CN107679987A - Asset Allocation strategy acquisition methods, device, computer equipment and storage medium - Google Patents
Asset Allocation strategy acquisition methods, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN107679987A CN107679987A CN201710614428.9A CN201710614428A CN107679987A CN 107679987 A CN107679987 A CN 107679987A CN 201710614428 A CN201710614428 A CN 201710614428A CN 107679987 A CN107679987 A CN 107679987A
- Authority
- CN
- China
- Prior art keywords
- finance product
- trend
- historical
- price
- target
- 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
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The present invention relates to a kind of Asset Allocation strategy acquisition methods, device, computer equipment and storage medium, method to include：The finance product grade of target finance product is obtained according to the current attribute information of target finance product and default finance product Grade Model, finance product Grade Model finance product grade according to corresponding to the historical status information and historical status information of the first finance product carries out model pre-training and obtained；The trend that target finance product is obtained according to the current criteria state of target finance product and default finance product trend model is inclined to, and finance product trend model historical trend according to corresponding to the second finance product in the history index state of historical juncture and historical juncture carries out model pre-training and obtained；Asset Allocation strategy is obtained according to the finance product grade of target finance product and the trend of target finance product tendency.The above method can be saved the time that user checks information, and can improve the accuracy of the Asset Allocation strategy of acquisition.
Description
Technical field
The present invention relates to field of computer technology, is set more particularly to Asset Allocation strategy acquisition methods, device, computer
Standby and storage medium.
Background technology
In investment field of managing money matters, in order that the earning rate that financing capital can obtain is, it is necessary to finance product such as stock
The ups and downs of ticket are judged, with according to the dealing for judging progress finance product.At present, the judgement master of the ups and downs to finance product
If user is judged following ups and downs by after the information for checking finance product by conventional financing experience.
However, in the research and practice to prior art, it was found by the inventors of the present invention that following ask be present in prior art
Topic：The financing experience of user is limited, causes user to judge that the accuracy rate of the ups and downs of finance product is low, is additionally, since financing
Product quantity is more and finance product contains much information, and user checks and required a great deal of time one by one in terminal, wastes
Computer network resources.
The content of the invention
Based on this, it is necessary to judge that the accuracy rate of the ups and downs of finance product is low for user, it is too many to be additionally, since information,
User checks and requires a great deal of time one by one in terminal, the problem of wasting computer network resources, there is provided Yi Zhongzi
Produce configuration strategy acquisition methods, device, computer equipment and storage medium.
A kind of Asset Allocation strategy acquisition methods, methods described include：According to the current attribute information of target finance product
And default finance product Grade Model obtains the finance product grade of the target finance product, the finance product grade
Model finance product grade according to corresponding to the historical status information of the first finance product and the historical status information is carried out
Model pre-training obtains；Obtained according to the current criteria state of the target finance product and default finance product trend model
The trend of the target finance product is taken to be inclined to, the finance product trend model is according to the second finance product in the historical juncture
Historical trend corresponding to history index state and the historical juncture carries out model pre-training and obtained；Managed money matters according to the target
The finance product grade of product and the trend of target finance product tendency obtain Asset Allocation strategy.
In one embodiment, methods described also includes：Second finance product is obtained after the historical juncture
The historical price time series of preset time, the historical price time series include n+1 price；According to the historical price
Trend judgement parameter is calculated in time series, and the Trend judgement parameter includes price standard fraction, or the trend is sentenced
Disconnected parameter includes the price standard fraction and change utilization coefficient；According to described in the Trend judgement parameter acquiring during history
Historical trend corresponding to quarter；By second finance product in history index state and the history of the historical juncture
Historical trend corresponding to quarter forms training data, and carries out model training according to the training data, obtains the finance product
Trend model；Wherein, the price standard fraction subtracts history valency including (n+1)th price in the historical price time series
Lattice time series average value difference again divided by historical price time series standard deviation, it is described change utilization coefficient be the history
In price series the poor absolute value of t-th price and first price again divided by first price to t-th price it
Between adjacent price difference absolute value sum, t is equal to n or n+1, and the n is positive integer.
In one embodiment, the historical trend corresponding to the historical juncture according to the Trend judgement parameter acquiring
The step of include：When the price standard fraction is more than the first predetermined threshold value, and to be more than second default for the change utilization coefficient
During threshold value, historical trend corresponding to the historical juncture is obtained to go up；When the absolute value of the price standard fraction is less than institute
The first predetermined threshold value is stated, and when the utilization coefficient is less than second predetermined threshold value, obtains going through corresponding to the historical juncture
History trend is concussion；When first predetermined threshold value that is less than of the price standard fraction, and the utilization coefficient is more than second
During predetermined threshold value, historical trend corresponding to the historical juncture is obtained to decline；Wherein, first predetermined threshold value and second
Predetermined threshold value is more than 0 and less than or equal to 1.
In one embodiment, the current criteria state and default financing according to the target finance product is produced
The step of trend that product trend model obtains the target finance product is inclined to includes：When the financing of the target finance product is produced
When product grade is more than or equal to predetermined level, produced according to the current criteria state of the target finance product and default financing
Product trend model obtains the trend tendency of the target finance product；It is described according to the finance product grade and the trend
The step that tendency obtains Asset Allocation strategy includes：Preset when the finance product grade of the target finance product is more than or equal to
Grade, and the trend tendency of the target finance product is when going up, to obtain the Asset Allocation for buying in the target finance product
Strategy.
A kind of Asset Allocation strategy acquisition device, described device include：Grade acquiring unit, produced for being managed money matters according to target
The current attribute information of product and default finance product Grade Model obtain the finance product grade of the target finance product,
The finance product Grade Model is according to corresponding to the historical status information of the first finance product and the historical status information
Finance product grade carries out model pre-training and obtained；Trend is inclined to acquiring unit, for working as according to the target finance product
Preceding index state and default finance product trend model obtain the trend tendency of the target finance product, the financing production
Product trend model history according to corresponding to the second finance product in the history index state of historical juncture and the historical juncture
Trend carries out model pre-training and obtained；Tactful acquiring unit, for the finance product grade according to the target finance product with
And the trend tendency of the target finance product obtains Asset Allocation strategy.
In one embodiment, described device also includes：Time Series of Random Macro-price acquiring unit, for obtaining second reason
The historical price time series of property product preset time after the historical juncture, the historical price time series include n+
1 price；Trend judgement parameter calculation unit, for Trend judgement ginseng to be calculated according to the historical price time series
Number, the Trend judgement parameter includes price standard fraction, or the Trend judgement parameter includes the price standard fraction
And change utilization coefficient；Historical trend acquiring unit, for the historical juncture pair according to the Trend judgement parameter acquiring
The historical trend answered；Second model training unit, for by second finance product the historical juncture history index
Historical trend corresponding to state and the historical juncture forms training data, and carries out model instruction according to the training data
Practice, obtain the finance product trend model；Wherein, the price standard fraction is included the in the historical price time series
N+1 price subtract historical price time series average value difference again divided by historical price time series standard deviation, the change
Change poor absolute value that utilization coefficient is t-th price and first price in the historical price sequence again divided by described first
Individual price is to the sum of the absolute value of adjacent price difference between t-th of price, and t is equal to n or n+1, and the n is positive integer.
In one embodiment, the historical trend acquiring unit is specifically used for：When the price standard fraction is more than the
One predetermined threshold value, and the change utilization coefficient is when being more than the second predetermined threshold value, obtain the historical juncture corresponding to history become
Gesture is rise；When the absolute value of the price standard fraction is less than first predetermined threshold value, and the utilization coefficient is less than institute
When stating the second predetermined threshold value, historical trend corresponding to the historical juncture is obtained as concussion；It is small when the price standard fraction
In first predetermined threshold value, and when the utilization coefficient is more than the second predetermined threshold value, obtain going through corresponding to the historical juncture
History trend is decline；Wherein, first predetermined threshold value and the second predetermined threshold value are more than 0 and less than or equal to 1.
In one embodiment, the trend tendency acquiring unit is specifically used for：When the financing of the target finance product
When product hierarchy is more than or equal to predetermined level, according to the current criteria state of the target finance product and default financing
Product trend model obtains the trend tendency of the target finance product；The tactful acquiring unit is used for：When the target is managed
The finance product grade of property product is more than or equal to predetermined level, and when the trend tendency of the target finance product is goes up,
Obtain the Asset Allocation strategy for buying in the target finance product.
A kind of computer equipment, including memory and processor, computer-readable instruction are stored with the memory, institute
When stating computer-readable instruction by the computing device so that the above-mentioned Asset Allocation strategy acquisition methods of computing device
The step of.
A kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction are handled by one or more
When device performs so that one or more processors perform the step of above-mentioned Asset Allocation strategy acquisition methods.
Above-mentioned Asset Allocation strategy acquisition methods, device, computer equipment and storage medium, finance product Grade Model
It is that finance product grade carries out model pre-training according to corresponding to the historical status information and historical status information of finance product
Obtain, finance product trend model is the historical trend according to corresponding to the history index state of finance product and historical juncture
Model pre-training is carried out to obtain, the attribute information and index state of finance product often contain respectively finance product etc.
The rule of level and the follow-up rising trend of finance product, therefore carried out using the finance product attribute information and index status information of history
Model training can accurately find out the rule of these data.Therefore, can be according to target when needing to obtain Asset Allocation strategy
The finance product grade of the current attribute information of finance product and default finance product Grade Model prediction finance product, root
It is inclined to according to the trend of the current criteria state of target finance product and default finance product trend model prediction finance product,
Then the Asset Allocation plan according to corresponding to obtaining the finance product grade of target finance product and the trend of finance product tendency
Slightly, user has been saved and has checked time and the computer network resources of bulk information, and the Asset Allocation plan of acquisition can be improved
Accuracy slightly.
Brief description of the drawings
Fig. 1 is the implementation environment figure of the Asset Allocation strategy acquisition methods provided in one embodiment；
Fig. 2 is the internal structure block diagram of one embodiment Computer equipment；
Fig. 3 is the flow chart of Asset Allocation strategy acquisition methods in one embodiment；
Fig. 4 is the flow chart of Asset Allocation strategy acquisition methods in one embodiment；
Fig. 5 is the flow chart of Asset Allocation strategy acquisition methods in one embodiment；
Fig. 6 is the structured flowchart of Asset Allocation strategy acquisition device in one embodiment；
Fig. 7 is the structured flowchart of Asset Allocation strategy acquisition device in one embodiment；
Fig. 8 is the structured flowchart of Asset Allocation strategy acquisition device in one embodiment.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is appreciated that term " first " used in this application, " second " etc. can be used to describe various elements herein,
Unless stated otherwise, otherwise these elements should not be limited by these terms.These terms are only used for first element and another
Element is distinguished.For example, in the case where not departing from scope of the present application, the first predetermined threshold value can be referred to as second and preset
Threshold value, and similarly, the second predetermined threshold value can be referred to as the first predetermined threshold value.But if the present invention clearly represents above-mentioned the
First, second is except representing order, for example, herein, first, n-th, t-th limitation included to order.
Fig. 1 is the implementation environment figure of the Asset Allocation strategy acquisition methods provided in one embodiment, as shown in figure 1,
In the implementation environment, including market feature acquisition device 110, computer equipment 120 and transaction system 130.
As shown in figure 1, after market characterizing arrangement 110 obtains the current finance product market of target finance product, it is input to
In computer equipment 120, computer equipment 120 is believed according to the current attribute of target finance product in the finance product market of input
Breath and finance product Grade Model obtain the finance product grade of target finance product, the current finger according to target finance product
Mark state and finance product trend model obtain the trend tendency of target finance product, then according to the reason of target finance product
Wealth product hierarchy and trend tendency obtain Asset Allocation strategy, and after Asset Allocation strategy is got, computer equipment 120 can
So that the Asset Allocation strategy is output in client, so that user checks.Directly it can also be sent out according to the Asset Allocation strategy
Transaction request is sent to be traded into transaction system 130.
For example, after the Asset Allocation strategy for buying in A01 finance products is got, it can be exported to user and buy in the financing
The suggestion of product, the transaction request for buying in the finance product can be sent to transaction system, trading volume can be advance according to user
Set and determine, can also be judged according to the intensity that the specific grade of finance product and trend are inclined to.
Above-mentioned computer equipment 120 can be independent physical server or terminal or multiple physical services
The server cluster that device is formed, can be to provide the basic cloud computing services such as Cloud Server, cloud database, cloud storage and CDN
Cloud Server.Finance product can be the noble metals such as silver, gold, can also be oil, stock, futures etc..
As shown in Fig. 2 being the cut-away view of one embodiment Computer equipment, the computer equipment is connected by system
Connect bus couple processor, non-volatile memory medium, built-in storage and network interface.Wherein, the computer equipment is non-easy
Lose property storage medium can storage program area and computer-readable instruction, when the computer-readable instruction is performed, may be such that place
Manage device and perform a kind of Asset Allocation strategy acquisition methods.The processor of the computer equipment is used to provide calculating and control ability,
Support the operation of whole computer equipment.Computer-readable instruction can be stored in the built-in storage, the computer-readable instruction
When being executed by processor, a kind of Asset Allocation strategy acquisition methods of computing device are may be such that.The network interface of computer equipment
For carrying out network service, Asset Allocation strategy is such as sent.It will be understood by those skilled in the art that the structure shown in Fig. 2,
The only block diagram of the part-structure related to application scheme, the calculating being applied thereon to application scheme is not formed
The restriction of machine equipment, specific computer equipment can include more some than more or less parts shown in figure, or combination
Part, or arranged with different parts.
As shown in figure 3, in one embodiment it is proposed that a kind of Asset Allocation strategy acquisition methods, the Asset Allocation plan
Slightly acquisition methods can apply in above-mentioned computer equipment 120, specifically may comprise steps of：
Step S302, obtained according to the current attribute information of target finance product and default finance product Grade Model
The finance product grade of target finance product.
The attribute information of finance product is the substantive characteristics or characteristic of finance product, such as the p/e ratio of finance product, city
Now rate, liquidity ratio and information ratio etc..Current attribute information refers to the attribute information in current target finance product, goes through
History attribute information refers to the attribute information of the finance product of historical juncture first before current time.Current time and historical juncture
The quantity of the attribute information of finance product can be configured according to being actually needed.For example, current time and historical juncture reason
The attribute information of property product can be the existing rate two of p/e ratio and city.Can also be p/e ratio, the existing rate in city, liquidity ratio and
Information ratio four.Certainly, other attribute informations of finance product can also be also added, to be more accurately predicted.Can be with
Understand, the moment can refer to a time point or a period of time.
Finance product grade corresponding to historical status information under the historical status information the first finance product etc.
Level.The grade of finance product can with it is excellent, in and the default grade such as difference quantified, can also be carried out with specific fraction
Quantify, as long as can classify to finance product.Default finance product Grade Model is to be produced in advance according to the first financing
Finance product grade corresponding to the historical status information and historical status information of product carries out what model pre-training obtained, works as training
After good model, the current attribute information of target finance product is input in the finance product Grade Model trained, can be obtained
To finance product grade corresponding to target finance product.
Step S304, obtained according to the current criteria state of target finance product and default finance product trend model
The trend tendency of target finance product.
Index state refers to one of relation between the state and index of each index of finance product or group
Close.Such as can be the magnitude relationship between the moving average of finance product, can be DEA (Difference
Exponential Average, smooth rolling average) be on the occasion of or negative value, DIF (Difference, deviation value) and DEA
The pass of the magnitude relationship of (Difference Exponential Average, smooth rolling average), share price and moving average
System, share price pressure line, the relation for supporting these three indexs of line and share price average line etc..Relation between each index can divide
To be multiple, for example, index 1 is more than that index 2, index 1 be equal with index 2, index 1 less than index 2, index 1 it is equal with index 2 and
The value of index 1 reduces.For example, moving average on the 5th is more than moving average on the 10th, DIF from low down more than DEA,
The distance between share price pressure line, support line and share price average line this three narrow.
Current criteria state refers to the index state in current target finance product.History index state refers to current time
The index state of the finance product of historical juncture second before, it will be understood that the moment can refer to a time point, can also refer to one
The section time.The quantity of the index state at current time and the index state of historical juncture can be according to being actually configured.Go through
Historical trend corresponding to the history moment referred in the historical juncture ensuing finance product of a period of time second relative to the historical juncture
Ups and downs trend, for example, a certain historical juncture is on December 15th, 2016, then its corresponding historical trend can be rising after 3 days
Fall situation, i.e. on December 18th, 2016 is rise, drop or concussion etc. relative to finance product price on December 15.
Trend is inclined to the ups and downs trend for referring to finance product, can be to go up, drop and shake, or ups and downs trend
Probability, for example, rise probability be 80% etc..It is unstable that concussion refers to finance product price, when height when rising.Default finance product
Trend model is the historical trend according to corresponding to the second finance product in the history index state of historical juncture and historical juncture
Carry out model pre-training to obtain, after model is trained, the current criteria state of target finance product is input to what is trained
In finance product trend model, the trend tendency of target finance product can be obtained.
Step S306, obtained according to the finance product grade of target finance product and the trend of target finance product tendency
Asset Allocation strategy.
Asset Allocation strategy refers to the suggestion bought and sold to finance product, can include the plan of one or more finance products
Slightly.It is that finance product grade is low as judged for example, the finance product held for user, under the trend tendency of finance product is
When falling, then it can suggest selling the finance product.The finance product do not held for user, if meeting the bar of selecting stocks of user
Part, and grade is high, trend is rise, then the Asset Allocation strategy that buy in the finance product can be sent to user.Certainly, for
The finance product that user has held, and grade is high, trend is rise, can also suggest that user continues to buy in.
In certain embodiments, Asset Allocation strategy can also include finance product trading volume.It can be managed money matters according to target
The trend tendency and/or finance product grade of product determine finance product trading volume.For example, the trend of setting is inclined to and trading volume
Corresponding relation, the corresponding relation of finance product grade and finance product trading volume.Trend tendency is higher for the probability to go up, then buys
The trading volume entered is bigger, and finance product higher grade, then the trading volume bought in is bigger.When the trend for getting target finance product
Tendency and finance product grade, it can be inclined to according to trend and the corresponding relation of trading volume and/or finance product grade and financing
Finance product trading volume corresponding to the corresponding relation acquisition of product trading amount.
It should be noted that the quantity of the first above-mentioned finance product, the second finance product and target finance product can
Think one or more, the first finance product, the second finance product and target finance product can be with entirely different, can also be complete
It is exactly the same, or part is identical.For example, the information that can obtain thousands of individual stocks carries out model training, the model is then utilized
Predict A-share ticket, B stocks.Model training only can also be carried out with the information of A-share ticket, then utilize the model prediction A-share ticket.
The embodiment of the present invention to the acquisition modes of target finance product without limiting, such as can be according to user can be with
The risk classifications undertaken are obtained, and can also be obtained at random.It can also be chosen according to selection of the user to certain industry a certain
Industry finance product is as target finance product.
Above-mentioned steps S302 and S304 can be carried out simultaneously, can also successively be carried out.Specifically can be according to being actually needed
Set S302 and S304 execution sequence, assets strategy configuration device receive and according to the execution sequence perform step S302 with
And S304.For example, to reduce the number of computations of target finance product, the trend tendency of target finance product can be first obtained, when
When trend tendency is goes up, then obtain the grade of the target finance product.Or the grade of target finance product is first obtained, when
When grade is higher than predetermined level, as good performance stocks when, then obtain target finance product trend tendency.
In one embodiment, step S304 is the current criteria state according to target finance product and default financing
The step of trend that product trend model obtains target finance product is inclined to includes：When the finance product grade of target finance product
During more than or equal to predetermined level, according to the current criteria state of target finance product and default finance product trend model
Obtain the trend tendency of target finance product.Step S306 obtains Asset Allocation according to finance product grade and trend tendency
The step of strategy includes：When the finance product grade of target finance product is more than or equal to predetermined level, and target finance product
Trend tendency to go up when, obtain and buy in the Asset Allocation strategy of target finance product.
By finance product grade for it is excellent, in, exemplified by poor three-level, if during predetermined level is, when according to finance product grade
When during the finance product grade that model obtains is or excellent, the current criteria state of target finance product is input to default reason
In property product trend model, the trend tendency of target finance product is obtained, if trend tendency is goes up, the target is bought in acquisition
The Asset Allocation strategy of finance product.If the finance product grade for obtaining target finance product is poor, without finance product
The prediction of trend tendency.
Above-mentioned Asset Allocation strategy acquisition methods, finance product Grade Model are the history category according to the first finance product
Property information and historical status information corresponding to finance product grade carry out model pre-training and obtain, finance product trend model
It is that historical trend progress model pre-training obtains according to corresponding to the history index state of the second finance product and historical juncture
, because the attribute information and index state of finance product often contain the grade and finance product of finance product respectively
The rule of follow-up rising trend, therefore can be accurate using finance product attribute information and index status information the progress model training of history
Really find out the rule of these data.Therefore, can be according to the current of target finance product when needing to obtain Asset Allocation strategy
The finance product grade of attribute information and default finance product Grade Model prediction finance product, according to target finance product
Current criteria state and default finance product trend model prediction finance product trend tendency, then managed according to target
Asset Allocation strategy corresponding to the finance product grade of property product and the trend tendency acquisition of finance product, has saved user and has looked into
See the time of bulk information, and the Asset Allocation strategy accuracy rate obtained is high.
In one embodiment, as shown in figure 4, assets tactics configuring method can also comprise the following steps：
S402, obtain the historical price time series of the second finance product preset time after the historical juncture, history valency
Lattice time series includes n+1 price.
Historical price time series develops for the price of preset time after historical juncture and historical juncture according to the time
The sequence of order sequence composition.Preset time can be configured according to actual requirement.Preset time includes after historical juncture
Historical juncture.Time interval between each historical price is identical.Such as can be continuous 7 days, daily closing price.Again
For example, the historical juncture is on May 1st, 2016, preset time is 7 days, then historical price time series is May 1 to May 8
The sequence of the price composition of every day, totally 8 prices.Using the price of historical juncture as P0, i.e., originally price is P0, final price
For Pn, then historical price sequence can be expressed as { P0、P1、P2、……Pn}。
S404, Trend judgement parameter is calculated according to historical price time series, Trend judgement parameter includes price mark
Quasi- fraction, or Trend judgement parameter include price standard fraction and change utilization coefficient.
Wherein, price standard fraction is that (n+1)th price subtracts historical price time series in historical price time series
Average value difference again divided by historical price time series standard deviation, change utilization coefficient be historical price sequence in t-th of valency
Lattice and the poor absolute value of first price are again divided by first price is to the absolute value of adjacent price difference between t-th of price
It is positive integer to be equal to n or n+1, n with, t.It is appreciated that (n+1)th price refers to price final in historical price sequence, the
One price refers to price initial in historical price sequence, is represented with formula, and price standard fraction A formula can be such as formula (1)
Shown, so that t is equal to n as an example, change utilization coefficient B formula can be as shown in formula (2).
Wherein, P represents historical price sequence, PnRepresent (n+1)th price, i.e. final price in preset time, P0Represent
First price, the i.e. price of historical juncture namely originate price, Pi+1For the i-th+2 prices in historical price sequence, PiFor
I+1 price in historical price sequence, wherein i is more than or equal to 0, less than or equal to n-1.E (P) is the equal of historical price sequence
Value, σ (P) are the standard deviation of historical price sequence.
From formula (1), (n+1)th price is so converted, the value of final price can be obtained in historical price sequence
Size position in row, if A is more than 0, final price is represented on the average of historical price sequence, A is less than 0, then it represents that
Final price is under the average of historical price sequence.
Explained by taking n=4 as an example, the meaning of above-mentioned formula (2) is as follows：If c1, c2, c3 are respectively P1With P0Difference, P2
With P1Difference, P3With P2Difference, then P1、P2、P3P can be expressed as0+c1、P0+c1+c2、P0+ c1+c2+c2, therefore formula 2 can be with
Formula (3) is turned to, from formula 3, B is less than or equal to 1 and more than or equal to 0, if equal to 1, illustrates within this time, financing production
Product rise or declined always always.There is fluctuation during equal to other values, therefore finance product can be judged according to B size
Fluctuation situation.
S406, according to historical trend corresponding to the Trend judgement parameter acquiring historical juncture.
Historical trend corresponding to historical juncture refer to the historical juncture ensuing finance product of a period of time second relative to
The ups and downs trend of historical juncture.When Trend judgement parameter includes price standard fraction, can set when price standard fraction is big
Historical trend corresponding to the historical juncture is then represented when predetermined threshold value to go up, then represents that the historical juncture corresponding less than predetermined threshold value
Historical trend for decline.Or when Trend judgement parameter includes price standard fraction and change utilization coefficient, Ke Yijie
Close price standard fraction and change utilization coefficient determines historical trend.
In one embodiment, in order that obtained finance product trend model preferably predicts finance product trend, because
This carries out model training, it is necessary to choose the obvious historical data of trend, therefore corresponding according to the Trend judgement parameter acquiring historical juncture
Historical trend the step of include：When price standard fraction is more than the first predetermined threshold value, and changes utilization coefficient to be more than second pre-
If during threshold value, historical trend corresponding to the historical juncture is obtained to go up；Preset when the absolute value of price standard fraction is less than first
Threshold value, and change utilization coefficient when being less than the second predetermined threshold value, historical trend corresponding to the historical juncture is obtained to shake；Work as price
Criterion score is less than the first predetermined threshold value, and when changing utilization coefficient and being more than the second predetermined threshold value, obtains historical juncture correspondence
Historical trend for decline；Wherein, the first predetermined threshold value and the second predetermined threshold value are more than 0 and are less than or equal to 1.
For example, when the first predetermined threshold value is 0.1, and the second predetermined threshold value is 0.4, if the valency of some the second finance product
Lattice criterion score is 0.5, and change utilization coefficient is 0.6, then can obtain historical trend to go up.
In certain embodiments, when the second predetermined threshold value is 0.5, the trend sample pattern prediction effect of acquisition is good.
S408, by the second finance product in historical trend corresponding to the history index state of historical juncture and historical juncture
Training data is formed, and model training is carried out according to training data, obtains finance product trend model.
It can also be multiple that the quantity of second finance product, which can be one, and the quantity of training data specifically can be according to reality
Border obtains, such as it can also be tens of thousands of that can be hundreds of.Each training data includes second finance product one
History index state and corresponding historical trend under the individual historical juncture.History index state can be one or more.Example
Such as, divide in the case of during 16 days 12 June 2016 historical juncture 55, then under the historical juncture, history index state can include 5
Day moving average be more than moving average on the 10th, DEA values more than 0, DEA values from small up more than DIF values etc., corresponding history
Trend is rise.After training data is got, carry out machine learning is carried out according to the training data, obtains machine learning training
Obtained model parameter, obtain finance product trend model.
The model of machine learning can be SVMs (Support Vector Machine, SVM) sorter model,
Neutral net (Artificial Neural Network, ANN) sorter model, logistic regression algorithm (logistic
Regression, LR) sorter model and hidden Markov model (Hidden Markov Model, HMM) etc. are various is divided
The model of class.The kernel function of use can be configured according to actual requirement, for example, in one embodiment, can use branch
The machine learning that vector machine carries out having supervision is held, kernel function can use polynomial function.
In one embodiment, as shown in figure 5, assets tactics configuring method can also comprise the following steps：
S502, obtains the first training sample set being made up of multiple first training samples, and the first training sample includes first
Finance product grade corresponding to multiple historical status information and historical status of the finance product in the historical juncture.
The quantity of first finance product can be one or more, and the first training sample concentrates the first number of training measurer
Body can be according to actual acquisition, such as it can also be tens of thousands of that can be hundreds of.Each first training sample includes multiple
Historical status information and corresponding finance product grade.Such as it is the existing rate in 5%, city that historical status information, which can include p/e ratio,
It is 20% etc. for 10%, turnover rate, corresponding finance product grade is good performance stocks.Finance product grade can taking human as mark,
Can be by obtaining the data of finance product, and then obtained according to dependent quantization formula.
In certain embodiments, the grade of the first finance product can be judged by Suo Tinuo ratios, Suo Tinuo
Ratio, which refers to, often to be undertaken the descending fluctuation of a unit and can be obtained unit income, and numerical value is bigger, illustrates to undertake same Downside Risk
In the case of, the return on more excess earnings or benchmark can be obtained.For example, it can set when Suo Tinuo ratios are more than
It is good performance stocks during three predetermined threshold values, is non-good performance stocks during less than certain four predetermined threshold value.3rd predetermined threshold value and
Four predetermined threshold values can be set according to specific requirement.
S504, model training is carried out according to the first training sample set, obtains finance product Grade Model.
After the first training sample set is got, carry out machine learning is carried out according to the first sample collection, obtains engineering
The model parameter that training obtains is practised, obtains finance product Grade Model.
The model of machine learning can be SVMs (Support Vector Machine, SVM) sorter model,
Neutral net (Artificial Neural Network, ANN) sorter model, logistic regression algorithm (logistic
Regression, LR) sorter model and hidden Markov model (Hidden Markov Model, HMM) etc. are various is divided
The model of class.The kernel function of use can be configured according to actual requirement, for example, in one embodiment, can use branch
The machine learning that vector machine carries out having supervision is held, kernel function can use polynomial function.
As shown in fig. 6, in one embodiment, there is provided a kind of Asset Allocation strategy acquisition device, the Asset Allocation plan
Slightly acquisition device can be integrated in above-mentioned computer equipment 120, can specifically include grade acquiring unit 602, trend is inclined
To acquiring unit 604 and tactful acquiring unit 606.
Grade acquiring unit 602, for the current attribute information according to target finance product and default finance product
Grade Model obtains the finance product grade of target finance product.
Default finance product Grade Model is believed according to the historical status information and historical status of the first finance product
Finance product grade corresponding to breath carries out what model pre-training obtained.
Trend is inclined to acquiring unit 604, for the current criteria state according to target finance product and default financing
Product trend model obtains the trend tendency of target finance product.
Default finance product trend model be according to the second finance product the historical juncture history index state and
Historical trend corresponding to historical juncture carries out what model pre-training obtained.
Tactful acquiring unit 606, for the finance product grade according to target finance product and target finance product
Trend tendency obtains Asset Allocation strategy.
In one embodiment, trend tendency acquiring unit 604 is used for：When the finance product grade of target finance product is big
When predetermined level, obtained according to the current criteria state of target finance product and default finance product trend model
The trend of target finance product is taken to be inclined to.Tactful acquiring unit 606 is used for：When the finance product grade of target finance product is more than
Or equal to predetermined level, and the trend tendency of target finance product is that the assets that target finance product is bought in acquisition are matched somebody with somebody when going up
Put strategy.
Above-mentioned Asset Allocation strategy acquisition device, finance product Grade Model are the history category according to the first finance product
Property information and historical status information corresponding to finance product grade carry out model pre-training and obtain, finance product trend model
It is that historical trend progress model pre-training obtains according to corresponding to the history index state of the second finance product and historical juncture
, the attribute information and index state of finance product often contain respectively finance product grade and finance product it is follow-up
The rule of rising trend, therefore carry out model training using the finance product attribute information and index status information of history and can accurately look for
Go out the rule of these data.Therefore, can be according to the current attribute of target finance product when needing to obtain Asset Allocation strategy
The finance product grade of information and default finance product Grade Model prediction finance product, according to working as target finance product
The trend tendency of preceding index state and default finance product trend model prediction finance product, then manages money matters according to target and produces
Asset Allocation strategy corresponding to the finance product grade of product and the trend tendency acquisition of finance product, has saved user and has checked greatly
Measure the time of information, and accuracy rate is high.
In one embodiment, as shown in fig. 7, assets strategy configuration device, which can also include Time Series of Random Macro-price, obtains list
Member 702, Trend judgement parameter calculation unit 704, the model training unit 708 of historical trend acquiring unit 706 and second：
Time Series of Random Macro-price acquiring unit 702, for obtaining the second finance product preset time after the historical juncture
Historical price time series, historical price time series include n+1 price.
Trend judgement parameter calculation unit 704, for obtaining the Trend judgement parameter of historical price time series, trend is sentenced
Disconnected parameter includes price standard fraction, or Trend judgement parameter includes price standard fraction and change utilization coefficient.
Historical trend acquiring unit 706, become for obtaining history according to Trend judgement parameter and default judgment rule
Gesture.
Second model training unit 708, for by the second finance product the historical juncture history index state and go through
Historical trend corresponding to the history moment forms training data, and carries out model training according to training data, obtains finance product trend
Model.
In one embodiment, as shown in figure 8, assets strategy configuration device can also include first sample collection acquiring unit
802 and the first model training unit 804：
First sample collection acquiring unit 802, for obtaining the first training sample set being made up of multiple first training samples,
First training sample includes reason corresponding to multiple historical status information and historical status of first finance product in the historical juncture
Wealth product hierarchy；
First model training unit 804, for carrying out model training according to the first training sample set, obtain finance product etc.
Level model.
In one embodiment, the Asset Allocation strategy acquisition device that the application provides can be implemented as a kind of computer journey
The form of sequence, computer program can be run on computer equipment as shown in Figure 2, and the non-volatile memories of computer equipment are situated between
Matter can store each program module for forming the Asset Allocation strategy acquisition device, such as grade acquiring unit 602 in Fig. 6,
Trend is inclined to acquiring unit 604 and tactful acquiring unit 606.Each program module includes computer-readable instruction, calculates
Machine readable instruction is used for the Asset Allocation strategy for making computer equipment perform each embodiment of the application described in this specification
Step in acquisition methods.For example, computer equipment can be by throwing grade acquiring unit 602 as shown in Figure 6 according to target
The current attribute information of finance product and default finance product Grade Model obtain finance product of target finance product etc.
Level, acquiring unit 604 is inclined to by trend and become according to the current criteria state and default finance product of target finance product
Potential model obtains the trend tendency of target finance product, is produced by tactful acquiring unit 606 according to the financing of target finance product
Product grade and the trend of target finance product tendency obtain Asset Allocation strategy.
In one embodiment it is proposed that a kind of computer equipment, computer equipment include memory, processor and storage
On a memory and the computer program that can run on a processor, following steps are realized during computing device computer program：
The reason of target finance product is obtained according to the current attribute information of target finance product and default finance product Grade Model
Wealth product hierarchy, finance product Grade Model are corresponding according to the historical status information and historical status information of the first finance product
Finance product grade carry out model pre-training obtain；According to the current criteria state of target finance product and default financing
Product trend model obtains the trend tendency of target finance product, and finance product trend model is according to the second finance product in history
Historical trend corresponding to the history index state at moment and historical juncture carries out model pre-training and obtained；Managed money matters and produced according to target
The finance product grade of product and the trend tendency of target finance product obtain Asset Allocation strategy.
In one embodiment, following steps are also performed during computing device computer-readable instruction：Obtain the second financing
The historical price time series of product preset time after the historical juncture, historical price time series include n+1 price；Root
Trend judgement parameter is calculated according to historical price time series, Trend judgement parameter includes price standard fraction, or trend
Judge that parameter includes price standard fraction and change utilization coefficient；Gone through according to corresponding to the Trend judgement parameter acquiring historical juncture
History trend；By the second finance product in historical trend composition instruction corresponding to the history index state of historical juncture and historical juncture
Practice data, and model training is carried out according to training data, obtain finance product trend model；Wherein, price standard fraction includes
(n+1)th price subtracts the difference of historical price time series average value again divided by the historical price time in historical price time series
The standard deviation of sequence, change utilization coefficient be the poor absolute value of t-th price and first price in historical price sequence again
Divided by first price, to the sum of the absolute value of adjacent price difference between t-th of price, it is positive integer that t, which is equal to n or n+1, n,.
In one embodiment, the historical trend according to corresponding to the Trend judgement parameter acquiring historical juncture, including：Work as price
Criterion score is more than the first predetermined threshold value, and when changing utilization coefficient and being more than the second predetermined threshold value, obtains corresponding to the historical juncture
Historical trend is rise；When the absolute value of price standard fraction is less than the first predetermined threshold value, and to be less than second default for utilization coefficient
During threshold value, historical trend corresponding to the historical juncture is obtained as concussion；When first predetermined threshold value that is less than of price standard fraction, and imitate
When being more than the second predetermined threshold value with coefficient, historical trend corresponding to the historical juncture is obtained to decline；Wherein, the first predetermined threshold value with
And second predetermined threshold value be more than 0 and less than or equal to 1.
In one embodiment, according to the current criteria state of target finance product and default finance product trend mould
Type obtains the trend tendency of target finance product, including：Preset when the finance product grade of target finance product is more than or equal to
During grade, target financing production is obtained according to the current criteria state of target finance product and default finance product trend model
The trend tendency of product；The step of Asset Allocation strategy is obtained according to finance product grade and trend tendency to be included：When target is managed
The finance product grade of property product is more than or equal to predetermined level, and the trend tendency of target finance product is when going up, to obtain
Buy in the Asset Allocation strategy of target finance product.
In one embodiment it is proposed that a kind of storage medium for being stored with computer-readable instruction, this is computer-readable
When instruction is executed by one or more processors so that one or more processors perform following steps：Managed money matters and produced according to target
The current attribute information of product and default finance product Grade Model obtain the finance product grade of target finance product, financing
Product hierarchy model finance product grade according to corresponding to the historical status information and historical status information of the first finance product
Model pre-training is carried out to obtain；Obtained according to the current criteria state of target finance product and default finance product trend model
Take the trend of target finance product to be inclined to, finance product trend model according to the second finance product the historical juncture history index
Historical trend corresponding to state and historical juncture carries out model pre-training and obtained；Finance product according to target finance product etc.
Level and the trend of target finance product tendency obtain Asset Allocation strategy.
In one embodiment, following steps are also performed during computing device computer-readable instruction：Obtain the second financing
The historical price time series of product preset time after the historical juncture, historical price time series include n+1 price；Root
Trend judgement parameter is calculated according to historical price time series, Trend judgement parameter includes price standard fraction, or trend
Judge that parameter includes price standard fraction and change utilization coefficient；Gone through according to corresponding to the Trend judgement parameter acquiring historical juncture
History trend；By the second finance product in historical trend composition instruction corresponding to the history index state of historical juncture and historical juncture
Practice data, and model training is carried out according to training data, obtain finance product trend model；Wherein, price standard fraction includes
(n+1)th price subtracts the difference of historical price time series average value again divided by the historical price time in historical price time series
The standard deviation of sequence, change utilization coefficient be the poor absolute value of t-th price and first price in historical price sequence again
Divided by first price, to the sum of the absolute value of adjacent price difference between t-th of price, it is positive integer that t, which is equal to n or n+1, n,.
In one embodiment, the historical trend according to corresponding to the Trend judgement parameter acquiring historical juncture, including：Work as price
Criterion score is more than the first predetermined threshold value, and when changing utilization coefficient and being more than the second predetermined threshold value, obtains corresponding to the historical juncture
Historical trend is rise；When the absolute value of price standard fraction is less than the first predetermined threshold value, and to be less than second default for utilization coefficient
During threshold value, historical trend corresponding to the historical juncture is obtained as concussion；When first predetermined threshold value that is less than of price standard fraction, and imitate
When being more than the second predetermined threshold value with coefficient, historical trend corresponding to the historical juncture is obtained to decline；Wherein, the first predetermined threshold value with
And second predetermined threshold value be more than 0 and less than or equal to 1.
In one embodiment, according to the current criteria state of target finance product and default finance product trend mould
Type obtains the trend tendency of target finance product, including：Preset when the finance product grade of target finance product is more than or equal to
During grade, target financing production is obtained according to the current criteria state of target finance product and default finance product trend model
The trend tendency of product；The step of Asset Allocation strategy is obtained according to finance product grade and trend tendency to be included：When target is managed
The finance product grade of property product is more than or equal to predetermined level, and the trend tendency of target finance product is when going up, to obtain
Buy in the Asset Allocation strategy of target finance product.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, the computer program can be stored in a computer-readable storage and be situated between
In matter, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, foregoing storage medium can be
The non-volatile memory mediums such as magnetic disc, CD, read-only memory (Read-Only Memory, ROM), or random storage note
Recall body (Random Access Memory, RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope that this specification is recorded all is considered to be.
Embodiment described above only expresses the several embodiments of the present invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of Asset Allocation strategy acquisition methods, it is characterised in that methods described includes：
The target financing is obtained according to the current attribute information of target finance product and default finance product Grade Model
The finance product grade of product, the finance product Grade Model is according to the historical status information of the first finance product and described
Finance product grade corresponding to historical status information carries out model pre-training and obtained；
The target is obtained according to the current criteria state of the target finance product and default finance product trend model
Finance product trend tendency, the finance product trend model according to the second finance product the historical juncture history index shape
Historical trend corresponding to state and the historical juncture carries out model pre-training and obtained；
Assets are obtained according to the finance product grade of the target finance product and the trend of target finance product tendency
Configuration strategy.
2. according to the method for claim 1, it is characterised in that methods described also includes：
Obtain the historical price time series of second finance product preset time after the historical juncture, the history
Time Series of Random Macro-price includes n+1 price；
Trend judgement parameter is calculated according to the historical price time series, the Trend judgement parameter includes price standard
Fraction, or the Trend judgement parameter include the price standard fraction and change utilization coefficient；
The historical trend corresponding to the historical juncture according to the Trend judgement parameter acquiring；
By second finance product in history corresponding to the history index state of the historical juncture and the historical juncture
Trend forms training data, and carries out model training according to the training data, obtains the finance product trend model；
Wherein, when the price standard fraction subtracts historical price including (n+1)th price in the historical price time series
Between serial mean difference again divided by historical price time series standard deviation, it is described change utilization coefficient be the historical price
The poor absolute value of t-th of price and first price is again in sequence divided by first price is to phase between t-th of price
The sum of the absolute value of adjacent price difference, t are equal to n or n+1, and the n is positive integer.
3. according to the method for claim 2, it is characterised in that the history according to the Trend judgement parameter acquiring
Include corresponding to moment the step of historical trend：
When the price standard fraction is more than the first predetermined threshold value, and the change utilization coefficient is more than the second predetermined threshold value,
Historical trend corresponding to the historical juncture is obtained to go up；
When the absolute value of the price standard fraction is less than first predetermined threshold value, and the utilization coefficient is less than described second
During predetermined threshold value, historical trend corresponding to the historical juncture is obtained as concussion；
It is less than first predetermined threshold value when the price standard fraction, and the utilization coefficient is more than the second predetermined threshold value
When, historical trend corresponding to the historical juncture is obtained to decline；
Wherein, first predetermined threshold value and the second predetermined threshold value are more than 0 and less than or equal to 1.
4. according to the method for claim 1, it is characterised in that the current criteria shape according to the target finance product
The step of trend that state and default finance product trend model obtain the target finance product is inclined to includes：
When the finance product grade of the target finance product is more than or equal to predetermined level, according to the target finance product
Current criteria state and default finance product trend model obtain the trend tendency of the target finance product；
The step that Asset Allocation strategy is obtained according to the finance product grade and trend tendency includes：
When the finance product grade of the target finance product is more than or equal to predetermined level, and the target finance product becomes
When gesture tendency is goes up, the Asset Allocation strategy for buying in the target finance product is obtained.
5. a kind of Asset Allocation strategy acquisition device, it is characterised in that described device includes：
Grade acquiring unit, for the current attribute information according to target finance product and default finance product Grade Model
Obtain the finance product grade of the target finance product, the finance product Grade Model is according to the history of the first finance product
Finance product grade corresponding to attribute information and the historical status information carries out model pre-training and obtained；
Trend is inclined to acquiring unit, for the current criteria state according to the target finance product and default finance product
Trend model obtains the trend tendency of the target finance product, and the finance product trend model exists according to the second finance product
Historical trend corresponding to the history index state of historical juncture and the historical juncture carries out model pre-training and obtained；
Tactful acquiring unit, for the finance product grade according to the target finance product and the target finance product
Trend tendency obtains Asset Allocation strategy.
6. device according to claim 5, it is characterised in that described device also includes：
Time Series of Random Macro-price acquiring unit, for obtaining second finance product preset time after the historical juncture
Historical price time series, the historical price time series include n+1 price；
Trend judgement parameter calculation unit, for Trend judgement parameter, institute to be calculated according to the historical price time series
Stating Trend judgement parameter includes price standard fraction, or the Trend judgement parameter includes the price standard fraction and change
Change utilization coefficient；
Historical trend acquiring unit, for the historical trend corresponding to the historical juncture according to the Trend judgement parameter acquiring；
Second model training unit, for by history index state of second finance product in the historical juncture and institute
State historical trend corresponding to the historical juncture and form training data, and model training is carried out according to the training data, obtain described
Finance product trend model；
Wherein, when the price standard fraction subtracts historical price including (n+1)th price in the historical price time series
Between serial mean difference again divided by historical price time series standard deviation, it is described change utilization coefficient be the historical price
The poor absolute value of t-th of price and first price is again in sequence divided by first price is to phase between t-th of price
The sum of the absolute value of adjacent price difference, t are equal to n or n+1, and the n is positive integer.
7. according to the method for claim 6, it is characterised in that the historical trend acquiring unit is specifically used for：
When the price standard fraction is more than the first predetermined threshold value, and the change utilization coefficient is more than the second predetermined threshold value,
Historical trend corresponding to the historical juncture is obtained to go up；
When the absolute value of the price standard fraction is less than first predetermined threshold value, and the utilization coefficient is less than described second
During predetermined threshold value, historical trend corresponding to the historical juncture is obtained as concussion；
It is less than first predetermined threshold value when the price standard fraction, and the utilization coefficient is more than the second predetermined threshold value
When, historical trend corresponding to the historical juncture is obtained to decline；
Wherein, first predetermined threshold value and the second predetermined threshold value are more than 0 and less than or equal to 1.
8. according to the method for claim 5, it is characterised in that the trend tendency acquiring unit is specifically used for：
When the finance product grade of the target finance product is more than or equal to predetermined level, according to the target finance product
Current criteria state and default finance product trend model obtain the trend tendency of the target finance product；
The tactful acquiring unit is used for：
When the finance product grade of the target finance product is more than or equal to predetermined level, and the target finance product becomes
When gesture tendency is goes up, the Asset Allocation strategy for buying in the target finance product is obtained.
9. a kind of computer equipment, including memory and processor, computer-readable instruction is stored with the memory, it is described
When computer-readable instruction is by the computing device so that the computing device is weighed according to any one of Claims 1-4
Profit requires the step of Asset Allocation strategy acquisition methods.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device performs so that one or more processors perform the Asset Allocation according to any one of Claims 1-4 claim
The step of tactful acquisition methods.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710614428.9A CN107679987A (en) | 2017-07-25 | 2017-07-25 | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium |
| SG11201913398QA SG11201913398QA (en) | 2017-07-25 | 2017-09-28 | Asset allocation strategy acquisition method and apparatus, computer device, and storage medium |
| PCT/CN2017/103954 WO2019019346A1 (en) | 2017-07-25 | 2017-09-28 | Asset allocation strategy acquisition method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710614428.9A CN107679987A (en) | 2017-07-25 | 2017-07-25 | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107679987A true CN107679987A (en) | 2018-02-09 |
Family
ID=61133548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710614428.9A Pending CN107679987A (en) | 2017-07-25 | 2017-07-25 | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN107679987A (en) |
| SG (1) | SG11201913398QA (en) |
| WO (1) | WO2019019346A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035028A (en) * | 2018-06-29 | 2018-12-18 | 平安科技（深圳）有限公司 | Intelligence, which is thrown, cares for strategy-generating method and device, electronic equipment, storage medium |
| CN109783876A (en) * | 2018-12-19 | 2019-05-21 | 平安科技（深圳）有限公司 | Time series models method for building up, device, computer equipment and storage medium |
| CN111860855A (en) * | 2019-12-18 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Behavior-guided resource delivery strategy generation method and device |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570207B (en) * | 2021-07-09 | 2024-04-26 | 北京淇瑀信息科技有限公司 | User policy allocation method and device and electronic equipment |
| CN115827821B (en) * | 2022-11-11 | 2024-01-09 | 深圳市今古科技有限公司 | Judgment strategy generation method and system based on information |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8560420B2 (en) * | 2009-12-07 | 2013-10-15 | Predictive Technologies Group, Llc | Calculating predictive technical indicators |
| CN106022522A (en) * | 2016-05-20 | 2016-10-12 | 南京大学 | Method and system for predicting stocks based on big data published by internet |
| CN106203731A (en) * | 2016-07-25 | 2016-12-07 | 上海电机学院 | A kind of stock trend forecasting method based on 2 dimension stream predictions |
| CN106600404A (en) * | 2016-11-08 | 2017-04-26 | 南京财经大学 | Prediction method and device |
-
2017
- 2017-07-25 CN CN201710614428.9A patent/CN107679987A/en active Pending
- 2017-09-28 SG SG11201913398QA patent/SG11201913398QA/en unknown
- 2017-09-28 WO PCT/CN2017/103954 patent/WO2019019346A1/en active Application Filing
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109035028A (en) * | 2018-06-29 | 2018-12-18 | 平安科技（深圳）有限公司 | Intelligence, which is thrown, cares for strategy-generating method and device, electronic equipment, storage medium |
| WO2020000689A1 (en) * | 2018-06-29 | 2020-01-02 | 平安科技（深圳）有限公司 | Transfer-learning-based robo-advisor strategy generation method and apparatus, and electronic device and storage medium |
| CN109035028B (en) * | 2018-06-29 | 2023-08-22 | 平安科技（深圳）有限公司 | Intelligent consultation strategy generation method and device, electronic equipment and storage medium |
| CN109783876A (en) * | 2018-12-19 | 2019-05-21 | 平安科技（深圳）有限公司 | Time series models method for building up, device, computer equipment and storage medium |
| CN109783876B (en) * | 2018-12-19 | 2024-02-06 | 平安科技（深圳）有限公司 | Time sequence model establishment method, device, computer equipment and storage medium |
| CN111860855A (en) * | 2019-12-18 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Behavior-guided resource delivery strategy generation method and device |
| CN111860855B (en) * | 2019-12-18 | 2023-12-05 | 北京嘀嘀无限科技发展有限公司 | Behavior-guided resource release strategy generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019019346A1 (en) | 2019-01-31 |
| SG11201913398QA (en) | 2020-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Vargas et al. | Deep leaming for stock market prediction using technical indicators and financial news articles | |
| Livieris et al. | A CNN–LSTM model for gold price time-series forecasting | |
| Thawornwong et al. | The adaptive selection of financial and economic variables for use with artificial neural networks | |
| CN107679987A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
| Shah et al. | A comprehensive review on multiple hybrid deep learning approaches for stock prediction | |
| US20220027993A1 (en) | System and method for facilitating social trading | |
| Eiamkanitchat et al. | Fundamental analysis and technical analysis integrated system for stock filtration | |
| Xing et al. | Discovering Bayesian market views for intelligent asset allocation | |
| Snihovyi et al. | Implementation of robo-advisor services for different risk attitude investment decisions using machine learning techniques | |
| CN111340244A (en) | Prediction method, training method, device, server and medium | |
| CN107368925A (en) | Stock trend forecasting method and system | |
| CN108596765A (en) | A kind of Electronic Finance resource recommendation method and device | |
| Ahmed et al. | The role of artificial intelligence in developing a banking risk index: an application of Adaptive Neural Network-Based Fuzzy Inference System (ANFIS) | |
| Maknickienė et al. | Comparison of forex market forecasting tools based on Evolino ensemble and technical analysis indicators | |
| El-Berawi et al. | Adaptive deep learning based cryptocurrency price fluctuation classification | |
| CN111667307A (en) | Method and device for predicting financial product sales volume | |
| Othman | Analysing financial distress in Malaysian Islamic banks: Exploring integrative predictive methods | |
| Pothumsetty | Application of artificial intelligence in algorithmic trading | |
| CN115439180A (en) | Target object determination method and device, electronic equipment and storage medium | |
| Hasanah et al. | Financial Robo-advisor: learning from academic literature | |
| Dunis et al. | Nonlinear forecasting of the gold miner spread: An application of correlation filters | |
| CN114529399A (en) | User data processing method, device, computer equipment and storage medium | |
| Kasabov et al. | Hybrid intelligent decision support systems and applications for risk analysis and discovery of evolving economic clusters in Europe | |
| Sahiner et al. | Do artificial neural networks provide improved volatility forecasts: Evidence from Asian markets | |
| Chaysiri et al. | Prediction of closing stock prices using the Artificial Neural Network in the Market for Alternative Investment (MAI) of the Stock Exchange of Thailand (SET) |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180529 Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 200000 Xuhui District, Shanghai Kai Bin Road 166, 9, 10 level. Applicant before: Shanghai Financial Technologies Ltd |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 518000 Room 201, building A, 1 front Bay Road, Shenzhen Qianhai cooperation zone, Shenzhen, Guangdong Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant before: Shenzhen one ledger Intelligent Technology Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180209 |