CN109493228A - A kind of method and device generating stock news in brief model - Google Patents
A kind of method and device generating stock news in brief model Download PDFInfo
- Publication number
- CN109493228A CN109493228A CN201811520380.6A CN201811520380A CN109493228A CN 109493228 A CN109493228 A CN 109493228A CN 201811520380 A CN201811520380 A CN 201811520380A CN 109493228 A CN109493228 A CN 109493228A
- Authority
- CN
- China
- Prior art keywords
- stock
- concept
- trend
- library
- mapping relations
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application provides a kind of method and devices for generating stock news in brief model, this method comprises: the stock information of acquisition targeted website, extract concept of time, objects concept and the situation concept for including in stock information, the mapping relations collection between building concept of time, objects concept and situation concept;The operation class situation conceptual design for including for each mapping relations calculates function, constructor library;For the judgement class situation concept that each mapping relations that mapping relations are concentrated include, according to the issuing time of the stock information, from stock market, the stock achievement data to match with the mapping relations and the issuing time is obtained;According to the stock achievement data, corresponding stock index trend is calculated, the corresponding relationship of the stock index trend and the mapping relations is constructed, is based on the corresponding stock index trend of each mapping relations, stock trend library is constructed, the stock news in brief model comprising function library and stock trend library is established.The formation efficiency of stock news in brief can effectively be promoted.
Description
Technical field
This application involves technical field of information processing, in particular to a kind of method for generating stock news in brief model and
Device.
Background technique
The rapid development of internet provides a large amount of conveniences for people, and numerous with national economy and money market
Honor, in conjunction with the convenience of internet, so that more and more users begin to focus on and invest in stock.Currently, user is generally logical
Internet is crossed, searches for and obtains stock information and analyzed, so that it is determined that the investment tactics of oneself.But the stock information obtains
Method, due to there are the information such as a large amount of website, news in relation to stock in internet, user's needs in different website or
Frequent switching is carried out between webpage to browse related stock information, so that user's operation is relatively complicated, when needing to expend a large amount of
Between splice stock information, stock news in brief formation efficiency is lower.
Summary of the invention
In view of this, the application's is designed to provide a kind of method and device for generating stock news in brief model, stock is promoted
The formation efficiency of ticket news in brief.
In a first aspect, the embodiment of the present application provides a kind of method for generating stock news in brief model, this method comprises:
The stock information for acquiring targeted website, extracts the concept of time, objects concept and shape for including in the stock information
Gesture concept, the mapping relations collection between building concept of time, objects concept and situation concept;
For the operation class situation concept that each mapping relations that the mapping relations are concentrated include, corresponding calculating is designed
Function, constructor library carry out numerical value calculating to the corresponding stock achievement data of the operation class situation concept to realize;
For the judgement class situation concept that each mapping relations that the mapping relations are concentrated include, provided according to the stock
The issuing time of news obtains the stock index to match with the mapping relations and the issuing time from stock market
Data;
According to the stock achievement data, corresponding stock index trend is calculated, the stock index trend is constructed and the mapping is closed
The corresponding relationship of system is based on the corresponding stock index trend of each mapping relations, constructs stock trend library, and establishing includes the function library
And the stock news in brief model in stock trend library.
Optionally, described according to the stock achievement data, calculate corresponding stock index trend, comprising:
The stock achievement data is normalized;
According to the normalized stock achievement data, corresponding stock index trend is calculated.
Optionally, after the corresponding stock index trend of the calculating, the stock index trend and the mapping relations are constructed
Before corresponding relationship, the method also includes:
According to the stock index trend calculated, matched with stock trend library;
If the stock index trend calculated matches with any stock index trend in stock trend library, do not deal with, if the stock calculated
Finger trend is mismatched with any stock index trend in stock trend library, executes the building stock index trend and the mapping is closed
The step of corresponding relationship of system.
Optionally, the stock index trend of the calculating matches with any stock index trend in stock trend library, comprising:
Using dynamic time consolidation algorithm, each stock index trend in the stock index trend and stock trend library of calculating is calculated separately
Similarity degree confirm in stock index trend and the stock trend library of calculating if there is a similarity degree to be higher than default similarity threshold
Any stock index trend matches.
Optionally, the stock news in brief model further includes stock knowledge base, the method also includes:
According to the concept of time extracted, the corresponding time interval of building concept of time, according to the objects concept extracted, building
The corresponding stock code of objects concept classifies to the situation concept of extraction, obtains stock knowledge base.
Optionally, the stock news in brief model further includes writing template library, the method also includes:
The concept of time, objects concept and situation concept that include in stock knowledge base are combined, building is comprising respectively writing
Make the writing template library of tuple template.
Optionally, the method also includes:
The writing tuple template in writing template library is parsed, writing tuple is obtained;
From stock knowledge base, the stock code to match with the writing tuple is obtained;
Obtain pair for the writing tuple traded in the corresponding time interval of concept of time for writing tuple
As the corresponding stock achievement data of concept, the stock achievement data according to the transaction calculates overall target data, according to comprehensive
Achievement data calculates trend to be assessed;
From stock trend library, the trend to match with trend to be assessed is obtained, the trend to match described in extraction is corresponding
Judgement class situation concept;
It is corresponding to the operation class situation concept based on the corresponding arithmetic logic of operation class situation concept of writing tuple
Stock achievement data carries out operation, obtains operation result;
It is ranked up according to operation result, obtains the personal share to be analyzed for meeting personal share quantity to be analyzed;
By the overall target data, the corresponding judgement class situation concept of the trend to match, operation result and to point
Analysis personal share is spliced to writing tuple, and the writing tuple based on each splicing generates stock news in brief.
Optionally, described from stock knowledge base, obtain the stock code to match with the writing tuple, comprising:
The corresponding time interval of concept of time of the writing tuple is obtained from stock knowledge base;
The corresponding stock code set of objects concept of the writing tuple is obtained from stock knowledge base.
Optionally, described to obtain the trend to match with trend to be assessed, the trend to match described in extraction is corresponding to be sentenced
Disconnected class situation concept, comprising:
Using dynamic time consolidation algorithm, the similarity degree of each trend in trend to be assessed and stock trend library is calculated,
Extract the corresponding judgement class situation concept of trend that similarity degree is higher than default similarity threshold;If the similarity degree calculated does not have
Higher than default similarity threshold, by the Trend storage to be assessed into stock trend library, class is judged for the trend setting to be assessed
Situation concept constructs the mapping relations of trend to be assessed with corresponding judgement class situation concept.
Second aspect, the embodiment of the present application provide a kind of device for generating stock news in brief model, which includes:
Stock information acquisition module extracts in the stock information for acquiring the stock information of targeted website and includes
Concept of time, objects concept and situation concept, the mapping relations collection between building concept of time, objects concept and situation concept;
Function library constructs module, the operation class situation that each mapping relations for concentrating for the mapping relations include
Concept designs corresponding calculating function, constructor library, to realize to the corresponding stock index number of the operation class situation concept
According to progress numerical value calculating;
Stock achievement data obtains module, the judgement that each mapping relations for concentrating for the mapping relations include
Class situation concept from stock market, obtains and the mapping relations and described according to the issuing time of the stock information
The stock achievement data that issuing time matches;
Stock news in brief model construction module is constructed for calculating corresponding stock index trend according to the stock achievement data
The corresponding relationship of the stock index trend and the mapping relations, is based on the corresponding stock index trend of each mapping relations, and building stock becomes
Gesture library, and establish the stock news in brief model comprising the function library and stock trend library.
The third aspect, the embodiment of the present application provide a kind of computer equipment, including memory, processor and are stored in institute
The computer program that can be run on memory and on the processor is stated, the processor executes real when the computer program
The step of existing above method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer-readable storage
Computer program is stored on medium, the computer program executes above-mentioned method when being run by processor the step of.
A kind of method and device generating stock news in brief model provided by the embodiments of the present application, passes through acquisition targeted website
Stock information, extracts the concept of time for including in the stock information, objects concept and situation concept, building concept of time, right
As the mapping relations collection between concept and situation concept;The operation for including for each mapping relations that the mapping relations are concentrated
Class situation concept designs corresponding calculating function, constructor library, to realize to the corresponding stock of the operation class situation concept
Achievement data carries out numerical value calculating;The judgement class situation concept that each mapping relations for mapping relations concentration include,
According to the issuing time of the stock information, from stock market, obtain and the mapping relations and the issuing time phase
Matched stock achievement data;According to the stock achievement data, calculate corresponding stock index trend, construct the stock index trend with
The corresponding relationship of the mapping relations is based on the corresponding stock index trend of each mapping relations, constructs stock trend library, and establish and include
The stock news in brief model in the function library and stock trend library.In this way, can use stock information and stock news in brief mould
Type generates stock news in brief, can effectively promote the formation efficiency of stock news in brief.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is stock news in brief generation method flow diagram provided by the embodiments of the present application;
Fig. 2 is a kind of another flow diagram of method for generating stock news in brief model provided by the embodiments of the present application;
Fig. 3 is the apparatus structure schematic diagram provided by the embodiments of the present application for generating stock news in brief model;
Fig. 4 is a kind of structural schematic diagram of computer equipment 400 provided by the embodiments of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
Fig. 1 is a kind of method flow schematic diagram for generating stock news in brief model provided by the embodiments of the present application.Such as Fig. 1 institute
Show, this method comprises:
Step 101, the stock information for acquiring targeted website extracts the concept of time for including in the stock information, object
Concept and situation concept, the mapping relations collection between building concept of time, objects concept and situation concept;
In the embodiment of the present application, as an alternative embodiment, using Sina's financial and economic news as targeted website, the timing acquiring net
Stock information under standing, wherein stock information includes but is not limited to: title, body matter, web site name, acquisition time, news
One of issuing time or any combination thereof.
In the embodiment of the present application, concept of time be characterize the time keyword, including but not limited to: by closing quotation, morning quotation,
Upper stock market at noon, lower stock market at noon etc..
Objects concept is the tag along sort for characterizing stock in stock market, and as an alternative embodiment, objects concept includes but not
It is limited to: A disk, B disk, two cities, stock markets of Shanghai, Shenzhen stock market, natural gas plate, the communications industry, three big stock index, GEM etc..Wherein, if object
Concept is " A disk ", then it represents that belongs to all stocks or stock code of A disk.If objects concept is " two cities ", then it represents that belong to Shanghai
All stocks or stock code in city and Shenzhen stock market.
In the embodiment of the present application, objects concept can be the tag along sort classified by stock market, for example, " three big stock index ", " depth
Demonstrate,prove into finger ", " GEM " etc., be also possible to the tag along sort classified by industry sector, for example, " petrochemical industry plate ", " communication
Service plate " etc., it can also be the tag along sort classified by concept plate, for example, " natural gas plate ", " rare earth permanent magnet plate
Block ".It can specifically be determined according to actual needs.
Situation concept, comprising: judge class situation concept and operation class situation concept.Wherein, judge that class situation concept characterizes
The keyword of stock index trend, indicate stock achievement data change trend curve text expression, including but not limited to: " it is low open it is low
Walk ", " concussion ", " drawing high ", " falling " etc..Operation class situation concept characterizes the specific value of stock index, i.e. expression stock index number
The text expression of calculated result according to statistics, including but not limited to: " drop 1.11% " " amount of increase 2.85% ", " fall and exceed 7% ", " is hit
Wear at 8000 points ", " report 1349.78 points " etc..
In the embodiment of the present application, be with the stock information in targeted website " by closing quotation, disk, natural gas plate
In the afternoon it draws high, the limit-ups such as Nanjing is public, Jin Hong is holding, Changchun combustion gas.The performance of stock trader's plate is surging, concussion is gone up, western security
Rise 2.85%, brocade dragon share, state's member security rise and exceed 1%.In terms of drop range, non-ferrous metal plate neck falls, and concussion drops, is lasting low
Fan, for Luoping zinc electricity, ancient cooking vessel victory green wood fall and exceed 7% ", the concept of time for including is " by closing quotation " that objects concept is " natural gas
Plate, stock trader's plate, non-ferrous metal plate ", situation concept are " concussion is dropped, continued downturn, performance is surging, shakes ".
Mapping relations collection then based on the building of concept of time, objects concept and situation concept includes following three mapping relations: { afternoon
Disk, natural gas plate, draws high }, { by closing quotation, stock trader's plate, surging, concussion is gone up }, by closing quotation, non-ferrous metal plate,
Concussion drop, continued downturn.
Step 102, the operation class situation concept that each mapping relations concentrated for the mapping relations include, design pair
The calculating function answered, constructor library carry out numerical value to the corresponding stock achievement data of the operation class situation concept to realize
It calculates;
In the embodiment of the present application, for the operation class situation concept in mapping relations, corresponding calculating function is designed, is constructed
Function library realizes the news content for obtaining reporting how much this kind of value type of how many point, amount of increase from stock achievement data.Wherein,
Different operation class situation concepts, can correspond to identical calculating function, can also correspond to different calculating functions.
Step 103, the judgement class situation concept that each mapping relations concentrated for the mapping relations include, according to institute
The issuing time for stating stock information, from stock market, acquisition matches with the mapping relations and the issuing time
Stock achievement data;
In the embodiment of the present application, acquisition is and the concept of time and object in the issuing time and the mapping relations
The stock achievement data that concept matches.If the issuing time of stock information is 2016.10.25 days, a concept of time therein,
The mapping relations of objects concept and situation concept are as follows: and by closing quotation, petrochemical industry plate, it is low open it is low walk, then from
2016.10.25 in the stock market (stock market) of day, the stock of all stocks in addition to suspension under petrochemical industry plate is obtained
Ticket achievement data.For another example the mapping relations of another concept of time for including in the stock information, objects concept and situation concept
Are as follows: { upper stock market at noon, rare earth permanent magnet plate are drawn high } then obtains all in addition to suspension under 9:30-11:30 rare earth permanent magnet plate
The stock achievement data of stock.
In the embodiment of the present application, as an alternative embodiment, stock achievement data includes: stock attribute data and stock
Transaction data, wherein stock attribute data includes but is not limited to: stock code, stock name, stock classification etc..Stock exchange
Data refer to data of the stock in the transaction of stock market.For example, with 5 minutes frequency, acquisition stock opening quotation time zone
Section continuous data, every stock achievement data includes: stock code, stock name, stock classification, beginning and ending time, initial value, knot
It is any multinomial in the stock informations such as beam value, peak, minimum, trading volume, price fluctuation.
In the embodiment of the present application, as an alternative embodiment, the stock using open source interface acquisition stock market refers to
Mark data.For example, by open source interface, from the corresponding each stock market of issuing time, acquisition time concept and objectives
The stock attribute data and stock exchange data of the corresponding all listed stocks of concept.
Step 104, according to the stock achievement data, corresponding stock index trend is calculated, constructs the stock index trend and institute
The corresponding relationship of mapping relations is stated, the corresponding stock index trend of each mapping relations is based on, constructs stock trend library, and establishing includes institute
State the stock news in brief model in function library and stock trend library.
In the embodiment of the present application, the storage of stock trend library: concept of time, objects concept are corresponding with class situation concept is judged
Stock index trend.As an alternative embodiment, stock achievement data is analyzed, the corresponding stock of the mapping relations is obtained and becomes
Gesture, to obtain concept of time, objects concept stock market type corresponding with class formal notion is judged.
It, can be by the variation tendency of the stock information of continuous time series, for example, 5 minutes as an alternative embodiment
Line, 20 minutes lines, half an hour line, hour line etc. characterize the stock index trend of corresponding concept of time.
In the embodiment of the present application, calculates corresponding stock index according to the stock achievement data as an alternative embodiment and become
Gesture, comprising:
The stock achievement data is normalized;
According to the normalized stock achievement data, corresponding stock index trend is calculated.
In the embodiment of the present application, due to the stock achievement data of different stocks, numerical value difference is larger, in order to avoid numerical difference
Away from larger impact stock news in brief model analysis precision, the stock achievement data got is normalized, with normalizing
Change to uniform data section.Stock achievement data is normalized to using the method for normal distribution as an alternative embodiment
Then (0,1) section carries out stock index trend calculating again.
In the embodiment of the present application, institute is constructed after the corresponding stock index trend of the calculating as another alternative embodiment
Before the corresponding relationship for stating stock index trend and the mapping relations, this method further include:
According to the stock index trend calculated, matched with stock trend library;
If the stock index trend calculated matches with any stock index trend in stock trend library, do not deal with, if the stock calculated
Finger trend is mismatched with any stock index trend in stock trend library, executes the building stock index trend and the mapping is closed
The step of corresponding relationship of system.
In the embodiment of the present application, for example, using DTW algorithm, by each stock index in the stock index trend of calculating and stock trend library
Trend comparison is respectively compared the similarity degree of each stock index trend in the stock index trend and stock trend library of calculating, if there is a phase
It is higher than default similarity threshold like degree, confirms that the stock index trend of calculating matches with any stock index trend in stock trend library.
In the embodiment of the present application, by acquiring the stock information (stock history information) of targeted website, stock history is extracted
The objects concept for including in information and the corresponding judgement class situation concept of the objects concept, in conjunction with the publication of stock history information
The stock achievement data of time map generates stock index trend, and constructs stock trend library based on stock index trend.For example, from stock
It in history information, finds out and judges class situation concept, then find corresponding concept of time and objects concept and stock history money
The issuing time of news;Then, the stock achievement data to match with concept of time and objects concept is found with issuing time to carry out
Analysis, to construct stock trend library.
In the embodiment of the present application, as an alternative embodiment, stock news in brief model further includes stock knowledge base, and this method is also
Include:
According to the concept of time extracted, the corresponding time interval of building concept of time, according to the objects concept extracted, building
The corresponding stock code of objects concept classifies to the situation concept of extraction, obtains stock knowledge base.
In the embodiment of the present application, stock knowledge base includes: the corresponding time interval of concept of time, the corresponding stock of objects concept
Ticket code, situation concept;Wherein,
By taking China Stock Markets as an example, for concept of time: by closing quotation, morning quotation, upper stock market at noon, lower stock market at noon, corresponding time zone
Between be respectively as follows: 15:00,9:30-11:30,9:30-11:30,13:00-15:00.
In the embodiment of the present application, by from stock information, acquisition time concept, according to different stock markets,
In stock knowledge base, the corresponding time interval of concept of time is respectively set.In this way, general by obtaining the time in stock information
It reads and stock market, inquires stock knowledge base, the corresponding time interval of available concept of time.For example, by obtaining
The concept of time " by closing quotation " in stock information is taken, stock knowledge base is inquired, obtains closing quotation moment " 15:00 ", for another example logical
Concept of time " morning quotation " is crossed, obtains the time interval of morning market as any time point in 9:30-11:30.
The corresponding stock code of objects concept refers to the stock code that the objects concept includes.For example, for objects concept
" A disk ", then corresponding stock code is all stocks for belonging to A disk, in stock knowledge base, stores each objects concept and phase
The corresponding stock code of the objects concept answered.
Situation concept includes: to judge class situation concept and operation class situation concept.
In the embodiment of the present application, as another alternative embodiment, stock news in brief model further includes writing template library, this method
Further include:
The concept of time, objects concept and situation concept that include in stock knowledge base are combined, building is comprising respectively writing
Make the writing template library of tuple template.
In the embodiment of the present application, for objects concept, by analysis and summarizes, stationary body objects concept can be classified as
With on-fixed main object concept.Wherein,
Stationary body object refers to similar index class stock, due to Shenzhen stock market, stock markets of Shanghai, Index of Shanghai Stock Exchange, Liang Shi, three big indexes,
It is relatively fixed that GEM etc. appears in the mode in stock information.Therefore, it is possible to be designed general as stationary body object analysis
Several writing tuple templates, such as " concept of time+objects concept+judgement class situation concept ", " concept of time+objects concept+is sentenced
Disconnected class situation concept+operation class situation concept ", " concept of time+objects concept+operation class situation concept " etc..Specifically, may be used
To be " today+', the city of '+two+judgement class situation+', '+Shenzhen composite index+operation class situation " etc..Show as an alternative embodiment, one
Under such as:
" { today: today }, { two cities: two cities } { judge class situation: slightly low to open, full-time low level concussion }, { Shenzhen composite index: deep
At finger } { operation class situation: 7999.35 points of report, drop range 1.41%, 119,800,000,000 yuan of transaction value } "
In above-mentioned example, a brace indicates that the corresponding generation of a concept is as a result, colon in a writing tuple template
It is before the concept of writing tuple template, is the content generated based on the concept after colon.
In writing tuple template, "+" symbol is can be used in the character in fixed clause and contextual information splices, and is used
Single quotation marks " ' " distinguished with the concept in writing tuple template.
On-fixed main object refers to this kind of stock achievement data of industry sector, concept plate, by being referred to respective panels
Overall target data are calculated according to stock formula, the analysis as on-fixed main object in personal share achievement data under block
As a result.
The method of the generation stock news in brief model of the embodiment of the present application is extracted by acquiring the stock information of targeted website
Concept of time, objects concept and the situation concept for including in the stock information, building concept of time, objects concept and situation are general
Mapping relations collection between thought;The judgement class situation concept that each mapping relations for mapping relations concentration include, according to
According to the issuing time of the stock information, from stock market, obtain and the mapping relations and the issuing time phase
The stock achievement data matched;According to the stock achievement data, corresponding stock index trend is calculated, constructs the stock index trend and institute
The corresponding relationship of mapping relations is stated, the corresponding stock index trend of each mapping relations, stock letter of the building comprising stock trend library are based on
Interrogate model.In this way, in subsequent applications its trend can be calculated, with stock based on the stock achievement data in stock market
News in brief model is matched, and so as to quickly determine stock news in brief, is carried out between different websites or webpage without user
Frequent switching browses related stock information, can effectively promote the formation efficiency of stock news in brief, simplifies user's operation, reduces
Browsing time of user.
Fig. 2 is a kind of another flow diagram of method for generating stock news in brief model provided by the embodiments of the present application.In Fig. 1
On the basis of, this method further include:
Step 201, the writing tuple template in writing template library is parsed, writing tuple is obtained;
In the embodiment of the present application, writing template library includes multiple writing tuple templates, and each writing tuple template is corresponding
Preset writing tuple.Wherein, writing tuple includes but is not limited to: concept of time, objects concept and situation concept.As another
Alternative embodiment, writing tuple can also include: personal share quantity to be analyzed and personal share screening rule to be analyzed.Wherein, in shape
In gesture concept, it can be set and judge class situation concept and operation class situation association of ideas logic, also can be set and judge class shape
Gesture concept or operation class situation concept, may be arranged as all situation concepts of Auto-matching.
In the embodiment of the present application, as an alternative embodiment, writing tuple includes: that concept of time, objects concept, situation are general
Thought, personal share quantity to be analyzed and personal share screening rule to be analyzed.
Assuming that writing template library includes following first writing tuple template and the second writing tuple template:
First writing tuple template: < drop by closing quotation+natural gas plate+concussion, continued downturn, performance advantage, concussion
Go up, concussion bottoms out+personal share: 4: fall to >
Second writing tuple template: < drop by closing quotation+non-ferrous metal plate+concussion, continued downturn, performance advantage, shake
Swing rise, concussion bottoms out+personal share: 3: limit down >
The personal share quantity to be analyzed of first writing tuple template is 4, the personal share quantity to be analyzed of the second writing tuple template
It is 3;
Personal share screening rule is operation class situation concept.Specifically, the rule of natural gas plate screening personal share is fortune
It calculates class situation concept: falling to, non-ferrous metal plate personal share screening rule is that operation class situation is general: limit down.
In the embodiment of the present application, need to analyze displaying in the first writing tuple template for personal share quantity to be analyzed
4 individual company share quotations information being categorized under natural gas plate;In the second writing tuple template, need to analyze 3 classification of displaying
Individual company share quotations information under non-ferrous metal plate.
Step 202, from stock knowledge base, the stock code to match with the writing tuple is obtained;
In the embodiment of the present application, by taking China Stock Markets as an example, for concept of time: by closing quotation, morning quotation, upper stock market at noon, afternoon
Disk, corresponding time interval is respectively as follows: 15:00,9:30-11:30,9:30-11:30,13:00-15:00 in stock knowledge base.
In the embodiment of the present application, in stock knowledge base, each objects concept and the objects concept corresponding stock generation are stored
Code.Thus, as an alternative embodiment, from stock knowledge base, the stock code to match with the writing tuple is obtained, packet
It includes:
The corresponding time interval of concept of time of the writing tuple is obtained from stock knowledge base;
The corresponding stock code set of objects concept of the writing tuple is obtained from stock knowledge base.
In the embodiment of the present application, the concept of time based on writing tuple: by closing quotation, by stock knowledge base, obtain from
It opens the set to the time interval of closing quotation;Objects concept based on writing tuple: natural gas plate, non-ferrous metal plate obtain respectively
It is referred to the stock code set of natural gas plate and is referred to the stock code set of non-ferrous metal plate.
Step 203, the writing traded in the corresponding time interval of concept of time for writing tuple is obtained
The corresponding stock achievement data of the objects concept of tuple, the stock achievement data according to the transaction calculate overall target data,
Trend to be assessed is calculated according to overall target data;
In the embodiment of the present application, as an alternative embodiment, the stock achievement data according to the transaction calculates synthesis and refers to
Mark data, comprising:
The corresponding stock achievement data of the objects concept of transaction is normalized;
According to normalized stock achievement data, the overall target data of the objects concept are calculated.
In the embodiment of the present application, due to the stock achievement data of different stocks, numerical value difference is larger, in order to avoid numerical difference
Precision is analyzed away from larger impact stock news in brief, the stock achievement data of the transaction got is normalized, to return
One changes to uniform data section.Stock achievement data is normalized to using the method for normal distribution as an alternative embodiment
(0,1) section.According to the corresponding all normalized stock achievement datas of objects concept, its normalized stock index number is calculated
According to average value, overall target data as the objects concept.
Step 204, from stock trend library, the trend to match with trend to be assessed is obtained, is matched described in extraction
The corresponding judgement class situation concept of trend;
In the embodiment of the present application, according to the stock achievement data obtained, matched with stock trend library.For example, utilizing
Dynamic time consolidation (DTW, Dynamic Time Warping) algorithm, by each trend ratio in trend to be assessed and stock trend library
Compared with, the similarity degree of trend to be assessed Yu each trend is calculated, similarity degree is corresponding higher than the trend of default similarity threshold
Judgement class situation concept, as the judgement class situation concept in the writing tuple;If the similarity degree calculated is not above pre-
If similarity threshold, then it fails to match for confirmation, and by the Trend storage to be assessed into stock trend library, for the trend to be assessed
Setting judges class situation concept, constructs the mapping relations of trend to be assessed with corresponding judgement class situation concept.
Step 205, the corresponding arithmetic logic of operation class situation concept based on writing tuple, it is general to the operation class situation
It reads corresponding stock achievement data and carries out operation, obtain operation result;
In the embodiment of the present application, the personal share screening rule to be analyzed for writing tuple is generally operation class situation concept, in addition,
The situation concept for writing tuple also includes operation class situation concept, and by taking the two is same operation class situation concept as an example, obtaining should
The corresponding arithmetic logic of operation class situation concept, i.e. calculating function, to the corresponding stock achievement data of operation class situation concept
Operation is carried out according to corresponding calculating function (arithmetic logic).For example, obtaining the operation class situation concept by stock function library
Corresponding arithmetic logic is referred to using the stock that the arithmetic logic of acquisition maps the corresponding objects concept of the operation class situation concept
It marks data and carries out operation, obtain operation result, spliced with the operation class situation concept, as the operation class situation concept
Analysis generates in content as a result, being presented in.
In the embodiment of the present application, stock function library is used to be directed to operation class situation concept, concept of time, objects concept, if
Corresponding arithmetic logic is set, realizes that numerical value class content generates service logic.Wherein it is possible to collect operation class from stock information
Situation concept, and arithmetic logic is set for the operation class situation concept collected, by running arithmetic logic, obtain corresponding operation knot
Fruit (numerical value) splices with the operation class situation concept, realizes the corresponding content automatic generation function of operation class situation concept.
In the embodiment of the present application, as an alternative embodiment, arithmetic logic includes but is not limited to: " amount of increase "+calculated result,
" breakthrough "+calculated result etc..For example, by after arithmetic logic operation, the analysis result of splicing are as follows: " amount of increase 3.14% " " is broken through
8000 points ".
In the embodiment of the present application, as an alternative embodiment, the corresponding arithmetic logic of each operation class situation concept is different
Operation class situation concept, identical or different arithmetic logic can be corresponded to.
Step 206, it is ranked up according to operation result, obtains the personal share to be analyzed for meeting personal share quantity to be analyzed;
In the embodiment of the present application, it is possible to specify the ordering rule of personal share to be analyzed, for example, exchange hand, transaction amount, key
Property specified judge class situation concept (such as substantially draw high, persistently drop).As an alternative embodiment, ordering rule are as follows: drop
Situation, default use drop range descending, and the personal share data of the specified quantity before screening drop range row are presented in and generate in content.Go up
Situation, default use amount of increase descending, the personal share data of the specified quantity before screening amount of increase row.
The step is optional step.
Step 207, by the overall target data, the corresponding judgement class situation concept of the trend to match, operation result
And personal share to be analyzed is spliced to writing tuple, the writing tuple based on each splicing generates stock news in brief.
In the embodiment of the present application, the text that is automatically generated according to each composition concept element of writing tuple obtained one by one
Content is integrated into complete words content (stock news in brief).It is as an alternative embodiment, same time concept, same object is general
The corresponding content of different situation concepts of thought merges, and after splicing to same concept of time, same target concept, makes
One paragraph content avoids redundant content to realize the Automatic Optimal of stock news in brief content.Wherein, a stock news in brief shows
Example result can be such that
News flash: middle card 500 is of short duration to bottom out subsequent rebound
On November 02nd, 2018 morning quotation, 500 (000905) height of middle card open.Stock market at noon, 500 (000905) height of middle card are walked.The same day,
500 (000905) height of middle card are opened, and are showed V-type reversion, are substantially drawn high, and blow rebound bugle, amount of increase 3.23%, report at one stroke
4437.95 point.
In the embodiment of the present application, tuple is write by parsing, the corresponding content of each element in writing tuple is automatically generated, spells
The corresponding content of same time concept and objectives concept in writing tuple is connect, paragraph content is generated;Paragraph content is combined, stock is generated
Ticket news in brief.
In the embodiment of the present application, as an alternative embodiment, stock news in brief is defaulted as a paragraph.In practical application,
Can according to specific needs, stock news in brief can not also limit this with customized one, two or three paragraphs, the present embodiment
It is fixed.By taking three paragraphs as an example, first section can be common index class stock situation analysis, and second segment is comprehensive for industry sector stock
Achievement data analysis is as a result, third section is concept plate stock overall target data analysis result.
Fig. 3 is the apparatus structure schematic diagram provided by the embodiments of the present application for generating stock news in brief model.As shown in figure 3, should
Device includes:
Stock information acquisition module 301 extracts in the stock information for acquiring the stock information of targeted website and includes
Concept of time, objects concept and situation concept, building concept of time, the mapping relations between objects concept and situation concept
Collection;
In the embodiment of the present application, stock information includes but is not limited to: title, body matter, web site name, acquisition time,
It gives a news briefing one of time or any combination thereof.
Function library constructs module 302, the operation class that each mapping relations for concentrating for the mapping relations include
Situation concept, designs corresponding calculating function, and constructor library refers to the corresponding stock of the operation class situation concept with realizing
It marks data and carries out numerical value calculating;
Stock achievement data obtains module 303, and each mapping relations for concentrating for the mapping relations include
Judge class situation concept, according to the issuing time of the stock information, from stock market, obtain with the mapping relations and
The stock achievement data that the issuing time matches;
In the embodiment of the present application, acquisition is and the concept of time and object in the issuing time and the mapping relations
The stock achievement data that concept matches.
In the embodiment of the present application, as an alternative embodiment, the stock using open source interface acquisition stock market refers to
Mark data.
Stock news in brief model construction module 304, for calculating corresponding stock index trend according to the stock achievement data,
The corresponding relationship of the stock index trend and the mapping relations is constructed, the corresponding stock index trend of each mapping relations is based on, constructs stock
Ticket trend library, and establish the stock news in brief model comprising the function library and stock trend library.
It is described according to the stock achievement data as an alternative embodiment in the embodiment of the present application, calculate corresponding stock
Finger trend, comprising:
The stock achievement data is normalized;
According to the normalized stock achievement data, corresponding stock index trend is calculated.
In the embodiment of the present application, as an alternative embodiment, stock news in brief model construction module 303 is also used to:
According to the stock index trend calculated, matched with stock trend library;
If the stock index trend calculated matches with any stock index trend in stock trend library, do not deal with, if the stock calculated
Finger trend is mismatched with any stock index trend in stock trend library, executes the building stock index trend and the mapping is closed
The step of corresponding relationship of system.
In the embodiment of the present application, as an alternative embodiment, the stock index trend of the calculating with it is any in stock trend library
Stock index trend matches, comprising:
Using dynamic time consolidation algorithm, each stock index trend in the stock index trend and stock trend library of calculating is calculated separately
Similarity degree confirm in stock index trend and the stock trend library of calculating if there is a similarity degree to be higher than default similarity threshold
Any stock index trend matches.
In the embodiment of the present application, as another alternative embodiment, stock news in brief model further includes stock knowledge base, stock letter
News model construction module 303 is also used to:
According to the concept of time extracted, the corresponding time interval of building concept of time, according to the objects concept extracted, building
The corresponding stock code of objects concept classifies to the situation concept of extraction, obtains stock knowledge base.
In the embodiment of the present application, as yet another alternative embodiment, stock news in brief model further includes writing template library, stock letter
News model construction module 303 is also used to:
The concept of time, objects concept and situation concept that include in stock knowledge base are combined, building is comprising respectively writing
Make the writing template library of tuple template.
In the embodiment of the present application, as another alternative embodiment, the device further include:
Stock news in brief generation module (not shown) is obtained for parsing the writing tuple template in writing template library
Write tuple;
From stock knowledge base, the stock code to match with the writing tuple is obtained;
Obtain pair for the writing tuple traded in the corresponding time interval of concept of time for writing tuple
As the corresponding stock achievement data of concept, the stock achievement data according to the transaction calculates overall target data, according to comprehensive
Achievement data calculates trend to be assessed;
From stock trend library, the trend to match with trend to be assessed is obtained, the trend to match described in extraction is corresponding
Judgement class situation concept;
It is corresponding to the operation class situation concept based on the corresponding arithmetic logic of operation class situation concept of writing tuple
Stock achievement data carries out operation, obtains operation result;
It is ranked up according to operation result, obtains the personal share to be analyzed for meeting personal share quantity to be analyzed;
By the overall target data, the corresponding judgement class situation concept of the trend to match, operation result and to point
Analysis personal share is spliced to writing tuple, and the writing tuple based on each splicing generates stock news in brief.
It is described from stock knowledge base as an alternative embodiment in the embodiment of the present application, it obtains and the writing tuple
The stock code to match, comprising:
The corresponding time interval of concept of time of the writing tuple is obtained from stock knowledge base;
The corresponding stock code set of objects concept of the writing tuple is obtained from stock knowledge base.
In the embodiment of the present application, as an alternative embodiment, the trend that the acquisition matches with trend to be assessed is extracted
The corresponding judgement class situation concept of trend to match, comprising:
Using dynamic time consolidation algorithm, the similarity degree of each trend in trend to be assessed and stock trend library is calculated,
Extract the corresponding judgement class situation concept of trend that similarity degree is higher than default similarity threshold;If the similarity degree calculated does not have
Higher than default similarity threshold, by the Trend storage to be assessed into stock trend library, class is judged for the trend setting to be assessed
Situation concept constructs the mapping relations of trend to be assessed with corresponding judgement class situation concept.
As shown in figure 4, one embodiment of the application provides a kind of computer equipment 400, for executing in Fig. 1 and Fig. 2
The method for generating stock news in brief model, the equipment include memory 401, processor 402 and are stored on the memory 401 and can
The computer program run on the processor 402, wherein above-mentioned processor 402 is realized when executing above-mentioned computer program
The step of stating the method for generating stock news in brief model.
Specifically, above-mentioned memory 401 and processor 402 can be general memory and processor, do not do have here
Body limits, and when the computer program of 402 run memory 401 of processor storage, is able to carry out above-mentioned generation stock news in brief mould
The method of type.
Corresponding to the method for the generation stock news in brief model in Fig. 1 and Fig. 2, the embodiment of the present application also provides a kind of calculating
Machine readable storage medium storing program for executing is stored with computer program on the computer readable storage medium, which is transported by processor
The step of method of above-mentioned generation stock news in brief model is executed when row.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, the method for being able to carry out above-mentioned parsing portable document format document table.
In embodiment provided herein, it should be understood that disclosed device and method, it can be by others side
Formula is realized.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only one kind are patrolled
Function division is collected, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be INDIRECT COUPLING or communication link by some communication interfaces, device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in embodiment provided by the present application can integrate in one processing unit, it can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing, in addition, term " the
One ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution.The protection in the application should all be covered
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of method for generating stock news in brief model, which is characterized in that this method comprises:
The stock information for acquiring targeted website, it is general to extract the concept of time, objects concept and situation for including in the stock information
It reads, the mapping relations collection between building concept of time, objects concept and situation concept;
For the operation class situation concept that each mapping relations that the mapping relations are concentrated include, corresponding calculating letter is designed
Number, constructor library carry out numerical value calculating to the corresponding stock achievement data of the operation class situation concept to realize;
For the judgement class situation concept that each mapping relations that the mapping relations are concentrated include, according to the stock information
Issuing time obtains the stock achievement data to match with the mapping relations and the issuing time from stock market;
According to the stock achievement data, corresponding stock index trend is calculated, constructs the stock index trend and the mapping relations
Corresponding relationship is based on the corresponding stock index trend of each mapping relations, constructs stock trend library, and establish comprising the function library and
The stock news in brief model in stock trend library.
2. the method as described in claim 1, which is characterized in that it is described according to the stock achievement data, calculate corresponding stock
Finger trend, comprising:
The stock achievement data is normalized;
According to the normalized stock achievement data, corresponding stock index trend is calculated.
3. the method as described in claim 1, which is characterized in that after the corresponding stock index trend of the calculating, described in building
Before the corresponding relationship of stock index trend and the mapping relations, the method also includes:
According to the stock index trend calculated, matched with stock trend library;
If the stock index trend calculated matches with any stock index trend in stock trend library, do not deal with, if the stock index calculated becomes
Gesture is mismatched with any stock index trend in stock trend library, executes the building stock index trend and the mapping relations
The step of corresponding relationship.
4. method as claimed in claim 3, which is characterized in that any stock in the stock index trend of the calculating and stock trend library
Finger trend matches, comprising:
Using dynamic time consolidation algorithm, the phase of the stock index trend and each stock index trend in stock trend library of calculating is calculated separately
Like degree, if there is a similarity degree to be higher than default similarity threshold, confirm the stock index trend of calculating with it is any in stock trend library
Stock index trend matches.
5. such as the described in any item methods of Claims 1-4, which is characterized in that the stock news in brief model further includes that stock is known
Know library, the method also includes:
According to the concept of time extracted, the corresponding time interval of building concept of time constructs object according to the objects concept extracted
The corresponding stock code of concept classifies to the situation concept of extraction, obtains stock knowledge base.
6. method as claimed in claim 5, which is characterized in that the stock news in brief model further includes writing template library, described
Method further include:
The concept of time, objects concept and situation concept that include in stock knowledge base are combined, building includes each writing member
The writing template library of group template.
7. method as claimed in claim 6, which is characterized in that the method also includes:
The writing tuple template in writing template library is parsed, writing tuple is obtained;
From stock knowledge base, the stock code to match with the writing tuple is obtained;
Acquisition is general in the object for the writing tuple that the corresponding time interval of concept of time of the writing tuple is traded
Corresponding stock achievement data is read, the stock achievement data according to the transaction calculates overall target data, according to overall target
Data calculate trend to be assessed;
From stock trend library, the trend to match with trend to be assessed is obtained, the trend to match described in extraction is corresponding to be sentenced
Disconnected class situation concept;
Based on the corresponding arithmetic logic of operation class situation concept of writing tuple, stock corresponding to the operation class situation concept
Achievement data carries out operation, obtains operation result;
It is ranked up according to operation result, obtains the personal share to be analyzed for meeting personal share quantity to be analyzed;
By the overall target data, the corresponding judgement class situation concept of the trend to match, operation result and to be analyzed
Stock is spliced to writing tuple, and the writing tuple based on each splicing generates stock news in brief.
8. the method for claim 7, which is characterized in that it is described from stock knowledge base, it obtains and the writing tuple
The stock code to match, comprising:
The corresponding time interval of concept of time of the writing tuple is obtained from stock knowledge base;
The corresponding stock code set of objects concept of the writing tuple is obtained from stock knowledge base.
9. the method for claim 7, which is characterized in that the trend that the acquisition matches with trend to be assessed is extracted
The corresponding judgement class situation concept of trend to match, comprising:
Using dynamic time consolidation algorithm, the similarity degree of each trend in trend to be assessed and stock trend library is calculated, is extracted
Similarity degree is higher than the corresponding judgement class situation concept of trend of default similarity threshold;If the similarity degree calculated is not above
Default similarity threshold judges class situation by the Trend storage to be assessed into stock trend library for the trend setting to be assessed
Concept constructs the mapping relations of trend to be assessed with corresponding judgement class situation concept.
10. a kind of device for generating stock news in brief model, which is characterized in that the device includes:
Stock information acquisition module extracts the time for including in the stock information for acquiring the stock information of targeted website
Concept, objects concept and situation concept, the mapping relations collection between building concept of time, objects concept and situation concept;
Function library constructs module, and the operation class situation that each mapping relations for concentrating for the mapping relations include is general
It reads, designs corresponding calculating function, constructor library, to realize to the corresponding stock achievement data of the operation class situation concept
Carry out numerical value calculating;
Stock achievement data obtains module, the judgement class shape that each mapping relations for concentrating for the mapping relations include
Gesture concept from stock market, obtains and the mapping relations and the publication according to the issuing time of the stock information
The stock achievement data that time matches;
Stock news in brief model construction module, for according to the stock achievement data, calculating corresponding stock index trend, described in building
The corresponding relationship of stock index trend and the mapping relations is based on the corresponding stock index trend of each mapping relations, constructs stock trend library,
And establish the stock news in brief model comprising the function library and stock trend library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811520380.6A CN109493228A (en) | 2018-12-12 | 2018-12-12 | A kind of method and device generating stock news in brief model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811520380.6A CN109493228A (en) | 2018-12-12 | 2018-12-12 | A kind of method and device generating stock news in brief model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109493228A true CN109493228A (en) | 2019-03-19 |
Family
ID=65709985
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811520380.6A Pending CN109493228A (en) | 2018-12-12 | 2018-12-12 | A kind of method and device generating stock news in brief model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109493228A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110209930A (en) * | 2019-04-30 | 2019-09-06 | 平安科技(深圳)有限公司 | The investee's analysis method and device of knowledge based map |
CN114493883A (en) * | 2022-02-14 | 2022-05-13 | 深圳市伊登软件有限公司 | Multi-channel data summarizing method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069141A (en) * | 2015-08-19 | 2015-11-18 | 北京工商大学 | Construction method and construction system for stock standard news library |
CN105373853A (en) * | 2015-11-18 | 2016-03-02 | 百度在线网络技术(北京)有限公司 | Stock public opinion index prediction method and device |
CN106056449A (en) * | 2016-05-26 | 2016-10-26 | 黑龙江省容维投资顾问有限责任公司 | Stock information push system and push method |
CN106780036A (en) * | 2016-11-16 | 2017-05-31 | 硕橙(厦门)科技有限公司 | A kind of moos index construction method based on internet data collection |
CN108647828A (en) * | 2018-05-15 | 2018-10-12 | 中山大学 | A kind of Prediction of Stock Index method of combination news corpus and stock market's transaction data |
-
2018
- 2018-12-12 CN CN201811520380.6A patent/CN109493228A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105069141A (en) * | 2015-08-19 | 2015-11-18 | 北京工商大学 | Construction method and construction system for stock standard news library |
CN105373853A (en) * | 2015-11-18 | 2016-03-02 | 百度在线网络技术(北京)有限公司 | Stock public opinion index prediction method and device |
CN106056449A (en) * | 2016-05-26 | 2016-10-26 | 黑龙江省容维投资顾问有限责任公司 | Stock information push system and push method |
CN106780036A (en) * | 2016-11-16 | 2017-05-31 | 硕橙(厦门)科技有限公司 | A kind of moos index construction method based on internet data collection |
CN108647828A (en) * | 2018-05-15 | 2018-10-12 | 中山大学 | A kind of Prediction of Stock Index method of combination news corpus and stock market's transaction data |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110209930A (en) * | 2019-04-30 | 2019-09-06 | 平安科技(深圳)有限公司 | The investee's analysis method and device of knowledge based map |
CN114493883A (en) * | 2022-02-14 | 2022-05-13 | 深圳市伊登软件有限公司 | Multi-channel data summarizing method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714139B (en) | Parallel data mining method for identifying a mass of mobile client bases | |
CN105447186B (en) | A kind of user behavior analysis system based on big data platform | |
CN102096717B (en) | Search method and search engine | |
CN102279851B (en) | Intelligent navigation method, device and system | |
CN103870973B (en) | Information push, searching method and the device of keyword extraction based on electronic information | |
CN102982153B (en) | A kind of information retrieval method and device thereof | |
CN105765573B (en) | Improvements in website traffic optimization | |
CN108363821A (en) | A kind of information-pushing method, device, terminal device and storage medium | |
US20140270497A1 (en) | Accurate text classification through selective use of image data | |
CN104102639B (en) | Popularization triggering method based on text classification and device | |
CN109918452A (en) | A kind of method, apparatus of data processing, computer storage medium and terminal | |
CN102663022B (en) | Classification recognition method based on URL (uniform resource locator) | |
CN105718579A (en) | Information push method based on internet-surfing log mining and user activity recognition | |
CN102929959A (en) | Book recommendation method based on user actions | |
CN103049440A (en) | Recommendation processing method and processing system for related articles | |
CN108319376B (en) | Input association recommendation method and device for optimizing commercial word promotion | |
CN103186550A (en) | Method and system for generating video-related video list | |
CN103778151A (en) | Method and device for identifying characteristic group and search method and device | |
CN102170446A (en) | Fishing webpage detection method based on spatial layout and visual features | |
CN103123633A (en) | Generation method of evaluation parameters and information searching method based on evaluation parameters | |
CN104077415A (en) | Searching method and device | |
CN108572988A (en) | A kind of house property assessment data creation method and device | |
CN101789929A (en) | Online business management network and operation method thereof | |
CN110309234A (en) | A kind of client of knowledge based map holds position method for early warning, device and storage medium | |
CN109493228A (en) | A kind of method and device generating stock news in brief model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |
|
RJ01 | Rejection of invention patent application after publication |