CN107515928A - A kind of method, apparatus, server, storage medium for judging assets price tendency - Google Patents
A kind of method, apparatus, server, storage medium for judging assets price tendency Download PDFInfo
- Publication number
- CN107515928A CN107515928A CN201710742294.9A CN201710742294A CN107515928A CN 107515928 A CN107515928 A CN 107515928A CN 201710742294 A CN201710742294 A CN 201710742294A CN 107515928 A CN107515928 A CN 107515928A
- Authority
- CN
- China
- Prior art keywords
- search
- mood
- search entry
- entry
- desired asset
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of method, apparatus, server, storage medium for judging assets price tendency, methods described includes：At least one search entry related to desired asset is obtained from the daily record data of search engine；Extract the mood keyword in each search entry；Using the mood scoring model and the mood keyword pre-established, each search entry is given a mark, obtains the mood total score of at least one search entry；The mood total score is analyzed using model when selecting pre-established, to judge the price trend of the desired asset.The embodiment of the present invention is realized the search engine data application of magnanimity in the financial investment analysis of assets, analysis summary based on the generation of search big data to market investment person's mood, the angle of subordinate act finance are accurately judged assets price tendency using big data market sentiment.
Description
Technical field
The present embodiments relate to data analysis technique, more particularly to a kind of method, apparatus for judging assets price tendency,
Server, storage medium.
Background technology
In the investment deals such as stock market, futures and staple commodities stock, the price trend of product is the transaction to product
One of most guiding information, if it is possible to accurately judge the price trend of assets, can just be advised in financial investment
Wind sheltering danger.
Traditional financial investment analysis mode is all the basic side from economical operation, or the technological side information of marketing
Analysis judgement is carried out to assets price tendency, by taking stock views on broad market movements as an example, existing deep bid data analysing method mainly relies on
Stock price index, by analyzing the historical data and trend curve of stock price index, estimation stock price index future
Change.But financial investment price trend is affected by many factors, the skill of basic side or marketing only according to economical operation
Art face information can not accurate estimated assets price trend.
The content of the invention
The embodiment of the present invention provides a kind of method, apparatus, server, storage medium for judging assets price tendency, with reality
Now accurately judge the price trend of assets.
In a first aspect, the embodiments of the invention provide a kind of method for judging assets price tendency, including：
At least one search entry related to desired asset is obtained from the daily record data of search engine；
Extract the mood keyword in each search entry；
Using the mood scoring model and the mood keyword pre-established, each search entry is given a mark, obtained
The mood total score of at least one search entry；
The mood total score is analyzed using model when selecting pre-established, to judge the valency of the desired asset
Lattice tendency.
Second aspect, the embodiment of the present invention additionally provide a kind of device for judging assets price tendency, including：
Search entry acquisition module, for obtaining at least one related to desired asset from the daily record data of search engine
Individual search entry；
Mood keyword extracting module, for extracting the mood keyword in each search entry；
Mood total score scoring modules, it is right for utilizing the mood scoring model pre-established and the mood keyword
Each search entry is given a mark, and obtains the mood total score of at least one search entry；
Price trend judge module, for being analyzed using model when selecting pre-established the mood total score,
To judge the price trend of the desired asset.
The third aspect, the embodiment of the present invention additionally provide a kind of server, and the server includes：
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are by one or more of computing devices so that one or more of processing
Device realizes the method as described above for judging assets price tendency.
Fourth aspect, the embodiment of the present invention additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Program, the method as described above for judging assets price tendency is realized when the program is executed by processor.
The embodiment of the present invention from the daily record data of search engine by obtaining related to desired asset at least one search
Rope entry, the mood keyword in each search entry is extracted, closed using the mood scoring model pre-established and the mood
Keyword, each search entry is given a mark, obtain the mood total score of at least one search entry, using pre-establishing when selecting
Model is analyzed the mood total score, to judge the price trend of the desired asset, is realized the search of magnanimity
Engine data is applied in the financial investment analysis of assets, and the analysis based on search big data generation to market investment person's mood converges
Always, the angle of subordinate act finance is accurately judged assets price tendency using big data market sentiment.
Brief description of the drawings
Fig. 1 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention one；
Fig. 2 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention two；
Fig. 3 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention three；
Fig. 4 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention four；
Fig. 5 is the structural representation of the device of the judgement assets price tendency in the embodiment of the present invention five；
Fig. 6 is the structural representation of the server in the embodiment of the present invention six.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention one, and the present embodiment is applicable
In situation about being judged assets price tendency, this method can be performed by the device of judgement assets price tendency, the judgement
The device of assets price tendency can be realized by the way of software and/or hardware, for example, the dress of the judgement assets price tendency
Put and be configured in server.As shown in figure 1, this method specifically includes：
S110, at least one search entry related to the desired asset is obtained from the daily record data of search engine.
Search engine refers to collect information from internet according to certain strategy, with specific computer program,
After tissue and processing are carried out to information, retrieval service is provided the user, is by what the related information of user search showed user
System.It extracts the information of each website from internet, it is established that database, and the note to match with user's querying condition can be retrieved
Record, by certain returning result that puts in order.
Search engine can every time retrieve user all retrieval strings used by journal file and all record, and search is drawn
Hold up position in returning result of the access time, ID, query word, URL of log recording user, the order that user clicks on
Number and the URL etc. that clicks on of user.The daily record data of search engine has polymerize the search behavior of magnanimity netizen and investor, is
The data acquisition system that mass users concern is intended to, can be more by search engine data from the point of view of the scale and magnitude of conceptual data
Add the mood for accurately analyzing market investment person.
In the present embodiment, by obtaining the related to desired asset of user's input from the daily record data of search engine
Multiple search entries.Internet user can submit the search need of magnanimity to search engine daily, be related to the every aspect of society,
The fields such as tourism, finance, game are numerous, to filter out the search entry related to desired asset from the search behavior of full dose.
Wherein desired asset can be the larger assets of Market clearing quantity, such as can be equity asset, gold assets or crude oil assets.
S120, extract mood keyword in each search entry.
Each class keywords are contained in the search entry of user's input, in the present embodiment, are extracted from each search entry
Go out the mood keyword wherein included, for example, when search entry for " price of gold go up in the recent period reason " when, " rise " can reflect
The mood of user, as the mood keyword included in the entry and extract.Except can directly represent user's feelings
Outside the keyword of thread, the keyword that can represent user emotion indirectly can also be come out as mood keyword extraction, example
It is therein although not including wherein has the keyword for directly representing user emotion such as when search entry is " the crude oil underproduction "
" underproduction " normally results in the reduction of crude supply amount, so as to bring crude oil price to rise, then between " underproduction " can be used as
Connect and represent the mood keyword extraction of user emotion and come out.
S130, using the mood scoring model and the mood keyword pre-established, each search entry is given a mark,
Obtain the mood total score of at least one search entry.
Preferably, mood scoring model can be established according to the emotion dictionary pre-established and default marking rule, to difference
The search entry of search intention is classified and measured to the positive negative sense of mood of mood keyword according to the financial investment logic of assets
Change, based on the mood scoring model, quantization marking can be carried out to the investing sentiment of different search entries, then by overall poly-
The market in general investor sentiment score value for counting daily desired asset is closed, draws mood total score.Wherein financial investment logic is
Refer to the positive negative sense division of word in addition to this kind of directly mood word that is expected to rise, appreciate, drops, also indivedual indirect logic relations
Word, by taking " the crude oil underproduction " mentioned above as an example, " underproduction " can be given a mark as the word that price may be made to increase.
S140, using model when selecting pre-established the mood total score is analyzed, to judge that the target provides
The price trend of production.
In the present embodiment, model can pass through the historical price tendency to desired asset and history mood total score when selecting
Analysis, i.e. the historical price tendency to desired asset and history mood total score carry out data analysis, and it is total to search out history mood
The incidence relation of score value and price trend, the mood total score based on the incidence relation and desired asset judge desired asset
Price trend.There is a variety of the mode of model, such as can be by way of machine learning, by historical price tendency when wherein foundation is selected
With history mood total score as training data, model is trained during to selecting, from training data learning historical price tendency
With the incidence relation between history mood total score, model when selecting trained is finally drawn.
The technical scheme of the present embodiment, by from the daily record data of search engine obtain it is related to desired asset at least
One search entry, the mood keyword in each search entry is extracted, utilize the mood scoring model and mood pre-established
Keyword, each search entry is given a mark, obtain the mood total score of at least one search entry, selected using what is pre-established
When model mood total score is analyzed, to judge the price trend of desired asset, realize the search engine number of magnanimity
According to applying in the financial investment analysis of assets, the analysis summary to market investment person's mood is generated based on search big data, from
The angle of behavior finance is accurately judged assets price tendency using big data market sentiment.
Embodiment two
Fig. 2 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention two, and the present embodiment is being implemented
Further optimized on the basis of example one.As shown in Fig. 2 methods described includes：
S210, whole search entries are obtained from the daily record data of search engine.
In the present embodiment, whole search entries in the daily record data of search engine are obtained first, wherein containing use
The search entry for being related to every field various aspects of family input.
The desired asset dictionary that S220, basis pre-establish, extraction and desired asset phase from whole search entries
The intermediate search entry of pass.
Preferably, desired asset dictionary can be pre-established, all users are contained in the dictionary and are searched for for desired asset
The word of Shi Keneng inputs.According to desired asset dictionary, whole search entries can be screened, and extract whole search entries
In the intermediate search entry related to desired asset.In this way, related to desired asset search can be gone out with preliminary screening
Rope entry, and search entry and specific desired asset are established into corresponding relation.
S230, user access activity data corresponding with the intermediate search entry are obtained from the daily record data, and
According to the access behavioral data, the search intention of user is filtered out from the intermediate search entry with the desired asset not
The noise data of symbol, obtain at least one search entry related to desired asset.
User access activity data corresponding with intermediate search entry, wherein user access activity are obtained from daily record data
The search result that data can include the incoming road domain name of user and the page, user access the title of search result, user access
URL, user is in residence time of website etc..Can be according to the user access activity data of acquisition, the mistake from middle search entry
Filter the search intention of user and noise data that desired asset is not inconsistent, finally give the search entry related to desired asset,
Search entry after filtering is mainly derived from the correlative investment person of concern desired asset, can accurately reflect correlative investment person's
Behavior and intention.
Preferably, the title for the search result that the noise data accesses including user is unrelated with the desired asset searches
Rope entry, or the URL of search result that accesses of user and the unmatched search entry in desired asset URL storehouses that pre-establishes.
The web page title that directly can be accessed according to user judges whether user search intent is related with desired asset, works as user to URL
The web page title of access and during URL unrelated with desired asset, filters out as noise data, ensure that the accurate of data
Property.
S240, extract mood keyword in each search entry.
S250, using the mood scoring model and the mood keyword pre-established, each search entry is given a mark,
Obtain the mood total score of at least one search entry.
S260, using model when selecting pre-established the mood total score is analyzed, to judge that the target provides
The price trend of production.
The technical scheme of the present embodiment, embody and obtained and the desired asset phase from the daily record data of search engine
At least one search entry closed, utilizes this method so that the search entry related to desired asset got is more accurate, real
Show the search engine data application of magnanimity in the financial investment analysis of assets, accurately generated pair based on search big data
The analysis summary of market investment person's mood, the angle of subordinate act finance are entered using big data market sentiment to assets price tendency
Row accurately judges.
Embodiment three
Fig. 3 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention three, and the present embodiment is with above-mentioned
Further optimized based on embodiment.As shown in figure 3, methods described includes：
S310, at least one search entry related to the desired asset is obtained from the daily record data of search engine.
S320, word segmentation processing is carried out to each search entry, obtain at least one participle phrase in each search entry.
In the present embodiment, search entry cutting can be generated according to the word segmentation regulation of existing segmenter using segmenter
Each participle phrase, and then obtain each participle phrase corresponding to user's input search entry.For example, current search entry is " yellow
Price of gold lattice go up reason in the recent period " when, can be following several participle phrases by the search entry cutting：It is " gold ", " price ", " near
Phase ", " rise ", " reason ".
The emotion dictionary that S330, basis pre-establish, matches, extracts respectively at least one participle phrase
Mood keyword in each search entry.
The keyword of user emotion can be embodied by including in emotion dictionary, after search entry is segmented, can be passed through
The matching relationship of participle phrase and the emotion dictionary pre-established after participle, filters out the mood keyword in search entry,
To be given a mark in subsequent step using the mood keyword filtered out to the search entry belonging to it.
S340, using the mood scoring model and the mood keyword pre-established, each search entry is given a mark,
Obtain the mood total score of at least one search entry.
S350, using model when selecting pre-established the mood total score is analyzed, to judge that the target provides
The price trend of production.
The technical scheme of the present embodiment, the mood keyword extracted in each search entry is embodied, using this method,
So that the screening to mood keyword in the search entry of search engine is more accurate, realize the search engine data of magnanimity
Apply in the financial investment analysis of assets, the analysis accurately generated based on search big data to market investment person's mood is converged
Always, the angle of subordinate act finance is accurately judged assets price tendency using big data market sentiment.
Example IV
Fig. 4 is the flow chart of the method for the judgement assets price tendency in the embodiment of the present invention four, and the present embodiment is with above-mentioned
Further optimized based on embodiment.As shown in figure 4, methods described includes：
S410, at least one search entry related to the desired asset is obtained from the daily record data of search engine.
S420, extract mood keyword in each search entry.
S430, using the mood scoring model and the mood keyword pre-established, each search entry is given a mark,
Obtain the mood total score of at least one search entry.
S440, using model when selecting pre-established, derivative index is calculated according to the mood total score.
Model is returned by the analysis to desired asset historical price tendency and history mood total score and surveyed when selecting, and finds history
The incidence relation of mood total score and historical price tendency, and then design a series of derivatives for history mood total score and refer to
Mark, and the operation rule based on derivative index prejudges to the operation trend of assets price.
Optionally, the derivative index of model includes when selecting：Equal line class index and slope class index.
Equal line class index is the important indicator of price reflection operation trend, is referred to history mood total score in different time
Interior average judges the price trend of desired asset as index.For example, define the average of the market mood total score of nearly 5 days
For mv5, the average of the market mood total score of nearly 10 days is mv10, and the average of the market mood total score of nearly 20 days is mv20,
Then according to market sentiment total score in nearly 5 days, nearly 10 days, the equal line of nearly 20 days relative position relation, to the valency of desired asset
Lattice tendency, which is made, is expected to rise or judgement expected to fall.
Slope class index refers to the numerical value progress linear regression calculating to the mood total score of the nearly n days on default value,
Using the slope of linear regression as index, the price trend of desired asset is judged.Wherein default value can be market nearly 20 days
Mood total score average mv20.In the present embodiment, can be by setting slope threshold values, when slope is more than or less than slope threshold
During value, make being expected to rise and judgement expected to fall respectively.If the numerical value of nearly n day mood total score of the desired asset more than default value
And the relation of number of days is：
The formula for then calculating the slope of linear regression is as follows：
Wherein x is number of days (the 1st day, the 2nd day ..., i-th day ..., n-th day), and y is the desired asset mood total score of i-th day
The numerical value of value,For average time,For the average of nearly n days mood total score,The slope of linear regression is represented,Represent line
The intercept of property regression equation.
S450, according to preset rules the derivative index is analyzed, to judge the price trend of the desired asset.
In the present embodiment, can be by analyzing the derivative index of desired asset, and according to corresponding preset rules
Judge the price trend of desired asset.
For example, when using equal line class index as derivative index, can be sentenced according to the relative position of the equal line of mood total score
The price trend of disconnected desired asset；When using slope class index as derivative index, slope threshold value can be set, and according to current mesh
The slope of assets and the magnitude relationship of slope threshold value are marked, judges the price trend of desired asset.
Model during based on above-mentioned selecting, time survey inspection is carried out using the asset history price data of nearly 3 years and parameter is excellent
Change, and obtain as surveyed result next time：
Stock market：
| Analysis strategy | Income | Maximum withdraws rate |
| Model when selecting | 54.73% | - 12.19% |
| 1 when technological side is selected | 24.86% | - 18.64% |
| 2 when technological side is selected | 37.78% | - 24.30% |
Gold bullion market：
| Analysis strategy | Income | Maximum withdraws rate |
| Model when selecting | 33.52% | - 6.79% |
| 1 when technological side is selected | 26.62% | - 6.79% |
Crude Oil Market：
| Analysis strategy | Income | Maximum withdraws rate |
| Model when selecting | 35.26% | - 13.96% |
| 1 when technological side is selected | 7.4% | - 32.50% |
Wherein maximum withdraws rate and refers within the selected cycle any history time point toward pusher, when product net value goes to minimum point
Earning rate withdraw the maximum of amplitude.Model when selecting of the present embodiment offer is can be seen that in history number by returning survey conclusion
According to return survey in compared with some traditional technical Analysis modes, earning rate is higher, and it is lower that maximum withdraws rate, can be more accurately
The operation trend of following assets price is prejudged, obtains more preferable performance.
The technical scheme of the present embodiment, the mood total score will be analyzed using model when selecting pre-established,
To judge that the price trend of the desired asset is embodied, using the method achieve the search engine data of magnanimity
Apply in the financial investment analysis of assets, the analysis summary based on the generation of search big data to market investment person's mood, utilize
The angle of model subordinate act finance is accurately judged assets price tendency using big data market sentiment when selecting.
Embodiment five
Fig. 5 is the structural representation of the device of the judgement assets price tendency in the embodiment of the present invention five.As shown in figure 5,
Described device includes：
Search entry acquisition module 510, in the daily record data from search engine obtain it is related to desired asset to
A few search entry；
Mood keyword extracting module 520, for extracting the mood keyword in each search entry；
Mood total score scoring modules 530, for utilizing the mood scoring model pre-established and the mood keyword,
Each search entry is given a mark, obtains the mood total score of at least one search entry；
Price trend judge module 540, for being divided using model when selecting pre-established the mood total score
Analysis, to judge the price trend of the desired asset.
Further, the search entry acquisition module 510 includes：
Whole search entry acquiring units, for obtaining whole search entries from the daily record data of search engine；
Intermediate search entry acquiring unit, the desired asset dictionary pre-established for basis, from whole search terms
The intermediate search entry related to desired asset is extracted in bar；
Final search entry acquiring unit, it is corresponding with the intermediate search entry for being obtained from the daily record data
User access activity data, and according to the access behavioral data, the search of user is filtered out from the intermediate search entry
It is intended to the noise data not being inconsistent with the desired asset, obtains at least one search entry related to desired asset.
Further, the final search entry acquiring unit is specifically used for：
User access activity data corresponding with the intermediate search entry are obtained from the daily record data, and according to institute
Access behavioral data is stated, the title that the search result of user's access is filtered out from the intermediate search entry provides with the target
Produce unrelated search entry, or the URL of search result that accesses of user and the desired asset URL storehouses that pre-establish it is unmatched
Search entry, obtain at least one search entry related to desired asset.
Further, the mood keyword extracting module 520 includes：
Participle phrase acquiring unit, for carrying out word segmentation processing to each search entry, obtain in each search entry at least
One participle phrase；
Mood keyword acquiring unit, the emotion dictionary pre-established for basis, at least one participle phrase
Matched respectively, extract the mood keyword in each search entry.
Further, the mood scoring model is established according to the emotion dictionary pre-established and default marking rule.
Further, the price trend judge module 540 includes：
Derivative indicator calculating unit, for using model when selecting pre-established, being calculated and being spread out according to the mood total score
Raw index；
Price trend judging unit, for being analyzed the derivative index to judge the target according to preset rules
The price trend of assets；
Wherein, the derivative index includes：Equal line class index and slope class index.
The technical scheme of the present embodiment, is obtained from the daily record data of search engine and mesh by search entry acquisition module
The related at least one search entry of assets is marked, the mood that mood keyword extracting module is extracted in each search entry is crucial
Word, mood total score scoring modules are carried out using the mood scoring model and mood keyword pre-established to each search entry
Marking, obtains the mood total score of at least one search entry, and price trend judge module utilizes model when selecting pre-established
Mood total score is analyzed, to judge the price trend of desired asset, realized the search engine data application of magnanimity
In the financial investment analysis of assets, the analysis summary based on the generation of search big data to market investment person's mood, subordinate act gold
The angle for melting accurately is judged assets price tendency using big data market sentiment.
The device for the judgement assets price tendency that the embodiment of the present invention is provided can perform any embodiment of the present invention and be carried
The method of the judgement assets price tendency of confession, possesses the corresponding functional module of execution method and beneficial effect.
Embodiment six
Fig. 6 is a kind of structural representation for server that the embodiment of the present invention six provides.Fig. 6 is shown suitable for being used for realizing
The block diagram of the exemplary servers 612 of embodiment of the present invention.The server 612 that Fig. 6 is shown is only an example, should not be right
The function and use range of the embodiment of the present invention bring any restrictions.
As shown in fig. 6, server 612 is showed in the form of universal computing device.The component of server 612 can include but
It is not limited to：One or more processor 616, system storage 628, connection different system component (including system storage 628
With processor 616) bus 618.
Bus 618 represents the one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor 616 or total using the local of any bus structures in a variety of bus structures
Line.For example, these architectures include but is not limited to industry standard architecture (ISA) bus, MCA
(MAC) bus, enhanced isa bus, VESA's (VESA) local bus and periphery component interconnection (PCI) are total
Line.
Server 612 typically comprises various computing systems computer-readable recording medium.These media can be it is any being capable of bedding and clothing
The usable medium that business device 612 accesses, including volatibility and non-volatile media, moveable and immovable medium.
System storage 628 can include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 630 and/or cache memory 632.Server 612 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 634 can be used for read-write not
Movably, non-volatile magnetic media (Fig. 6 is not shown, is commonly referred to as " hard disk drive ").Although not shown in Fig. 6, can with
There is provided for the disc driver to may move non-volatile magnetic disk (such as " floppy disk ") read-write, and to removable non-volatile
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 618.Memory 628 can include at least one program
Product, the program product have one group of (for example, at least one) program module, and these program modules are configured to perform the present invention
The function of each embodiment.
Program/utility 640 with one group of (at least one) program module 642, can be stored in such as memory
In 628, such program module 642 includes but is not limited to operating system, one or more application program, other program modules
And routine data, the realization of network environment may be included in each or certain combination in these examples.Program module 642
Generally perform the function and/or method in embodiment described in the invention.
Server 612 can also be with one or more external equipments 614 (such as keyboard, sensing equipment, display 624 etc.)
Communication, can also enable a user to the equipment communication interacted with the server 612 with one or more, and/or with causing the clothes
Any equipment (such as network interface card, modem etc.) that business device 612 can be communicated with one or more of the other computing device
Communication.This communication can be carried out by input/output (I/O) interface 622.Also, server 612 can also be fitted by network
Orchestration 620 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as because of spy
Net) communication.As illustrated, network adapter 620 is communicated by bus 618 with other modules of server 612.It should be understood that
Although not shown in the drawings, can combine server 612 uses other hardware and/or software module, include but is not limited to：Micro- generation
Code, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup are deposited
Storage system etc..
Processor 616 is stored in program in system storage 628 by operation, so as to perform various function application and
Data processing, such as the method for realizing the judgement assets price tendency that the embodiment of the present invention is provided, this method include：From search
At least one search entry related to desired asset is obtained in the daily record data of engine；
Extract the mood keyword in each search entry；
Using the mood scoring model and the mood keyword pre-established, each search entry is given a mark, obtained
The mood total score of at least one search entry；
The mood total score is analyzed using model when selecting pre-established, to judge the valency of the desired asset
Lattice tendency.
Embodiment seven
The embodiment of the present invention seven additionally provides a kind of computer-readable recording medium, is stored thereon with computer program, should
The method that the judgement assets price tendency provided such as the embodiment of the present invention is provided when program is executed by processor, this method bag
Include：
At least one search entry related to desired asset is obtained from the daily record data of search engine；
Extract the mood keyword in each search entry；
Using the mood scoring model and the mood keyword pre-established, each search entry is given a mark, obtained
The mood total score of at least one search entry；
The mood total score is analyzed using model when selecting pre-established, to judge the valency of the desired asset
Lattice tendency.
The computer-readable storage medium of the embodiment of the present invention, any of one or more computer-readable media can be used
Combination.Computer-readable medium can be computer-readable signal media or computer-readable recording medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any combination above.The more specifically example (non exhaustive list) of computer-readable recording medium includes：Tool
There are the electrical connections of one or more wires, portable computer diskette, hard disk, random access memory (RAM), read-only storage
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any includes or the tangible medium of storage program, the program can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, the computer-readable medium, which can send, propagates or transmit, to be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc., or above-mentioned any appropriate combination.
It can be write with one or more programming languages or its combination for performing the computer that operates of the present invention
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Also include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
Fully perform, partly perform on the user computer on the user computer, the software kit independent as one performs, portion
Divide and partly perform or performed completely on remote computer or server on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as carried using Internet service
Pass through Internet connection for business).
Pay attention to, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art various obvious changes,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (14)
- A kind of 1. method for judging assets price tendency, it is characterised in that including：At least one search entry related to desired asset is obtained from the daily record data of search engine；Extract the mood keyword in each search entry；Using the mood scoring model and the mood keyword pre-established, each search entry is given a mark, obtained described The mood total score of at least one search entry；The mood total score is analyzed using model when selecting pre-established, to judge that the price of the desired asset is walked Gesture.
- 2. according to the method for claim 1, it is characterised in that in the daily record data from search engine obtain with it is described The related at least one search entry of desired asset includes：Whole search entries are obtained from the daily record data of search engine；According to the desired asset dictionary pre-established, the extraction centre related to desired asset is searched from whole search entries Rope entry；User access activity data corresponding with the intermediate search entry are obtained from the daily record data, and according to the visit Behavioral data is asked, the search intention of user is filtered out from the intermediate search entry and noise number that the desired asset is not inconsistent According to obtaining at least one search entry related to desired asset.
- 3. according to the method for claim 2, it is characterised in that the noise data includes the search result that user accesses The title search entry unrelated with the desired asset, or the URL of search result that accesses of user and the target that pre-establishes The unmatched search entry in assets URL storehouses.
- 4. according to the method for claim 1, it is characterised in that the mood keyword bag extracted in each search entry Include：Word segmentation processing is carried out to each search entry, obtains at least one participle phrase in each search entry；According to the emotion dictionary pre-established, at least one participle phrase is matched respectively, extracts each search term Mood keyword in bar.
- 5. according to the method for claim 1, it is characterised in that the mood scoring model is according to the emotion pre-established Dictionary and default marking rule are established.
- 6. according to the method for claim 1, it is characterised in that described to utilize model when selecting pre-established to the mood Total score is analyzed, to judge that the price trend of the desired asset includes：Using model when selecting pre-established, derivative index is calculated according to the mood total score；The derivative index is analyzed according to preset rules, to judge the price trend of the desired asset；Wherein, the derivative index includes：Equal line class index and slope class index.
- A kind of 7. device for judging assets price tendency, it is characterised in that including：Search entry acquisition module, for obtaining related to desired asset at least one search from the daily record data of search engine Rope entry；Mood keyword extracting module, for extracting the mood keyword in each search entry；Mood total score scoring modules, for utilizing the mood scoring model pre-established and the mood keyword, to respectively searching Rope entry is given a mark, and obtains the mood total score of at least one search entry；Price trend judge module, for being analyzed using model when selecting pre-established the mood total score, to sentence The price trend for the desired asset of breaking.
- 8. device according to claim 7, it is characterised in that the search entry acquisition module includes：Whole search entry acquiring units, for obtaining whole search entries from the daily record data of search engine；Intermediate search entry acquiring unit, the desired asset dictionary pre-established for basis, from whole search entries The extraction intermediate search entry related to desired asset；Final search entry acquiring unit, for obtaining user corresponding with the intermediate search entry from the daily record data Behavioral data is accessed, and according to the access behavioral data, the search intention of user is filtered out from the intermediate search entry The noise data not being inconsistent with the desired asset, obtain at least one search entry related to desired asset.
- 9. device according to claim 8, it is characterised in that the final search entry acquiring unit is specifically used for：User access activity data corresponding with the intermediate search entry are obtained from the daily record data, and according to the visit Ask behavioral data, filtered out from the intermediate search entry user's access search result title and the desired asset without The search entry of pass, or the URL of search result that accesses of user and the unmatched search in desired asset URL storehouses that pre-establishes Entry, obtain at least one search entry related to desired asset.
- 10. device according to claim 7, it is characterised in that the mood keyword extracting module includes：Participle phrase acquiring unit, for carrying out word segmentation processing to each search entry, obtain at least one in each search entry Participle phrase；Mood keyword acquiring unit, for according to the emotion dictionary pre-established, distinguishing at least one participle phrase Matched, extract the mood keyword in each search entry.
- 11. device according to claim 7, it is characterised in that the mood scoring model is according to the feelings pre-established Feel dictionary and default marking rule is established.
- 12. device according to claim 7, it is characterised in that the price trend judge module includes：Derivative indicator calculating unit, for using model when selecting pre-established, calculating derivative according to the mood total score and referring to Mark；Price trend judging unit, for being analyzed the derivative index to judge the desired asset according to preset rules Price trend；Wherein, the derivative index includes：Equal line class index and slope class index.
- 13. a kind of server, it is characterised in that the server includes：One or more processors；Storage device, for storing one or more programs；When one or more of programs are by one or more of computing devices so that one or more of processors are real The now method of the judgement assets price tendency as described in any in claim 1-6.
- 14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor The method that the judgement assets price tendency as described in any in claim 1-6 is realized during execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710742294.9A CN107515928A (en) | 2017-08-25 | 2017-08-25 | A kind of method, apparatus, server, storage medium for judging assets price tendency |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710742294.9A CN107515928A (en) | 2017-08-25 | 2017-08-25 | A kind of method, apparatus, server, storage medium for judging assets price tendency |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107515928A true CN107515928A (en) | 2017-12-26 |
Family
ID=60724183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710742294.9A Pending CN107515928A (en) | 2017-08-25 | 2017-08-25 | A kind of method, apparatus, server, storage medium for judging assets price tendency |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107515928A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112860995A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Interaction method, device, client, server and storage medium |
| CN113919447A (en) * | 2021-12-10 | 2022-01-11 | 浙江中科华知科技股份有限公司 | Digital asset transaction management method and system based on DNA molecular encryption and LightGBM algorithm |
| CN116611696A (en) * | 2023-07-19 | 2023-08-18 | 北京大学 | Digital asset market risk prediction system based on time sequence analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140004489A1 (en) * | 2012-06-29 | 2014-01-02 | Jong-Phil Kim | Method and apparatus for providing emotion expression service using emotion expression identifier |
| CN104834976A (en) * | 2015-05-14 | 2015-08-12 | 浪潮集团有限公司 | Method for searching for, analyzing and predicting price change trend of memory chip through big data |
| CN105022725A (en) * | 2015-07-10 | 2015-11-04 | 河海大学 | Text emotional tendency analysis method applied to field of financial Web |
| CN106227756A (en) * | 2016-07-14 | 2016-12-14 | 苏州大学 | A kind of stock index forecasting method based on emotional semantic classification and system |
-
2017
- 2017-08-25 CN CN201710742294.9A patent/CN107515928A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140004489A1 (en) * | 2012-06-29 | 2014-01-02 | Jong-Phil Kim | Method and apparatus for providing emotion expression service using emotion expression identifier |
| CN104834976A (en) * | 2015-05-14 | 2015-08-12 | 浪潮集团有限公司 | Method for searching for, analyzing and predicting price change trend of memory chip through big data |
| CN105022725A (en) * | 2015-07-10 | 2015-11-04 | 河海大学 | Text emotional tendency analysis method applied to field of financial Web |
| CN106227756A (en) * | 2016-07-14 | 2016-12-14 | 苏州大学 | A kind of stock index forecasting method based on emotional semantic classification and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112860995A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Interaction method, device, client, server and storage medium |
| CN113919447A (en) * | 2021-12-10 | 2022-01-11 | 浙江中科华知科技股份有限公司 | Digital asset transaction management method and system based on DNA molecular encryption and LightGBM algorithm |
| CN116611696A (en) * | 2023-07-19 | 2023-08-18 | 北京大学 | Digital asset market risk prediction system based on time sequence analysis |
| CN116611696B (en) * | 2023-07-19 | 2024-01-26 | 北京大学 | Digital asset market risk prediction system based on time sequence analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Mining semantic soft factors for credit risk evaluation in peer-to-peer lending | |
| Kettenring | The practice of cluster analysis | |
| CN104915879B (en) | The method and device that social relationships based on finance data are excavated | |
| CN107146089B (en) | Method and device for identifying bill swiping and electronic equipment | |
| JP5421737B2 (en) | Computer implementation method | |
| Chen | Classifying credit ratings for Asian banks using integrating feature selection and the CPDA-based rough sets approach | |
| CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
| CN106227756A (en) | A kind of stock index forecasting method based on emotional semantic classification and system | |
| Li et al. | Stock price prediction incorporating market style clustering | |
| CN111046297A (en) | Service intelligent matching recommendation method, device, equipment and storage medium based on machine learning algorithm | |
| US20230111911A1 (en) | Generation and use of content briefs for network content authoring | |
| CN103729365A (en) | Searching method and system | |
| CN107515928A (en) | A kind of method, apparatus, server, storage medium for judging assets price tendency | |
| CN111738856A (en) | Stock public opinion investment decision analysis method and device | |
| Hu et al. | A POI-sensitive knowledge graph based service recommendation method | |
| CN107527289B (en) | Investment portfolio industry configuration method, device, server and storage medium | |
| CN112464051A (en) | Abnormal data detection method and device and computer readable storage medium | |
| Hirano et al. | Comparing actual and simulated HFT traders' behavior for agent design | |
| CN110389963A (en) | The recognition methods of channel effect, device, equipment and storage medium based on big data | |
| CN110222180A (en) | A kind of classification of text data and information mining method | |
| Yu et al. | Neural network based transaction classification system for chinese transaction behavior analysis | |
| CN108197729A (en) | Value investment analysis method, equipment and storage medium based on machine learning | |
| Zhong et al. | Identification of opinion spammers using reviewer reputation and clustering analysis | |
| CN110209944A (en) | A kind of stock analysis teacher recommended method, device, computer equipment and storage medium | |
| CN111242494B (en) | Patent infringement detection method and system based on game theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |
Effective date of registration: 20191112 Address after: 201815 room 3135, zone a, floor 3, building h, No. 55, Jiading District, Shanghai Applicant after: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd. Address before: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 10 Baidu building, layer three Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20171226 Assignee: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. Assignor: SHANGHAI YOUYANG NEW MEDIA INFORMATION TECHNOLOGY Co.,Ltd. Contract record no.: X2019110000009 Denomination of invention: Asset price trend judgement method and device, server and storage medium License type: Exclusive License Record date: 20191218 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171226 |
|
| RJ01 | Rejection of invention patent application after publication |