CN107885806A - Plate intelligence division methods and device, computing device and storage medium - Google Patents
Plate intelligence division methods and device, computing device and storage medium Download PDFInfo
- Publication number
- CN107885806A CN107885806A CN201711068194.9A CN201711068194A CN107885806A CN 107885806 A CN107885806 A CN 107885806A CN 201711068194 A CN201711068194 A CN 201711068194A CN 107885806 A CN107885806 A CN 107885806A
- Authority
- CN
- China
- Prior art keywords
- plate
- keyword
- similarity
- personal share
- word
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of plate intelligence division methods and device, computing device and storage medium, and division method of slab includes:Stock information is obtained, extracts the keyword in basic side information and technological side data message;Merge the synonym in the keyword or similarity meets the word of threshold value, generate plate characteristic word, the plate characteristic word includes basic panel block feature word and technological side plate characteristic word;Calculate the similarity of personal share keyword and plate characteristic word;Establish the similarity matrix of Feature Words and personal share keyword mapping relations.The present invention can dynamically adjust the personal share of plate and corresponding plate in time according to the development of enterprise, the change of market and government decision trend, realize the real-time intelligent division of personal share and plate, timely and effectively investing tip is provided to investor, the allocative efficiency of assets is greatly enhanced, helps investor to make correct decision-making.
Description
Technical field
The present invention relates to field of computer technology, especially, is related to a kind of Stock block intelligence division methods and device, meter
Calculate equipment and storage medium.
Technical background
A system there is predicable or the stock of concept to carry out by people in order to clear investment train of thought in stock market
Sort out, each set for sorting out series formation is referred to as a plate.The change in newest policy, hot ticket, weather, season etc.
Often producing group to investor influences, and corresponding plate often shows active.For example, country encourages intelligent robot industry
Development, now often performance is active for the stock of intelligent robot plate, and presentation amount valency rises phenomenon together.Again for example, in April, 2017,
The Central Committee of the Communist Party of China, State Council's decision install vertical national new district in hero, and hero peace related notion stock is propagandized with numerous investors are become
Popular subject matter, whole plate exchange hand and the remote super large disk of rising trend in longer period.
Plate is the important bridge of market and personal share, and investor can carry out investing the combing of train of thought by plate, to plate
The assurance of block, be advantageous to investor and analysis of selecting stocks is carried out within the quick period.Therefore, the accuracy pair of personal share Plate division
Important influence is played in the decision-making of investor.
In the prior art, for Stock block often according to manually being divided, its classification is more accurate but less efficient.Separately
Outside, with the development in enterprise and market, the plate attribute of stock has tended to occur very big change, and the plate manually divided
Block may be not belonging to the plate at lower a moment, so as to cause mispairing, influence the decision-making of investor.
If a kind of side for according to the development of enterprise, the change of market dynamically adjust Stock block immediately can be invented
Method, then the allocative efficiency of assets is greatly improved, effectively helps investor to make correct decision-making.
The content of the invention
In view of drawbacks described above, the present invention provides a kind of plate intelligence division methods and device, computing device and storage medium,
For overcoming or solving the above problems.
According to an aspect of the invention, there is provided a kind of plate intelligence division methods, suitable for being performed in computing device,
By extracting the keyword in stock information, merge synonym or near synonym automatically generate plate characteristic word, and it is individual by calculating
The similarity of stock keyword and plate characteristic word divides personal share plate automatically, realizes the real-time intelligent division of personal share plate.This
Invention plate intelligence division methods specifically include following steps:
The basic side information and technological side data message in stock information are obtained, extracts basic side information and technological side data
Keyword in information;
Merge the synonym in the keyword or similarity meets the word of threshold value, generate plate characteristic word, it is described
Plate characteristic word includes basic panel block feature word and technological side plate characteristic word;
Calculate the similarity of personal share keyword and plate characteristic word;
Establish the similarity matrix of Feature Words and personal share keyword mapping relations.
After the similarity matrix step for establishing Feature Words with personal share keyword mapping relations, in addition to sort out step
Suddenly:
Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, according to plate characteristic word pair
Personal share is sorted out;
Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, it is special to plate according to personal share
Sign word is sorted out.
After the classifying step, include the sequence step of sequence:
Preferably, personal share is ranked up according to the similarity size of plate characteristic word keyword corresponding to personal share;
Preferably, plate characteristic word is ranked up according to the similarity size of plate characteristic word keyword corresponding to personal share.
According to another aspect of the present invention, there is provided a kind of plate intelligently divides device, suitable for residing in computing device,
To ensure the realization and application of the above method in practice, including with lower module:
Keyword extracting module, suitable for obtaining basic side information and technological side data message in stock information, extract base
Keyword in this face information and technological side data message;
Plate characteristic word generation module, the word of threshold value is met suitable for the synonym in the merging keyword or similarity,
Plate characteristic word is generated, the plate characteristic word includes basic panel block feature word and technological side plate characteristic word;
Similarity calculation module, suitable for calculating the similarity of personal share keyword and plate characteristic word;
Similarity matrix generation module, it is adapted to set up the similarity matrix of Feature Words and personal share keyword mapping relations.
Intelligently division device also includes classifying module to plate of the present invention:
It is preferably adapted to choose the word for meeting threshold value in personal share keyword with plate characteristic Word similarity, according to plate characteristic
Word is sorted out to personal share;
It is preferably adapted to choose the word for meeting threshold value in personal share keyword with plate characteristic Word similarity, according to personal share to plate
Block feature word is sorted out.
Intelligently division device also includes order module to plate of the present invention:
It is preferably adapted to be ranked up personal share according to the similarity size of plate characteristic word keyword corresponding to personal share;
It is preferably adapted to arrange plate characteristic word according to the similarity size of plate characteristic word keyword corresponding to personal share
Sequence.
According to another aspect of the present invention, there is provided a kind of computing device, including:One or more processors;Memory;
And one or more programs, wherein one or more of program storages are in the memory and are configured as by described one
Individual or multiple computing devices, one or more of programs include being used to perform the either method in plate intelligence division methods
Instruction.
According to another aspect of the present invention, there is provided a kind of computer-readable storage medium, the storage medium are stored with one
Or multiple programs, one or more of programs include instruction, the instruction is when executed by a computing apparatus so that the calculating
Equipment performs the either method in plate intelligence division methods.
Compared with prior art, the invention has the advantages that:
Using the solution of the present invention, by extracting the keyword in stock information, merge synonym or near synonym are given birth to automatically
Into plate characteristic word, and the similarity by calculating personal share keyword and plate characteristic word divides personal share plate come automatic, can root
Dynamically adjust the personal share of plate and corresponding plate in time according to the development of enterprise, the change of market and government decision trend, realize
The real-time intelligent of personal share and plate divides, and provides timely and effectively investing tip to investor, is greatly enhanced the configuration of assets
Efficiency, investor is helped to make correct decision-making.
Brief description of the drawings
Fig. 1 shows the plate intelligence division methods flow chart of the embodiment of the present invention one.
Fig. 2 shows the plate intelligence division methods flow chart of the embodiment of the present invention two.
Fig. 3 shows the plate intelligence division methods flow chart of the embodiment of the present invention three.
Fig. 4 shows the plate of the embodiment of the present invention four intelligently division apparatus function block diagram.
Fig. 5 shows the plate of the embodiment of the present invention five intelligently division apparatus function block diagram.
Fig. 6 shows July 1st kind computing device block diagram of the embodiment of the present invention.
Embodiment
Plate intelligence division methods and system of the present invention, be applicable but be not limited to the stock in securities trading market, futures,
The trade varieties such as foreign exchange, option.Corresponding information can obtain from common platform, can extract corresponding concern time zone as needed
The information in domain.
One of main thought of the present invention is the stock information by extracting certain time region on platform, passes through extraction
Intelligently generation plate characteristic word, the plate characteristic root enter Mobile state according to the change of time zone and adjusted corresponding keyword automatically
It is whole, provide newest plate information to investor.
Another main thought of the present invention is by calculating the similarity between personal share keyword and plate characteristic word, and is set
Respective threshold is determined to be divided to personal share plate, is realized that the dynamic realtime of personal share and plate intelligently divides, is determined for investor
Plan provides important reference.
Present invention sets itself information extraction time section on transaction platform is quantified by user, is referred to by computer automatic execution
Stock block generation and the intelligence division of personal share plate are completed in order.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, so that Stock block divides as an example, in the embodiment of the present invention
Technical scheme is clearly and completely described, it is clear that and described embodiment is only part of the embodiment of the present invention, without
It is whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work
Under the premise of the every other embodiment that is obtained, belong to the scope of protection of the invention.
Embodiment one
With reference to figure 1, the flow chart of the plate intelligence division methods of the embodiment of the present invention one is shown, including:
Step 101, the basic side information and technological side information in stock information are obtained, extracts basic side information and technological side
Keyword in data message.
By taking domestic A share market as an example, in the present embodiment, the information of stock can be from DZH, sensible in A share market
The platforms such as letter, straight flush obtain, and corresponding information includes the basic side information and technological side data message of stock, basic side
Information includes but is not limited to the title of the affiliated company of stock, stock code, main business, industry, product, financial index, newest
Message, shareholder, concept subject matter.Stock technological side data message, the including but not limited to price of stock, closing time, amount of increase and amount of decrease,
Turnover rate, exchange hand, transaction value, amount ratio.The period of above-mentioned basic side information and technological side information crosses can be pressed by user
Fancy setting, can it be the last week, preceding January, the previous year.Information time zone is shorter, and Plate division can be more accurate, to user
Reference significance it is bigger.
So that straight flush F10 pages A share market goes over the basic side information of one week as an example, feature based word extraction algorithm is from base
Multiple keywords are extracted in this face information, specifically, feature word algorithm can be extracted by information gain, card side extracts Feature Words and calculated
Method is extracted, for example extracts electric power, electric energy, wind-force, wind energy, new energy, heat energy, plate, concept etc. keyword, while from mistake
The day line market gone one week are technological side data, and limit-up yesterday plate, continuous receipts sun, continuously go up plate.Meanwhile reject default
Word, in the present embodiment, reject the keyword that plate, concept etc. are not belonging to plate characteristic word, then extract basic side keyword:
Electric power, electric energy, wind-force, wind energy, new energy ...;Technological side keyword:Limit-up yesterday, continuous receipts sun, continuous rise ....This
In embodiment, in addition to reject the market data of suspension personal share.
Step 102, merge the synonym in keyword or similarity meets the word of threshold value, generate plate characteristic word.
Synonym in above-mentioned keyword or near synonym are merged, generate plate characteristic word.Specifically, meter can be passed through
The similarity between keyword is calculated to merge, by setting similarity threshold, the word to meeting threshold value merges into a plate
Block feature word.Specifically, still by taking the multiple keywords extracted in step 101 as an example, synonym electric power, electric energy are merged into electricity
Can, wind-force, wind energy merge into wind energy, while merge the larger word of similarity, and new energy, solar energy, wind energy, heat energy are merged into newly
The energy, continuous rise, continuous sun of receiving merge into continuous rise.Then generate substrate panel block feature word:Electric power, new energy;Technology
Panel block Feature Words:Limit-up yesterday, continuous rise.
Step 103, the similarity of personal share keyword and plate characteristic word is calculated.
The similarity between the keyword and plate characteristic word extracted in personal share is calculated, similarity calculating method can be based on language
The vocabulary Similarity Measure of adopted dictionary, the Lexical Similarity based on corpus statisticses calculate, the vocabulary phase based on retrieval page quantity
Calculated like degree, however it is not limited to this.
Specifically, the step of the present embodiment also includes merging the keyword in above-mentioned personal share, merge in keyword
Synonym, or calculate keyword between similarity, the larger word of similarity is merged.It is same to calculate the keyword merged
Similarity between plate characteristic word.
Step 104, the similarity matrix of personal share and Feature Words mapping relations is established.
Personal share and plate characteristic word are established into mapping relations, form similarity matrix.Specifically, using plate characteristic word as horizontal stroke
Coordinate, using the stock code of personal share as ordinate, corresponding similarity is included in matrix, and generation personal share maps with plate characteristic word
The similarity matrix of relation.Reference table 1, show the similarity matrix of personal share and Feature Words mapping relations.
The similarity matrix of the personal share of table 1 and Feature Words mapping relations
Embodiment two
The embodiment of the present invention two is considered as the further modified flow to plate intelligence division methods flow described in embodiment one,
With reference to figure 2, the flow chart of the plate intelligence division methods of the embodiment of the present invention two, step 201 to step 204 and embodiment are shown
Corresponding step 101 is identical to step 104 in one, will not be repeated here.
After step 204, in addition to:
Classifying step 205, personal share is sorted out according to plate characteristic word.Specifically, it is special with plate to set personal share keyword
The similarity threshold of word is levied, for example sets similarity threshold as 0.5,0.5 will be more than or equal to plate characteristic Word similarity threshold value
Personal share be classified as a plate.Specifically, still by taking the table 1 in embodiment one as an example, nearly one week and plate characteristic Word similarity
Personal share more than or equal to 0.5 collects as one kind, for example electronics plate is sorted out, then the related stock of power plate includes:
000720……;State-owned enterprise reform plate:600148……;New energy plate:000720……;Limit-up yesterday plate:
000720……;Continuous rise plate:000720,600148 ....Personal share is sorted out by plate, investor selects at interface
Corresponding plate is selected, the related all stocks of the plate will all be listed one by one.
Preferably, the present embodiment also includes:
Sequence step 206, personal share is ranked up according to the similarity size of the corresponding keyword of personal share and plate characteristic word.It is right
The personal share that each plate is sorted out, is ranked up by with corresponding plate similarity size to personal share.Reference table 1, it is continuous to nearly one week
Each branch stock of rise plate is ranked up, and its clooating sequence is:000720,600148 ....Preferably, in addition to extraction is each
The forward stock of plate sequence is sorted out.
The personal share of each plate is ranked up according to similarity size, facilitates investor to check, more meets investor's demand.
Embodiment three
The embodiment of the present invention three is also considered as the further improvement stream to plate intelligence division methods flow described in embodiment one
Journey, it is with the difference of embodiment two, the present embodiment carries out classification sequence to the corresponding plate of personal share.With reference to figure 3, show
The flow charts of the plate intelligence division methods of the embodiment of the present invention three, step 301 to step 304 is identical with embodiment one, herein
Repeat no more.
After step 304, in addition to:
Classifying step 305, plate characteristic word is sorted out according to personal share.Specifically, it is special with plate to set personal share keyword
The similarity threshold of word is levied, for example sets similarity threshold as 0.5,0.5 plate will be more than or equal to personal share similarity threshold
It is classified as one kind.Still by taking the table 1 in embodiment one as an example, specifically, the plate of one week nearly to personal share is sorted out, stock 000720
Affiliated plate:Electric power, new energy, limit-up yesterday are continuous to go up;Plate belonging to stock 600148:The state-owned enterprise reform, it is continuous on
Rise.
Sort out plate by personal share, investor selects corresponding personal share at interface, and the related all plates of the personal share all will one by one
List.
Preferably, the present embodiment also includes:
Sequence step 206, according to the similarity size of the corresponding keyword of personal share and plate characteristic word to each affiliated plate of branch personal share
Block is ranked up.To the plate sorted out by personal share, plate is ranked up by corresponding plate and personal share similarity size.Reference table
1, the plate of nearly one week each branch stock is sorted by similarity size, its plate clooating sequence:000720:Electric power, limit-up yesterday,
It is continuous to go up, new energy;600148:The state-owned enterprise reform, it is continuous to go up.Preferably, in addition in each branch personal share of extraction sort forward
Plate sorted out.
Each branch personal share is ranked up according to similarity size to plate, facilitates investor to check, more meets investor's demand.
Example IV
Corresponding with the embodiment of the present invention one, the present invention also provides a kind of plate, and intelligently division device, the device reside in
In computing device, to quantify one of transaction platform operation submodule, independently installed it can also run.In the device, including people
Machine interactive interface, the time zone of information is set by investor or user, plate characteristic word is automatically generated by system and is entered
Row Plate division, and it is shown to user or investor.
With reference to figure 4, the plate of the embodiment of the present invention four intelligently division apparatus function block diagram is shown, including:
Keyword extracting module 401, suitable for obtaining basic side information and technological side data message in stock information, extraction
Keyword in basic side information and technological side data message.
By taking domestic A share market as an example, in the present embodiment, the information of stock can be from DZH, sensible in A share market
The platforms such as letter, straight flush obtain, and corresponding information includes the basic side information and technological side data message of stock, basic side
Information includes but is not limited to the title of the affiliated company of stock, stock code, main business, industry, product, financial index, newest
Message, shareholder, concept subject matter.Stock technological side data message, the including but not limited to price of stock, closing time, amount of increase and amount of decrease,
Turnover rate, exchange hand, transaction value, amount ratio.The period of above-mentioned basic side information and technological side information crosses can be pressed by user
Fancy setting, can be one week, January, 1 year.Information time zone is shorter, and Plate division can be more accurate, the reference to user
Meaning is bigger.
So that straight flush F10 pages A share market goes over the basic side information of one week as an example, feature based word extraction algorithm is from base
Multiple keywords are extracted in this face information, specifically, feature word algorithm can be extracted by information gain, card side extracts Feature Words and calculated
Method is extracted, for example extracts electric power, electric energy, wind-force, wind energy, new energy, heat energy, plate, concept etc. keyword, while from mistake
The day line market gone one week are technological side data, and limit-up yesterday plate, continuous receipts sun, continuously go up plate.Meanwhile reject default
Word, in the present embodiment, reject the keyword that plate, concept etc. are not belonging to plate characteristic word, then generate substrate panel block feature
Word:Electric power, new energy;Technological side plate characteristic word:Limit-up yesterday, continuous rise.In the present embodiment, in addition to reject suspension
The market data of stock.
Plate characteristic word generation module 402, meet threshold value suitable for the synonym in the merging keyword or similarity
Word, generate plate characteristic word.
Synonym in above-mentioned keyword or near synonym are merged, generate plate characteristic word.Specifically, meter can be passed through
The similarity between keyword is calculated to merge, by setting similarity threshold, the word to meeting threshold value merges into a plate
Block feature word.Specifically, still by taking the multiple keywords extracted in step 101 as an example, synonym electric power, electric energy are merged into electricity
Can, wind-force, wind energy merge into wind energy, while merge the larger word of similarity, and new energy, solar energy, wind energy, heat energy are merged into newly
The energy, continuous rise, continuous sun of receiving merge into continuous rise.Then generate real estate plate:Electric power, new energy;Technology panel block:
Limit-up yesterday, continuous rise.
Similarity calculation module 403, suitable for calculating the similarity of personal share keyword and plate characteristic word.
The similarity between the keyword and plate characteristic word extracted in personal share is calculated, similarity calculating method can be based on language
The vocabulary Similarity Measure of adopted dictionary, the Lexical Similarity based on corpus statisticses calculate, the vocabulary phase based on retrieval page quantity
Calculated like degree, however it is not limited to this.
Specifically, the step of the present embodiment also includes merging the keyword in above-mentioned personal share, merge in keyword
Synonym, or calculate keyword between similarity, the larger word of similarity is merged.It is same to calculate the keyword merged
Similarity between plate characteristic word.
Similarity matrix generation module 404, it is adapted to set up the similarity matrix of Feature Words and personal share keyword mapping relations.
Personal share and plate characteristic word are established into mapping relations, form similarity matrix.Specifically, using plate characteristic word as horizontal stroke
Coordinate, using the stock code of personal share as ordinate, corresponding similarity is included in matrix, generation personal share and Feature Words mapping relations
Similarity matrix, reference table 1, show the similarity matrix of personal share and Feature Words mapping relations.
Embodiment five
Corresponding with plate intelligence division methods embodiment two of the present invention, embodiment three, present invention also offers a kind of plate
Block intelligence dividing system preferred embodiment five, with reference to figure 5, show the plate of the embodiment of the present invention five intelligently division apparatus function frame
Figure, including:
Module 501 is identical to module 404 with the module 401 described in example IV to module 504, is not repeated herein.
Plate intelligence dividing system of the present invention also includes:
Classifying module 505.
It is preferably adapted to choose the word for meeting threshold value in personal share keyword with plate characteristic Word similarity, according to plate characteristic
Word is sorted out to personal share;
The similarity threshold of personal share keyword and plate characteristic word is set, for example sets similarity threshold as 0.5, will be with phase
Personal share of the plate similarity threshold more than or equal to 0.5 is answered to be classified as a plate.Specifically, still by taking the table 1 in embodiment one as an example,
Collected with personal share of the plate characteristic Word similarity more than or equal to 0.5 as one kind, for example electronics plate sorted out within nearly one week,
Then the related stock of power plate includes:000720……;State-owned enterprise reform plate:600148……;New energy plate:
000720……;Limit-up yesterday plate:000720……;Continuous rise plate:000720,600148 ....
It is preferably adapted to choose the word for meeting threshold value in personal share keyword with plate characteristic Word similarity, according to personal share to plate
Block feature word is sorted out.
Set the similarity threshold of personal share keyword and plate characteristic word, for example set similarity threshold as 0.5, will with it is individual
Plate of the stock similarity threshold more than or equal to 0.5 is classified as one kind.It is specifically, near to personal share still by taking the table 1 in embodiment one as an example
The plate of one week is sorted out, the plate belonging to stock 000720:Electric power, new energy, limit-up yesterday are continuous to go up;Stock
Plate belonging to 600148:The state-owned enterprise reform, it is continuous to go up.
Sort out plate by personal share, investor selects corresponding personal share at interface, and the related all plates of the personal share all will one by one
List.
Order module 506.
It is preferably adapted to be ranked up personal share according to the similarity size of plate characteristic word keyword corresponding to personal share.It is right
The personal share that each plate is sorted out, is ranked up by with corresponding plate similarity size to personal share.Reference table 1, it is continuous to nearly one week
Each branch stock of rise plate is ranked up, and its clooating sequence is:000720,600148 ....Preferably, in addition to extraction is each
The module that the forward stock of plate sequence is sorted out.
It is preferably adapted to arrange plate characteristic word according to the similarity size of plate characteristic word keyword corresponding to personal share
Sequence.To the plate sorted out by personal share, plate is ranked up by with corresponding plate similarity size.Reference table 1, it is each to nearly one week
The plate of branch stock sorts by similarity size, its plate clooating sequence:000720:Electric power, limit-up yesterday is continuous to go up, newly
The energy;600148:The state-owned enterprise reform, it is continuous to go up.Preferably, in addition in each branch personal share of extraction the forward plate that sorts is returned
Class.
Each branch personal share is ranked up according to similarity size to plate, facilitates investor to check, more meets investor's demand.
Embodiment six
The embodiment of the present invention additionally provides a kind of computer-readable storage medium, and the storage medium is stored with one or more journeys
Sequence, one or more of programs include instruction, and instruction is when executed by a computing apparatus so that computing device is above-mentioned any
Plate intelligence division methods in embodiment.
Embodiment seven
The embodiment of the present invention seven also proposed a kind of computing device, with reference to figure 6, show July 1st kind meter of the embodiment of the present invention
Equipment block diagram is calculated, specific implementation of the present invention not to computing device limits.
As shown in fig. 6, the computing device can include:Processor 601, memory 602, communication interface 603, communication bus
604.Processor 601, memory 602, communication interface 603 complete mutual communication by communication bus 604.
Wherein:
Communication interface 603 is used to communicate with the network element of miscellaneous equipment such as client or server etc..
Processor 601, one or more processors can be included, such as on-chip cache and two level can be included at a high speed
Cache, processor core and register of one or more ranks etc. of caching etc, for configuration processor 605, specifically
Ground, the step in above-mentioned plate intelligence division methods embodiment can be performed.Specifically, program 605 can include code, the journey
Sequence code includes computer-managed instruction.
Memory 602, for depositing program 605.The memory can include high-speed RAM memory, it is also possible to including non-easy
The property lost memory, for example, at least a magnetic disk storage.
And one or more programs, wherein one or more program storages in the memory 602 and be configured as by
Processor 601 performs, and one or more programs include being used to perform in above-mentioned any one embodiment mesoplate intelligence division methods
Either method instruction.
Specifically, the computing device in the present embodiment can be implemented as numerous general or special purpose computing system environments or
In configuration as personal computer, server computer, handheld device or portable set, laptop device, multicomputer system,
Distributed computer environment including any of the above system or equipment etc..
It will be understood by those skilled in the art that embodiments of the invention can be provided as method, equipment or computer program production
Product.Therefore, the application can use the embodiment of complete hardware embodiment, complete software embodiment or software and combination of hardware
Form.The present invention can use the computer for wherein including computer usable program code in one or more storage can be used to be situated between
The form for the computer program product implemented in matter.
Plate intelligence division methods provided by the present invention and device, computing device and storage medium have been carried out in detail above
Thin introduction, and apply specific case and the principle and embodiment of the present invention are set forth, the explanation of above example
It is only intended to help and understands the present processes and core concept.Meanwhile for those of ordinary skill in the art, according to this hair
Bright thought, in specific embodiments and applications there will be changes.In summary, this specification content should not manage
Solve as limitation of the present invention.
Claims (10)
- A kind of 1. plate intelligence division methods, suitable for being performed in computing device, it is characterised in that comprise the following steps:A. the basic side information and technological side data message in stock information are obtained, extracts basic side information and technological side data letter Keyword in breath;B. merge the synonym in the keyword or similarity meets the word of threshold value, generate plate characteristic word, the plate is special Sign word includes basic panel block feature word and technological side plate characteristic word;C. the similarity of personal share keyword and plate characteristic word is calculated;D. the similarity matrix of personal share and plate characteristic word mapping relations is established.
- 2. plate intelligence division methods as claimed in claim 1, it is characterised in that the step a is specifically included:The basic side information and technological side data message in stock information are obtained, extracts basic side information and technological side data message In keyword;Reject default keyword.
- 3. plate intelligence division methods as claimed in claim 1, it is characterised in that the step c is specifically included:Calculate the similarity in personal share between keyword and similarity is met to the keyword of threshold value and merge;Calculate the similarity of personal share keyword and plate characteristic word.
- 4. plate intelligence division methods as claimed in claim 1, it is characterised in that after the step d, in addition to sort out step Rapid e:Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, according to plate characteristic word to personal share Sorted out;Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, according to personal share to plate characteristic word Sorted out.
- 5. plate intelligence division methods as claimed in claim 4, it is characterised in that after the step e, in addition to sequence Step f:Preferably, personal share is ranked up according to the similarity size of plate characteristic word keyword corresponding to personal share;Preferably, plate characteristic word is ranked up according to the similarity size of plate characteristic word keyword corresponding to personal share.
- 6. a kind of plate intelligently divides device, suitable for residing in computing device, it is characterised in that including with lower module:Keyword extracting module, suitable for obtaining basic side information and technological side data message in stock information, extract basic side Keyword in information and technological side data message;Plate characteristic word generation module, the word of threshold value, generation are met suitable for the synonym in the merging keyword or similarity Plate characteristic word, the plate characteristic word include basic panel block feature word and technological side plate characteristic word;Similarity calculation module, suitable for calculating the similarity of personal share keyword and plate characteristic word;Similarity matrix generation module, it is adapted to set up the similarity matrix of Feature Words and personal share keyword mapping relations.
- 7. plate as claimed in claim 6 intelligently divides device, it is characterised in that also including classifying module:Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, according to plate characteristic word to personal share Sorted out;Preferably, the word for meeting threshold value in personal share keyword with plate characteristic Word similarity is chosen, according to personal share to plate characteristic word Sorted out.
- 8. the plate as any one of claim 6 or 7 intelligently divides device, it is characterised in that also including order module:It is preferably adapted to be ranked up personal share according to the similarity size of plate characteristic word keyword corresponding to personal share;It is preferably adapted to be ranked up plate characteristic word according to the similarity size of plate characteristic word keyword corresponding to personal share.
- 9. a kind of computing device, including:One or more processors;Memory;AndOne or more programs, wherein one or more of program storages are in the memory and are configured as by described one Individual or multiple computing devices, one or more of programs include being used to perform according in claim 1-5 methods describeds The instruction of either method.
- 10. a kind of computer-readable storage medium, the storage medium is stored with one or more programs, one or more of programs Including instruction, the instruction is when executed by a computing apparatus so that computing device side according to claim 1-5 Either method in method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711068194.9A CN107885806A (en) | 2017-11-03 | 2017-11-03 | Plate intelligence division methods and device, computing device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711068194.9A CN107885806A (en) | 2017-11-03 | 2017-11-03 | Plate intelligence division methods and device, computing device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107885806A true CN107885806A (en) | 2018-04-06 |
Family
ID=61778617
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711068194.9A Pending CN107885806A (en) | 2017-11-03 | 2017-11-03 | Plate intelligence division methods and device, computing device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107885806A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532499A (en) * | 2019-09-04 | 2019-12-03 | 深圳市思迪信息技术股份有限公司 | Market data intelligence method for pushing and device |
CN110889024A (en) * | 2019-10-25 | 2020-03-17 | 武汉灯塔之光科技有限公司 | Method and device for calculating information-related stock |
-
2017
- 2017-11-03 CN CN201711068194.9A patent/CN107885806A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110532499A (en) * | 2019-09-04 | 2019-12-03 | 深圳市思迪信息技术股份有限公司 | Market data intelligence method for pushing and device |
CN110889024A (en) * | 2019-10-25 | 2020-03-17 | 武汉灯塔之光科技有限公司 | Method and device for calculating information-related stock |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021088499A1 (en) | False invoice issuing identification method and system based on dynamic network representation | |
CN108596443A (en) | A kind of Electricity customers method for evaluating credit rating based on multi-dimensional data | |
CN107833153B (en) | Power grid load missing data completion method based on k-means clustering | |
CN109101489A (en) | A kind of text automatic abstracting method, device and a kind of electronic equipment | |
Li et al. | Risk dependence between energy corporations: A text-based measurement approach | |
CN103700030A (en) | Grey rough set-based power grid construction project post-evaluation index weight assignment method | |
CN106227802A (en) | A kind of based on Chinese natural language process and the multiple source Forecasting of Stock Prices method of multi-core classifier | |
CN107885806A (en) | Plate intelligence division methods and device, computing device and storage medium | |
CN103207804B (en) | Based on the MapReduce load simulation method of group operation daily record | |
CN112463958A (en) | Method for rapidly clustering massive texts based on MapReduce framework | |
CN109241146A (en) | Student's intelligence aid method and system under cluster environment | |
Han | Financial performance evaluation of colleges and universities based on DEA model and balanced scorecard method | |
CN108197729A (en) | Value investment analysis method, equipment and storage medium based on machine learning | |
Wang | AHP-entropy method credit risk assessment based on Python | |
Yang et al. | Legal empirical research on financing complex network | |
Guang et al. | Enterprise financial audit modeling research based on data mining | |
Lai et al. | Chinese stock market prediction based on multifeature fusion and TextCNN | |
Chen et al. | Evaluation and application of cloud model controller in financial technologies in the age of big data | |
Chen | The apply of ID3 in stock analysis | |
Guan et al. | Stock prediction via time series clustering and image feature extraction | |
Feifei et al. | Intelligent question and answer analysis model of power ICT based on BI-LSTM-CRF | |
Tanzi | 1 Fiscal Policy for Growth and Stability in Developing Countries: Selected Issues | |
CN112651415B (en) | Power utilization problem mining method and device for power customer group | |
Gao et al. | Research on Classification Evaluation System Based on Topsis Evaluation Model | |
Ng et al. | Evaluation on rapid profiling with clustering algorithms for plantation stocks on Bursa Malaysia |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180406 |
|
WD01 | Invention patent application deemed withdrawn after publication |