping relations between business income rate absolute deviation, comprising:
To the corresponding industry of various industries be averaged daily earning rate sequence and business income rate absolute deviation sequence difference
Carry out polynomial regression analysis, obtain the corresponding characterization industry of various industries be averaged daily earning rate and business income rate it is absolute
The regression expression of mapping relations between deviation.
In information recommendation method provided in an embodiment of the present invention, from various industries, choosing corresponding mapping relations is
The industry of Nonlinear Mapping relationship alternately industry, comprising:
From various industries, the industry alternately industry that corresponding regression expression is quadratic polynomial is chosen.
In information recommendation method provided in an embodiment of the present invention, from various industries, choosing corresponding mapping relations is
The industry of Nonlinear Mapping relationship alternately industry, further includes:
From various industries, two-term coefficient is negative in corresponding regression expression industry alternately industry is chosen;
Alternatively,
Significance analysis is carried out to the corresponding regression expression of various industries respectively, various industries is obtained and respectively corresponds to
Saliency value, and from various industries, the two-term coefficient for choosing corresponding regression expression is negative and saliency value is greater than first
The industry of given threshold alternately industry.
In information recommendation method provided in an embodiment of the present invention, if specified type component stock be there are head effect at
Share split, then call type data analysis process analyzes each alternative corresponding second historical trading data of industry,
Obtain the number for the specified type component stock that each alternative industry respectively contains, including call type data analysis process execute with
Lower operation:
Each alternative corresponding second historical trading data of industry is analyzed, obtains each alternative industry respectively
The each component stock for including is in component stock closing price sequence, the first composition in third time range in the second time range
Stock transaction value sequence and the second composition stock transaction value sequence in the 4th time range;
The corresponding component stock closing price sequence of each component stock that is respectively contained according to each alternative industry, first composition stock
Transaction value sequence and second composition stock transaction value sequence, determine each corresponding industry of alternative industry be averaged amount of increase degree and
The corresponding component stock amount of increase degree of each component stock respectively contained, component stock be averaged transaction value, first composition stock total business volume and
Second composition stock total business volume;
According to each alternative corresponding industry of industry be averaged amount of increase degree and each component stock for respectively containing it is corresponding
Component stock amount of increase degree, component stock be averaged transaction value, first composition stock total business volume and second composition stock total business volume, from each
In each component stock that alternative industry respectively contains, the component stock that selection meets amount of increase condition is respectively wrapped as each alternative industry
The specified type component stock contained;
Count the number for the specified type component stock that each alternative industry respectively contains.
In information recommendation method provided in an embodiment of the present invention, amount of increase condition includes at least following any one or group
It closes:
Component stock amount of increase degree is not less than the second given threshold;
Component stock amount of increase degree be averaged amount of increase degree not less than industry, wherein the industry amount of increase degree that is averaged is greater than third given threshold;
Component stock be averaged transaction value ranking not less than the 4th given threshold, and first composition stock total business volume is greater than second
Component stock total business volume.
In information recommendation method provided in an embodiment of the present invention, the specified type that is respectively contained according to each alternative industry
The number of component stock chooses popular industry from each alternative industry, comprising:
From each alternative industry, the number for choosing the specified type component stock for including is standby not less than the 5th given threshold
Select industry as popular industry.
In information recommendation method provided in an embodiment of the present invention, from each alternative industry, the specified class for including is chosen
The number of type component stock is not less than the alternative industry of the 5th given threshold as popular industry, further includes:
From comprising specified type component stock alternative industry of the number not less than the 5th given threshold in, any choose sets
The alternative industry of fixed number purpose is as popular industry;Alternatively,
According to comprising specified type component stock number sequence from high to low, from comprising specified type component stock
Number is used as popular industry not less than the alternative industry in the alternative industry of the 5th given threshold, choosing setting number.
The embodiment of the invention provides a kind of information recommending apparatus, comprising:
First query unit is inquired each when for receiving information recommendation request from historical transactional information database
Corresponding first historical trading data of industry;
First call unit, the various industries for calling industry data analysis process to inquire the first query unit are each
Self-corresponding first historical trading data is analyzed, and is obtained there are multiple industries of Herd Behavior and alternately industry;
Second query unit, it is each alternative for inquire that the first call unit obtains from historical transactional information database
Corresponding second historical trading data of industry;
Second call unit, each alternative row that the second query unit is inquired for call type data analysis process
Corresponding second historical trading data of industry is analyzed, and the specified type component stock that each alternative industry respectively contains is obtained
Number;
Industry selection unit, the specified type that each alternative industry for being obtained according to the second call unit respectively contains
The number of component stock chooses popular industry from each alternative industry;
Recommend display unit, the popular industry selected for display industry selection unit.
In information recommending apparatus provided in an embodiment of the present invention, calling industry data analysis process each to various industries
Self-corresponding first historical trading data is analyzed, obtain there are multiple industries of Herd Behavior and alternately industry when,
First call unit is specifically used for that industry data analysis process is called to execute following operation:
According to corresponding first historical trading data of various industries, determine that various industries are each within first time
Self-corresponding industry is averaged daily earning rate sequence and business income rate absolute deviation sequence;
Be averaged daily earning rate sequence and business income rate absolute deviation sequence of the corresponding industry of various industries is carried out
Analysis obtains the mapping that the corresponding industry of various industries is averaged between daily earning rate and business income rate absolute deviation and closes
System;
From various industries, the industry alternately industry that corresponding mapping relations are Nonlinear Mapping relationship is chosen.
In information recommending apparatus provided in an embodiment of the present invention, handed over according to corresponding first history of various industries
Easy data determine that various industries corresponding industry within first time is averaged daily earning rate sequence and business income rate
When absolute deviation sequence, the first call unit is specifically used for:
The first historical trading data corresponding to various industries is analyzed, obtain various industries respectively contain it is each
Component stock daily earning rate sequence of a component stock within first time;
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time,
Determine that various industries corresponding industry within first time is averaged daily earning rate sequence;And
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time
And corresponding industry is averaged daily earning rate sequence, determines various industries corresponding industry within first time
Earning rate absolute deviation sequence.
In information recommending apparatus provided in an embodiment of the present invention, received day being averaged to the corresponding industry of various industries
Beneficial rate sequence and business income rate absolute deviation sequence are analyzed, and are obtained the corresponding industry of various industries and are averaged day income
When mapping relations between rate and business income rate absolute deviation, the first call unit is specifically used for:
To the corresponding industry of various industries be averaged daily earning rate sequence and business income rate absolute deviation sequence difference
Carry out polynomial regression analysis, obtain the corresponding characterization industry of various industries be averaged daily earning rate and business income rate it is absolute
The regression expression of mapping relations between deviation.
In information recommending apparatus provided in an embodiment of the present invention, corresponding mapping relations from various industries, are being chosen
For Nonlinear Mapping relationship industry alternately industry when, the first call unit is specifically used for:
From various industries, the industry alternately industry that corresponding regression expression is quadratic polynomial is chosen.
In information recommending apparatus provided in an embodiment of the present invention, corresponding mapping relations from various industries, are being chosen
For Nonlinear Mapping relationship industry alternately industry when, the first call unit is also used to:
From various industries, two-term coefficient is negative in corresponding regression expression industry alternately industry is chosen;
Alternatively,
Significance analysis is carried out to the corresponding regression expression of various industries respectively, various industries is obtained and respectively corresponds to
Saliency value, and from various industries, the two-term coefficient for choosing corresponding regression expression is negative and saliency value is greater than first
The industry of given threshold alternately industry.
In information recommending apparatus provided in an embodiment of the present invention, if the specified type component stock that the second call unit determines
For there are the component stocks of head's effect, then gone through in call type data analysis process corresponding to each alternative industry second
History transaction data is analyzed, and when obtaining the number for the specified type component stock that each alternative industry respectively contains, second is called
Unit is specifically used for call type data analysis process and executes following operation:
Each alternative corresponding second historical trading data of industry is analyzed, obtains each alternative industry respectively
The each component stock for including is in component stock closing price sequence, the first composition in third time range in the second time range
Stock transaction value sequence and the second composition stock transaction value sequence in the 4th time range;
The corresponding component stock closing price sequence of each component stock that is respectively contained according to each alternative industry, first composition stock
Transaction value sequence and second composition stock transaction value sequence, determine each corresponding industry of alternative industry be averaged amount of increase degree and
The corresponding component stock amount of increase degree of each component stock respectively contained, component stock be averaged transaction value, first composition stock total business volume and
Second composition stock total business volume;
According to each alternative corresponding industry of industry be averaged amount of increase degree and each component stock for respectively containing it is corresponding
Component stock amount of increase degree, component stock be averaged transaction value, first composition stock total business volume and second composition stock total business volume, from each
In each component stock that alternative industry respectively contains, the component stock that selection meets amount of increase condition is respectively wrapped as each alternative industry
The specified type component stock contained;
Count the number for the specified type component stock that each alternative industry respectively contains.
In information recommending apparatus provided in an embodiment of the present invention, the second call unit is when choosing specified type component stock
The amount of increase condition of use includes at least following any one or combination:
Component stock amount of increase degree is not less than the second given threshold;
Component stock amount of increase degree be averaged amount of increase degree not less than industry, wherein the industry amount of increase degree that is averaged is greater than third given threshold;
Component stock be averaged transaction value ranking not less than the 4th given threshold, and first composition stock total business volume is greater than second
Component stock total business volume.
In information recommending apparatus provided in an embodiment of the present invention, in each alternative row obtained according to the second call unit
The number for the specified type component stock that industry respectively contains, when choosing popular industry from each alternative industry, industry selection unit
It is specifically used for:
From each alternative industry, the number for choosing the specified type component stock for including is standby not less than the 5th given threshold
Select industry as popular industry.
In information recommending apparatus provided in an embodiment of the present invention, include specified from each alternative industry, is being chosen
When the number of type components stock is used as popular industry not less than the alternative industry of the 5th given threshold, industry selection unit is also used
In:
From comprising specified type component stock alternative industry of the number not less than the 5th given threshold in, any choose sets
The alternative industry of fixed number purpose is as popular industry;Alternatively,
According to comprising specified type component stock number sequence from high to low, from comprising specified type component stock
Number is used as popular industry not less than the alternative industry in the alternative industry of the 5th given threshold, choosing setting number.
The embodiment of the invention provides a kind of non-volatile computer readable storage medium storing program for executing, the non-volatile computer is readable
Storage medium is stored with executable program, which, which executes, realizes that information provided in an embodiment of the present invention pushes away
The step of recommending method.
The embodiment of the invention provides a kind of information recommendation equipment, including memory, processor and storage are on a memory
Computer program, processor realizes the step of information recommendation method provided in an embodiment of the present invention when executing the computer program
Suddenly.
The embodiment of the present invention has the beneficial effect that:
In the embodiment of the present invention, alternative industry is chosen by Herd Behavior, and the alternative industry selected is accorded with
Current industry Investment Trend is closed, to ensure that the popular industry selected from alternative industry can meet current trade investment
Trend, and then improve the accuracy for recommending the popular industry of user, in addition, according to the number of specified type component stock from standby
The popular industry of selection in industry is selected to further improve so that the popular industry selected more meets sets requirement and recommend use
The accuracy of the popular industry at family.
Detailed description of the invention
Fig. 1 is Herd Behavior production principle schematic diagram provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of information recommendation method provided in an embodiment of the present invention;
Fig. 3 A be it is provided in an embodiment of the present invention when there are Herd Behavior, industry be averaged daily earning rate and business income rate
Mapping relations schematic diagram between absolute deviation;
Fig. 3 B is provided in an embodiment of the present invention when Herd Behavior is not present, and industry is averaged daily earning rate and business income
Mapping relations schematic diagram between rate absolute deviation;
Fig. 4 is provided in an embodiment of the present invention for showing the interface schematic diagram of the popular plate of popular industry;
Fig. 5 is the recommendation effect schematic diagram of information recommendation method provided in an embodiment of the present invention;
Fig. 6 is the illustrative view of functional configuration of information recommending apparatus provided in an embodiment of the present invention;
Fig. 7 is the hardware structural diagram of information recommendation equipment provided in an embodiment of the present invention.
Specific embodiment
Currently, there are mainly two types of for the recommended method of popular industry:
First method: the popular industry recommended method based on historical return.Which is mainly according to historical yield
Rate determines the amount of increase degree of various industries, and the sequence according to amount of increase degree from high to low, chooses the industry conduct of setting number
Popular industry recommends user.
Second method: moved in turn regular popular industry recommended method based on history.This method mainly utilizes frequent episode
Set algorithm determines that the history of hot topic industry moves in turn rule, and is moved in turn rule according to the history determined, determines that hot topic industry is recommended
To user.
Obviously, list is all based on using the popular industry that the recommended method of both current popular industries recommends user
One historical return or history moves in turn what rule obtained, and predictive poor, accuracy is not high.For this purpose, invention of the invention
People expects, from various industries, chooses that there are multiple industries of Herd Behavior alternately industries, and according to each alternative industry
The number of the specified type component stock respectively contained is chosen popular industry and is shown from each alternative industry.In this way, passing through sheep
Group's effect enables the alternative industry selected to meet current industry Investment Trend, to ensure that choose alternative industry
The popular industry selected from alternative industry can meet current industry Investment Trend, and then improve the heat for recommending user
The accuracy of door industry, in addition, popular industry is chosen from alternative industry according to the number of specified type component stock, so that choosing
Popular industry out more meets sets requirement, further improves the accuracy for recommending the popular industry of user.
Tellable to be, referenced herein " first ", " second ", " third ", " the 4th " and " the 5th " etc. is to be used for
Similar object is distinguished, without being used to describe a particular order or precedence order, it should be appreciated that the data used in this way are suitable
It can be interchanged in the case of, so that the embodiments described herein can be with suitable other than the content for illustrating or describing herein
Sequence is implemented, moreover, referenced herein " multiple " refer to two or more.
After simply describing information recommendation method provided in an embodiment of the present invention, next, combining the present invention real
The attached drawing in example is applied, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described implementation
Example is only a part of the embodiment of the present invention, is not whole embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
To facilitate the understanding of the present invention, portion of techniques term involved in the embodiment of the present invention is illustrated first.
Herd Behavior is the convergent a kind of phenomenon of investment behavior in sometime range, as shown in fig.1, being flock of sheep
The typical case of effect, for example, several bellwethers have jumped off steep cliff, subsequent sheep has also jumped off steep cliff therewith, and here it is so-called
" Herd Behavior ", also referred to as " bandwagon effect ".
Head's effect, for set the pace in Herd Behavior, promote other investors and its investment behavior it is convergent one
Kind phenomenon, for example, the bellwether in Herd Behavior promotes other sheep to jump off steep cliff therewith.
Alternative industry is that there are the industries of Herd Behavior in various industries.
Specified type component stock, for there are the component stocks of head's effect.
Popular industry, for there are Herd Behavior and comprising specified type component stock number be not less than given threshold row
Industry.
Secondly, the information recommendation method to exemplary embodiment of the invention is illustrated, specifically, as shown in fig.2,
The process of the information recommendation method of exemplary embodiment of the invention is as follows:
Step 200: when receiving information recommendation request, it is respectively right that various industries are inquired from historical transactional information database
The first historical trading data answered.
In practical applications, user can be by clicking " the industry recommendation " that is shown in information recommendation client, " refreshing
The icons such as recommendation ", to initiate information recommendation request, certainly, information recommendation request is also possible to open information recommendation in user
It is automatically initiated when client, can also be what information recommendation client was periodically initiated, be not specifically limited herein.
It in the specific implementation,, can be from historical trading when receiving information recommendation request in order to reduce subsequent calculation amount
Various industries corresponding historical trading data within first time is inquired in information database, wherein various industries
Corresponding historical trading data includes but is not limited to each component stock going through within first time that the sector includes
History component stock transaction data.
The acquisition of the corresponding historical trading data of the sector is illustrated by taking an industry as an example below.Assuming that the sector
Comprising N number of component stock, first time range is nearest T days, then available N number of component stock respectively corresponds in nearest T days
Historical element stock transaction data, and corresponding Historical element stock is traded in nearest T days by N number of component stock of acquisition
Historical trading data of the data as the sector in nearest T days.
Step 201: industry data analysis process the first historical trading data corresponding to various industries being called to carry out
Analysis, obtains there are multiple industries of Herd Behavior and alternately industry.
It in the specific implementation, can be by calling industry data analysis process to execute following operation:
Firstly, determining various industries in first time model according to corresponding first historical trading data of various industries
Interior corresponding industry is enclosed to be averaged daily earning rate sequence and business income rate absolute deviation sequence.
Specifically, can first corresponding first historical trading data to various industries within first time into
Row analysis obtains the component stock daily earning rate sequence of each component stock that various industries respectively contain within first time,
Wherein, the component stock daily earning rate sequence within the scope of first time is to receive the component stock day for every day that first time range includes
The set of beneficial rate;Component stock daily earning rate of each component stock respectively contained further according to various industries within first time
Sequence determines that various industries corresponding industry within first time is averaged daily earning rate sequence, wherein at the first time
Corresponding industry industry that daily earning rate sequence is first time range every day for including that is averaged be averaged and receives day in range
The set of beneficial rate;Finally, component stock day of each component stock respectively contained according to various industries within first time receives
Beneficial rate sequence and corresponding industry are averaged daily earning rate sequence, determine that various industries are respectively right within first time
The business income rate absolute deviation sequence answered, wherein corresponding business income rate absolute deviation within first time
Sequence is the set of the business income rate absolute deviation for every day that first time range includes.
Below by taking an industry as an example, it is averaged in daily earning rate sequence any one day industry to the corresponding industry of the sector
Any one day business income rate is absolute in average daily earning rate and the corresponding business income rate absolute deviation sequence of the sector
The determination of deviation is illustrated.Assuming that the sector includes N number of component stock, first time range is nearest T days, then can be by ingredient
Stock i is denoted as R (i, t) in the t days component stock daily earning rates, component stock of the N number of component stock for including according to the sector at the t days
Daily earning rate R (i, t), can determine the sector the t days industries be averaged daily earning rate be R (t)=sum (R (i, t))/
N, wherein sum is summing function, it is possible to further the component stock daily earning rate R (i, t) according to N number of component stock at the t days
It is averaged the average value of the difference between daily earning rate R (t)=sum (R (i, t))/N, determines in the t days industries with the sector
The sector is CSAD (t)=sum (/R (i, t)-R (t))/N in the t days business income rate absolute deviations.In this manner it is possible to root
It is averaged daily earning rate R (t)=sum (R (i, t))/N according to the industry for the every day determined, obtains the sector in nearest T days
Industry is averaged daily earning rate sequence, and according to business income rate absolute deviation CSAD (t)=sum of the every day determined (/
R (i, t)-R (t))/N, obtain business income rate absolute deviation sequence of the sector in nearest T days.
Then, it is averaged daily earning rate sequence and business income rate absolute deviation sequence to the corresponding industry of various industries
It is analyzed, obtains the mapping that the corresponding industry of various industries is averaged between daily earning rate and business income rate absolute deviation
Relationship.
It in the specific implementation, can be corresponding to various industries in order to ensure the accuracy of the mapping relations of acquisition
Industry is averaged daily earning rate sequence and business income rate absolute deviation sequence carries out polynomial regression analysis respectively, to obtain each
The recurrence for the mapping relations that a corresponding characterization industry of industry is averaged between daily earning rate and business income rate absolute deviation
Expression formula.
Finally, choosing the industry that corresponding mapping relations are Nonlinear Mapping relationship from various industries and alternately going
Industry.
Under normal circumstances, it is received day refering to shown in Fig. 3 A and Fig. 3 B, industry corresponding to the industry there are Herd Behavior is averaged
Mapping relations between beneficial rate and business income rate absolute deviation be it is nonlinear, industry is averaged day when Herd Behavior may be not present
Mapping relations between earning rate and business income rate absolute deviation be it is linear, be based on this, it is standby being chosen from various industries
When selecting industry, the industry that corresponding mapping relations are Nonlinear Mapping relationship can be chosen.Specifically, if passing through polynomial regression
Analysis obtains the corresponding characterization industry of various industries and is averaged reflecting between daily earning rate and business income rate absolute deviation
The regression expression of relationship is penetrated, then can choose the industry that corresponding regression expression is quadratic polynomial from various industries
Alternately industry.In order to further increase selection alternative industry accuracy, can also from various industries, choose correspond to
Regression expression the industry that is negative of two-term coefficient alternately industry.
Under normal circumstances, Herd Behavior existing for alternative industry is more significant, which becomes the credible of popular industry
Degree is bigger, and alternative industry is being chosen from various industries in order to improve the confidence level of the popular industry finally obtained based on this
When, significance analysis can also be carried out respectively to the corresponding regression expression of various industries, it is respectively right to obtain various industries
After the saliency value answered, from various industries, the two-term coefficient for choosing corresponding regression expression is negative and saliency value is greater than the
The industry of one given threshold alternately industry, in this manner it is possible to select the more significant alternative industry of Herd Behavior, in turn
Improve the confidence level of the popular industry finally obtained.
Below by taking an industry as an example, to whether the sector be chosen for alternative industry being illustrated.Continue to continue to use
Example, if be averaged daily earning rate sequence and business income rate absolute deviation sequence of the industry of the sector is carried out polynomial regression and divided
Analysis, the regression expression for obtaining the sector are It then can be with
In quadratic polynomial coefficient gamma2When being negative, determining the sector, there are Herd Behaviors, and then the sector alternately can be gone
One of industry.It certainly, can also be to the regression expression of the sector in order to improve the confidence level of the popular industry finally obtained Significance analysis is carried out, it is corresponding aobvious to obtain the sector
After work value, if the quadratic polynomial coefficient gamma of the corresponding regression expression of the sector2It is negative and saliency value is greater than the first setting threshold
Value, then can determine that Herd Behavior existing for the sector is more significant, at this point it is possible to by the sector alternately one of industry.
Step 202: corresponding second historical trading of each alternative industry is inquired from historical transactional information database
Data.
In the specific implementation, various industries can be inquired from historical transactional information database in the second time range,
Corresponding historical trading data in three periods of three time ranges and the 4th time range, wherein various industries are
Two time ranges, corresponding second historical trading data packet in three periods of third time range and the 4th time range
It includes but is not limited to each component stock that the sector includes in the second time range, third time range and the 4th time range three
Historical element stock transaction data in period.
Step 203: call type data analysis process is to each alternative corresponding second historical trading data of industry
It is analyzed, obtains the number for the specified type component stock that each alternative industry respectively contains.
It in practical applications, can be according to recommended requirements, flexible setting specified type component stock.For example, being used according to history
Family investment data determines the component stock of user preference, and from each component stock that alternative industry includes choose user preference at
Share split is set as specified type component stock.For another example, the higher component stock of earning rate is determined according to historical yield data, and from alternative
The higher component stock of earning rate is chosen in each component stock that industry includes is set as specified type component stock, etc..
It should be noted that in the information recommendation method of exemplary embodiment of the invention, categorical data analysis process
It can be two independent Data Analysis Software with industry data analysis process, be also possible to a Data Analysis Software, work as class
When type data analysis process and industry data analysis process are a Data Analysis Software, which has the present invention
The function analyzed of the first historical trading data corresponding to various industries required in embodiment and to each
The function that alternative corresponding second historical trading data of industry is analyzed.
In order to improve the accuracy of the popular industry finally obtained, the embodiment of the present invention sets specified type component stock to
There are the component stocks of head's effect.Specifically, following operation can be executed by call type data analysis process:
Firstly, analyzing each alternative corresponding second historical trading data of industry, each alternative row is obtained
Each component stock that industry respectively contains is in the component stock closing price sequence in the second time range, in third time range
One component stock transaction value sequence and the second composition stock transaction value sequence in the 4th time range.
Then, the corresponding component stock closing price sequence of each component stock respectively contained according to each alternative industry, first
Component stock transaction value sequence and second composition stock transaction value sequence determine that each corresponding industry of alternative industry is averaged amount of increase
It spends and the corresponding component stock amount of increase degree of each component stock that respectively contains, component stock is averaged transaction value, first composition stock assembly
Friendship volume and second composition stock total business volume.
Specifically, can be according to ingredient of each component stock that each alternative industry respectively contains in the second time range
Stock closing price sequence determines the component stock amount of increase of each component stock that each alternative industry respectively contains in the second time range
Degree and each alternative industry corresponding industry in the second time range are averaged amount of increase degree;And according to each alternative industry
First composition stock transaction value sequence of each component stock respectively contained in third time range, determines that each alternative industry is each
Component stock of the self-contained each component stock in third time range is averaged transaction value and first composition stock total business volume;With
And second composition stock transaction value sequence of each component stock respectively contained according to each alternative industry in the 4th time range
Column determine the second composition stock total business volume of each component stock that each alternative industry respectively contains in the 4th time range.
Secondly, being averaged amount of increase degree and each component stock for respectively containing according to each alternative corresponding industry of industry
Corresponding component stock amount of increase degree, component stock are averaged transaction value, first composition stock total business volume and second composition stock total business volume, from
In each component stock that each alternative industry respectively contains, the component stock that selection meets amount of increase condition is each as each alternative industry
Self-contained specified type component stock.
It is tellable to be, it can be by amount of increase condition setting while meet following three conditions:
(1) component stock amount of increase degree is not less than the second given threshold.
(2) component stock amount of increase degree be averaged amount of increase degree not less than industry, wherein the industry amount of increase degree that be averaged is greater than third setting threshold
Value.
(3) component stock be averaged transaction value ranking not less than the 4th given threshold, and first composition stock total business volume is greater than
Second composition stock total business volume.
Finally, the number for the specified type component stock that each alternative industry of statistics respectively contains.
Whether the component stock for including to the sector by taking the component stock that an industry includes as an example below is that there are head
The component stock of neck effect is illustrated.Assuming that the second time range is nearest 12 days, third time range is nearest 5 days,
4th time range is nearest 10 days, then can first determine component stock closing price sequence of the component stock in nearest 12 days,
First composition stock transaction value sequence in nearest 5 days and the second composition stock transaction value sequence in nearest 10 days, further according to this
Component stock closing price sequence of the component stock in nearest 12 days, determine component stock amount of increase degree of the component stock in nearest 12 days and
Industry of the sector in nearest 12 days is averaged amount of increase degree, and is struck a bargain according to first composition stock of the component stock in nearest 12 days
Volume sequence determines that component stock of the component stock in nearest 12 days is averaged transaction value and first composition stock total business volume, Yi Jigen
According to second composition stock transaction value sequence of the component stock in nearest 5 days, second composition of the component stock in nearest 5 days is determined
Stock total business volume, is not less than finally, meeting component stock amount of increase degree of (1) component stock in nearest 12 days simultaneously in the component stock
The component stock amount of increase degree of second given threshold, (2) component stock in nearest 12 days is not less than industry where the component stock nearest
Industry in 12 days is averaged amount of increase degree, wherein the sector be averaged amount of increase degree greater than third given threshold, (3) component stock most
Component stock in nearly 12 days be averaged transaction value ranking not less than the 4th given threshold, and the component stock in nearest 12 days the
When one component stock total business volume is greater than second composition stock these three conditions of total business volume of the component stock in nearest 5 days, determine
There are head's effects for the component stock, and then the specified type component stock that can include as the sector using the component stock, and count
In the number for entering the specified type component stock that the sector includes.
Step 204: according to the number for the specified type component stock that each alternative industry respectively contains, from each alternative industry
Industry that middle selection is popular is simultaneously shown.
In the specific implementation, the number that from each alternative industry, can choose the specified type component stock for including is not small
Popular industry is used as in the alternative industry of the 5th given threshold.For example, choosing and being deposited comprising 2 or more from each alternative industry
Popular industry is used as in the alternative industry of the component stock of head's effect.
In the information recommendation method of exemplary embodiment of the invention, can by comprising specified type component stock number
Mesh is all used as popular industry not less than all alternative industries of the 5th given threshold, can also from comprising specified type component stock
Number not less than in the alternative industry of the 5th given threshold, any alternative industry for choosing setting number as popular industry,
Can also according to comprising specified type component stock number sequence from high to low, from comprising specified type component stock number
Mesh is used as popular industry not less than the alternative industry in the alternative industry of the 5th given threshold, choosing setting number, specific to select
Mode is taken to be not specifically limited herein.In practical applications, it when popular industry is shown to user, can be chosen with equal weight allocation
Each popular industry out, and each popular industry selected according to the period display of moving in turn of setting, it is expired when the period of moving in turn
When, popular industry can be chosen again using the information recommendation method of exemplary embodiment of the invention and shown.
Such as: assuming that there are the alternative industries of the component stock of head's effect A industry, B industry, C row comprising 2 or more
Industry, D industry, E industry and F industry etc., then can by these alternative industries all as popular industry, and for A industry, B industry,
This identical display weight of 6 industry distributions of C industry, D industry, E industry and F industry, enables this 6 industries to show simultaneously,
In practical applications, this 6 popular industries can be simultaneously displayed in popular plate as shown in Figure 4, further, it is also possible to will
The period of moving in turn of each hot topic industry is set as 5 days, i.e., in 5 days time ranges, shows in popular plate as shown in Figure 4
Popular industry be this 6 industries of A industry, B industry, C industry, D industry, E industry and F industry, when the time limit is expired within 5 day,
Using the information recommendation method of exemplary embodiment of the invention, popular industry is chosen again and is shown in heat as shown in Figure 4
In door panels.
Tellable to be, Fig. 5 is the recommendation effect schematic diagram of the information recommendation method of exemplary embodiment of the invention, root
According to Fig. 5 data shown it is found that recommending popular row to user using the information recommendation method of exemplary embodiment of the invention
Industry, it can be ensured that the popular industry for recommending user meets current industry Investment Trend, to improve the heat for recommending user
The accuracy of door industry.
Next, the information recommending apparatus 600 to exemplary embodiment of the invention is described in detail, refering to Fig. 6 institute
Show, the information recommending apparatus 600 of exemplary embodiment of the invention includes at least:
First query unit 601 when for receiving information recommendation request, is inquired each from historical transactional information database
A corresponding first historical trading data of industry;
First call unit 602, it is each for calling industry data analysis process to inquire the first query unit 601
Corresponding first historical trading data of industry is analyzed, and is obtained multiple industries there are Herd Behavior and is alternately gone
Industry;
Second query unit 603, for inquired from historical transactional information database the first call unit 602 obtain it is each
A corresponding second historical trading data of alternative industry;
Second call unit 604 inquires the second query unit 603 for call type data analysis process each
Alternative corresponding second historical trading data of industry is analyzed, and the specified type that each alternative industry respectively contains is obtained
The number of component stock;
Industry selection unit 605, the finger that each alternative industry for being obtained according to the second call unit 604 respectively contains
The number for determining type components stock chooses popular industry from each alternative industry;
Recommend display unit 606, the popular industry selected for display industry selection unit 605.
In information recommending apparatus 600, industry data analysis process corresponding to various industries first is being called to go through
History transaction data is analyzed, obtain there are multiple industries of Herd Behavior and alternately industry when, the first call unit 602
Specifically for calling industry data analysis process to execute following operation:
According to corresponding first historical trading data of various industries, determine that various industries are each within first time
Self-corresponding industry is averaged daily earning rate sequence and business income rate absolute deviation sequence;
Be averaged daily earning rate sequence and business income rate absolute deviation sequence of the corresponding industry of various industries is carried out
Analysis obtains the mapping that the corresponding industry of various industries is averaged between daily earning rate and business income rate absolute deviation and closes
System;
From various industries, the industry alternately industry that corresponding mapping relations are Nonlinear Mapping relationship is chosen.
In information recommending apparatus 600, according to corresponding first historical trading data of various industries, determine each
Industry corresponding industry within first time be averaged daily earning rate sequence and business income rate absolute deviation sequence when,
First call unit 602 is specifically used for:
The first historical trading data corresponding to various industries is analyzed, obtain various industries respectively contain it is each
Component stock daily earning rate sequence of a component stock within first time;
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time,
Determine that various industries corresponding industry within first time is averaged daily earning rate sequence;And
Component stock daily earning rate sequence of each component stock respectively contained according to various industries within first time
And corresponding industry is averaged daily earning rate sequence, determines various industries corresponding industry within first time
Earning rate absolute deviation sequence.
In information recommending apparatus 600, it is averaged daily earning rate sequence and industry to the corresponding industry of various industries
Earning rate absolute deviation sequence is analyzed, and is obtained the corresponding industry of various industries and is averaged daily earning rate and business income rate
When mapping relations between absolute deviation, the first call unit 602 is specifically used for:
To the corresponding industry of various industries be averaged daily earning rate sequence and business income rate absolute deviation sequence difference
Carry out polynomial regression analysis, obtain the corresponding characterization industry of various industries be averaged daily earning rate and business income rate it is absolute
The regression expression of mapping relations between deviation.
It is Nonlinear Mapping relationship from various industries, choosing corresponding mapping relations in information recommending apparatus 600
Industry alternately industry when, the first call unit 602 is specifically used for:
From various industries, the industry alternately industry that corresponding regression expression is quadratic polynomial is chosen.
It is Nonlinear Mapping relationship from various industries, choosing corresponding mapping relations in information recommending apparatus 600
Industry alternately industry when, the first call unit 602 is also used to:
From various industries, two-term coefficient is negative in corresponding regression expression industry alternately industry is chosen;
Alternatively,
Significance analysis is carried out to the corresponding regression expression of various industries respectively, various industries is obtained and respectively corresponds to
Saliency value, and from various industries, the two-term coefficient for choosing corresponding regression expression is negative and saliency value is greater than first
The industry of given threshold alternately industry.
In information recommending apparatus 600, if the specified type component stock that the second call unit 604 determines is that there are head's effects
The component stock answered, then call type data analysis process to each alternative corresponding second historical trading data of industry into
Row analysis, when obtaining the number for the specified type component stock that each alternative industry respectively contains, the second call unit 604 is specifically used
Following operation is executed in call type data analysis process:
Each alternative corresponding second historical trading data of industry is analyzed, obtains each alternative industry respectively
The each component stock for including is in component stock closing price sequence, the first composition in third time range in the second time range
Stock transaction value sequence and the second composition stock transaction value sequence in the 4th time range;
The corresponding component stock closing price sequence of each component stock that is respectively contained according to each alternative industry, first composition stock
Transaction value sequence and second composition stock transaction value sequence, determine each corresponding industry of alternative industry be averaged amount of increase degree and
The corresponding component stock amount of increase degree of each component stock respectively contained, component stock be averaged transaction value, first composition stock total business volume and
Second composition stock total business volume;
According to each alternative corresponding industry of industry be averaged amount of increase degree and each component stock for respectively containing it is corresponding
Component stock amount of increase degree, component stock be averaged transaction value, first composition stock total business volume and second composition stock total business volume, from each
In each component stock that alternative industry respectively contains, the component stock that selection meets amount of increase condition is respectively wrapped as each alternative industry
The specified type component stock contained;
Count the number for the specified type component stock that each alternative industry respectively contains.
In information recommending apparatus 600, amount of increase item that the second call unit 604 is used when choosing specified type component stock
Part includes at least following any one or combination:
Component stock amount of increase degree is not less than the second given threshold;
Component stock amount of increase degree be averaged amount of increase degree not less than industry, wherein the industry amount of increase degree that is averaged is greater than third given threshold;
Component stock be averaged transaction value ranking not less than the 4th given threshold, and first composition stock total business volume is greater than second
Component stock total business volume.
In information recommending apparatus 600, respectively contained in each alternative industry obtained according to the second call unit 604
The number of specified type component stock, when choosing popular industry from each alternative industry, industry selection unit 605 is specifically used for:
From each alternative industry, the number for choosing the specified type component stock for including is standby not less than the 5th given threshold
Select industry as popular industry.
In information recommending apparatus 600, from each alternative industry, the number for the specified type component stock for including is chosen
When alternative industry not less than the 5th given threshold is used as popular industry, industry selection unit 605 is also used to:
From comprising specified type component stock alternative industry of the number not less than the 5th given threshold in, any choose sets
The alternative industry of fixed number purpose is as popular industry;Alternatively,
According to comprising specified type component stock number sequence from high to low, from comprising specified type component stock
Number is used as popular industry not less than the alternative industry in the alternative industry of the 5th given threshold, choosing setting number.
It should be noted that since information recommending apparatus 600 solves the principle and the exemplary implementation of the present invention of technical problem
The information recommendation method of mode is similar, and therefore, the implementation of information recommending apparatus 600 may refer to exemplary embodiment of the invention
Information recommendation method implementation, overlaps will not be repeated.
After the information recommendation method and device for describing exemplary embodiment of the invention, next, to the present invention
The information recommendation equipment of illustrative embodiments is simply introduced.
As shown in fig.7, the information recommendation equipment 700 of exemplary embodiment of the invention may include processor 71, deposit
Reservoir 72 and the computer program being stored on memory 72, processor 71 realize that the present invention is exemplary when executing computer program
Step in the information recommendation method of embodiment.
It should be noted that information recommendation equipment 700 shown in Fig. 7 is only an example, the present invention should not be implemented
The function and use scope of example bring any restrictions.
Memory 72 may include the readable medium of form of volatile memory, such as random access memory (Random
Access Memory, RAM) 721 and/or cache memory 722, it can further include read-only memory (Read
Only Memory, ROM) 723.
Memory 72 can also include the program means 725 with one group of (at least one) program module 724, program module
724 include but is not limited to: operational subsystems, one or more application program, other program modules and program data, these
It may include the realization of network environment in each of example or certain combination.
Information recommendation equipment 700 can also be communicated with one or more external equipments 74 (such as keyboard, remote controler etc.), also
Can be enabled a user to one or more equipment interacted with information recommendation equipment 700 communication, and/or with make the information
Any equipment that recommendation apparatus 700 can be communicated with one or more of the other information recommendation equipment 700 (such as router, adjust
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (Input/Output, I/O) interface 75.Also,
Information recommendation equipment 700 can also pass through network adapter 76 and one or more network (such as local area network (Local Area
Network, LAN), wide area network (Wide Area Network, WAN) and/or public network, such as internet) communication.Such as Fig. 7
Shown, network adapter 76 is communicated by bus 73 with other modules of information recommendation equipment 700.It will be appreciated that though in Fig. 7
It is not shown, other hardware and/or software module can be used with combining information recommendation apparatus 700, including but not limited to: microcode,
Device driver, redundant processor, external disk drive array, disk array (Redundant Arrays of
Independent Disks, RAID) subsystem, tape drive and data backup storage subsystem etc..
The non-volatile computer readable storage medium storing program for executing of exemplary embodiment of the invention is introduced below.The present invention
Embodiment provides a kind of non-volatile computer readable storage medium storing program for executing, which is stored with
Computer executable instructions, which, which executes, realizes that the various information of exemplary embodiment of the invention push away
The step of recommending method.Specifically, which can be built in information recommendation equipment 700, in this way, information recommendation equipment
700 can realize the various information recommendation methods of exemplary embodiment of the invention by the executable program built in executing
Step.
In addition, the various information recommendation methods of exemplary embodiment of the invention are also implemented as a kind of program product,
The program product includes program code, and when the program product can be run in information recommendation equipment 700, which is used
In the step of making information recommendation equipment 700 execute the various information recommendation methods of exemplary embodiment of the invention.
Program product provided in an embodiment of the present invention can be using any combination of one or more readable mediums, wherein
Readable medium can be readable signal medium or readable storage medium storing program for executing, and readable storage medium storing program for executing can be but it is electric to be not limited to,
Magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination is specifically, readable to deposit
The more specific example (non exhaustive list) of storage media includes: electrical connection with one or more conducting wires, portable disc, hard
Disk, RAM, ROM, erasable programmable read only memory (Erasable Programmable Read Only Memory,
EPROM), optical fiber, portable compact disc read only memory (Compact Disc Read-Only Memory, CD-ROM), light are deposited
Memory device, magnetic memory device or above-mentioned any appropriate combination.
Program product provided in an embodiment of the present invention can also be set using CD-ROM and including program code in calculating
Standby upper operation.However, program product provided in an embodiment of the present invention is without being limited thereto, and in embodiments of the present invention, readable storage medium
Matter can be any tangible medium for including or store program, which, which can be commanded execution system, device or device, makes
With or it is in connection.
Readable signal medium may include in a base band or as the data-signal that carrier wave a part is propagated, wherein carrying
Readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal, optical signal
Or above-mentioned any appropriate combination.Readable signal medium can also be any readable medium other than readable storage medium storing program for executing, should
Readable medium can send, propagate or transmit for by instruction execution system, device or device use or it is in connection
The program used.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language, Java, C++ etc., further include conventional mistake
Formula programming language, such as " C " language or similar programming language.Program code can be fully in user equipment
Upper execution, partly executes on a user device, executes as an independent software package, partially execute on a user device,
Part executes on a remote computing, or executes in remote computing device or server completely.It is being related to remote computation
In the situation of equipment, remote computing device can such as pass through LAN by the network connection of any kind to user calculating equipment
Or WAN is connected to user calculating equipment;Or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
It should be noted that although being referred to several unit or sub-units of device in the above detailed description, this stroke
It point is only exemplary not enforceable.In fact, embodiment according to the present invention, it is above-described two or more
The feature and function of unit can embody in a unit.Conversely, the feature and function of an above-described unit can
It is to be embodied by multiple units with further division.
In addition, although describing the operation of the method for the present invention in the accompanying drawings with particular order, this do not require that or
Hint must execute these operations in this particular order, or have to carry out shown in whole operation be just able to achieve it is desired
As a result.Additionally or alternatively, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/or by one
Step is decomposed into execution of multiple steps.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, those skilled in the art can carry out various modification and variations without departing from this hair to the embodiment of the present invention
The spirit and scope of bright embodiment.In this way, if these modifications and variations of the embodiment of the present invention belong to the claims in the present invention
And its within the scope of equivalent technologies, then the present invention is also intended to include these modifications and variations.
Claims (13)
1. a kind of information recommendation method characterized by comprising
When receiving information recommendation request, corresponding first history of various industries is inquired from historical transactional information database
Transaction data;
It calls industry data analysis process the first historical trading data corresponding to the various industries to analyze, obtains
There are multiple industries of Herd Behavior and alternately industry;
Corresponding second historical trading data of each alternative industry is inquired from the historical transactional information database;
Call type data analysis process analyzes each alternative corresponding second historical trading data of industry,
Obtain the number for the specified type component stock that each alternative industry respectively contains;
According to the number for the specified type component stock that each alternative industry respectively contains, selected from each alternative industry
It takes popular industry and shows.
2. information recommendation method as described in claim 1, which is characterized in that call industry data analysis process to described each
Corresponding first historical trading data of industry is analyzed, and is obtained multiple industries there are Herd Behavior and is alternately gone
Industry, including the industry data analysis process is called to execute following operation:
According to corresponding first historical trading data of the various industries, determine the various industries in first time range
Interior corresponding industry is averaged daily earning rate sequence and business income rate absolute deviation sequence;
Be averaged daily earning rate sequence and business income rate absolute deviation sequence of the corresponding industry of the various industries is carried out
Analysis, obtains the mapping that the corresponding industry of the various industries is averaged between daily earning rate and business income rate absolute deviation
Relationship;
From the various industries, the industry alternately industry that corresponding mapping relations are Nonlinear Mapping relationship is chosen.
3. information recommendation method as claimed in claim 2, which is characterized in that according to the various industries corresponding first
Historical trading data, determine the various industries corresponding industry within first time be averaged daily earning rate sequence and
Business income rate absolute deviation sequence, comprising:
The first historical trading data corresponding to the various industries is analyzed, and is obtained the various industries and is respectively contained
Component stock daily earning rate sequence of each component stock within the first time;
Component stock daily earning rate of each component stock respectively contained according to the various industries within the first time
Sequence determines that the various industries corresponding industry within the first time is averaged daily earning rate sequence;And
Component stock daily earning rate of each component stock respectively contained according to the various industries within the first time
Sequence and corresponding industry are averaged daily earning rate sequence, determine that the various industries are each within the first time
Self-corresponding business income rate absolute deviation sequence.
4. information recommendation method as claimed in claim 2, which is characterized in that flat to the corresponding industry of the various industries
Equal daily earning rate sequence and business income rate absolute deviation sequence are analyzed, and the corresponding industry of the various industries is obtained
Mapping relations between average daily earning rate and business income rate absolute deviation, comprising:
To the corresponding industry of the various industries be averaged daily earning rate sequence and business income rate absolute deviation sequence difference
Polynomial regression analysis is carried out, the corresponding characterization industry of the various industries is obtained and is averaged daily earning rate and business income rate
The regression expression of mapping relations between absolute deviation.
5. information recommendation method as claimed in claim 4, which is characterized in that from the various industries, choose corresponding reflect
Penetrate the industry alternately industry that relationship is Nonlinear Mapping relationship, comprising:
From the various industries, choosing corresponding regression expression is the industry of quadratic polynomial as the alternative industry.
6. information recommendation method as claimed in claim 5, which is characterized in that from the various industries, choose corresponding reflect
Penetrate the industry alternately industry that relationship is Nonlinear Mapping relationship, further includes:
From the various industries, industry that the two-term coefficient in corresponding regression expression is negative is chosen as described alternative
Industry;Alternatively,
Significance analysis is carried out to the corresponding regression expression of the various industries respectively, obtains the various industries respectively
Corresponding saliency value, and from the various industries, the two-term coefficient for choosing corresponding regression expression is negative and saliency value
Greater than the industry of the first given threshold as the alternative industry.
7. information recommendation method as described in claim 1, which is characterized in that if the specified type component stock is that there are heads
The component stock of effect, then call type data analysis process is to each alternative corresponding second historical trading number of industry
According to being analyzed, the number for the specified type component stock that each alternative industry respectively contains is obtained, including call the class
Type data analysis process executes following operation:
Each alternative corresponding second historical trading data of industry is analyzed, each alternative industry is obtained
The each component stock respectively contained in the second time range component stock closing price sequence, first in third time range
Component stock transaction value sequence and the second composition stock transaction value sequence in the 4th time range;
The corresponding component stock closing price sequence of each component stock that is respectively contained according to each alternative industry, first composition stock
Transaction value sequence and second composition stock transaction value sequence determine that each alternative corresponding industry of industry is averaged amount of increase degree
And be averaged transaction value, first composition stock of the corresponding component stock amount of increase degree of each component stock that respectively contains, component stock always strikes a bargain
Volume and second composition stock total business volume;
According to each alternative corresponding industry of industry be averaged amount of increase degree and each component stock for respectively containing it is corresponding
Component stock amount of increase degree, component stock be averaged transaction value, first composition stock total business volume and second composition stock total business volume, from described
In each component stock that each alternative industry respectively contains, the component stock for meeting amount of increase condition is chosen as each alternative row
The specified type component stock that industry respectively contains;
Count the number for the specified type component stock that each alternative industry respectively contains.
8. information recommendation method as claimed in claim 7, which is characterized in that the amount of increase condition includes at least:
Component stock amount of increase degree is not less than the second given threshold;
Component stock amount of increase degree be averaged amount of increase degree not less than industry, wherein the industry amount of increase degree that is averaged is greater than third given threshold;
Component stock be averaged transaction value ranking not less than the 4th given threshold, and first composition stock total business volume is greater than second composition
Stock total business volume.
9. such as the described in any item information recommendation methods of claim 1-8, which is characterized in that each according to each alternative industry
The number of self-contained specified type component stock chooses popular industry from each alternative industry, comprising:
From each alternative industry, the number for choosing the specified type component stock for including is standby not less than the 5th given threshold
Select industry as the popular industry.
10. information recommendation method as claimed in claim 9, which is characterized in that from each alternative industry, selection includes
Specified type component stock number not less than the alternative industry of the 5th given threshold as the popular industry, further includes:
From comprising specified type component stock alternative industry of the number not less than the 5th given threshold in, it is any to choose setting number
The alternative industry of purpose is as the popular industry;Alternatively,
According to comprising specified type component stock number sequence from high to low, from comprising specified type component stock number
In alternative industry not less than the 5th given threshold, the alternative industry of setting number is chosen as the popular industry.
11. a kind of information recommending apparatus characterized by comprising
First query unit inquires various industries from historical transactional information database when for receiving information recommendation request
Corresponding first historical trading data;
First call unit, each row for calling industry data analysis process to inquire first query unit
Corresponding first historical trading data of industry is analyzed, and is obtained multiple industries there are Herd Behavior and is alternately gone
Industry;
Second query unit, for inquired from the historical transactional information database first call unit obtain it is each
Corresponding second historical trading data of alternative industry;
Second call unit inquires second query unit for call type data analysis process described each standby
It selects corresponding second historical trading data of industry to be analyzed, obtains the specified class that each alternative industry respectively contains
The number of type component stock;
Industry selection unit, each alternative industry for being obtained according to second call unit respectively contain specified
The number of type components stock chooses popular industry from each alternative industry;
Recommend display unit, the hot topic industry selected for showing the industry selection unit.
12. a kind of non-volatile computer readable storage medium storing program for executing, which is characterized in that the non-volatile computer readable storage medium
Matter is stored with executable program, and the executable code processor, which executes, realizes the described in any item information of claim 1-10
The step of recommended method.
13. a kind of information recommendation equipment, which is characterized in that including memory, processor and the meter being stored on the memory
Calculation machine program, the processor realize the described in any item information recommendation sides claim 1-10 when executing the computer program
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810994930.1A CN109214919A (en) | 2018-08-29 | 2018-08-29 | A kind of information recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810994930.1A CN109214919A (en) | 2018-08-29 | 2018-08-29 | A kind of information recommendation method, device, equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109214919A true CN109214919A (en) | 2019-01-15 |
Family
ID=64985221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810994930.1A Pending CN109214919A (en) | 2018-08-29 | 2018-08-29 | A kind of information recommendation method, device, equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109214919A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111680858A (en) * | 2020-04-16 | 2020-09-18 | 上海淇玥信息技术有限公司 | Method and device for managing service promotion strategy and electronic equipment |
-
2018
- 2018-08-29 CN CN201810994930.1A patent/CN109214919A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111680858A (en) * | 2020-04-16 | 2020-09-18 | 上海淇玥信息技术有限公司 | Method and device for managing service promotion strategy and electronic equipment |
CN111680858B (en) * | 2020-04-16 | 2023-12-26 | 上海淇玥信息技术有限公司 | Method and device for managing service promotion policy and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11113704B2 (en) | Systems and methods for interactive annuity product services using machine learning modeling | |
US10439891B2 (en) | Hyperparameter and network topology selection in network demand forecasting | |
US20210142253A1 (en) | Explainable artificial intelligence-based sales maximization decision models | |
CN108446382B (en) | Method and apparatus for pushed information | |
US20200320462A1 (en) | Calculating online social network distance between entities of an organization | |
US11694267B2 (en) | Automation and latency remediation for secure messaging systems | |
US11237806B2 (en) | Multi objective optimization of applications | |
US11386358B2 (en) | Intelligent decision support system | |
US20140258175A1 (en) | Generating Personalized Investment Recommendations | |
US20210065294A1 (en) | Trading platforms using market sentiment and dynamic risk assessment profiles | |
CN110472798A (en) | Prediction technique, device and the computer readable storage medium of time series data | |
US11551129B2 (en) | Quantum platform routing of a quantum application component | |
Maroc et al. | Cloud services security-driven evaluation for multiple tenants | |
Lepenioti et al. | Human-augmented prescriptive analytics with interactive multi-objective reinforcement learning | |
Zhang | A computing allocation strategy for Internet of things’ resources based on edge computing | |
US11520757B2 (en) | Explanative analysis for records with missing values | |
CN109214919A (en) | A kind of information recommendation method, device, equipment and medium | |
US20200012948A1 (en) | Real time ensemble scoring optimization | |
Chen | Individual Mobile Communication Services and Tariffs | |
US20230245149A1 (en) | Dynamic web content insertion | |
WO2021096564A1 (en) | Explainable artificial intelligence-based sales maximization decision models | |
US20220383100A1 (en) | Cost-efficient reinforcement learning using q-learning | |
WO2022251237A1 (en) | Explainable artificial intelligence-based sales maximization decision models | |
US20230103778A1 (en) | Hybrid human-computer learning system | |
Lin et al. | Application of intelligent logistics inventory optimization algorithm based on digital supply chain |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |