CN109598393A - A kind of analysis method and device of the influence information that event generates enterprise - Google Patents
A kind of analysis method and device of the influence information that event generates enterprise Download PDFInfo
- Publication number
- CN109598393A CN109598393A CN201710915307.8A CN201710915307A CN109598393A CN 109598393 A CN109598393 A CN 109598393A CN 201710915307 A CN201710915307 A CN 201710915307A CN 109598393 A CN109598393 A CN 109598393A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- keyword
- event
- analyzed
- influence
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 27
- 239000013598 vector Substances 0.000 claims description 86
- 230000000694 effects Effects 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 230000008901 benefit Effects 0.000 claims description 9
- 230000007935 neutral effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 2
- 206010003694 Atrophy Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000037444 atrophy Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the analysis methods and device of the influence information that a kind of event generates enterprise, wherein method includes: to obtain the corresponding event keyword of event to be analyzed and at least one corresponding enterprise's keyword set of enterprise to be analyzed；Obtain multiple text sentences comprising event keyword and at least one enterprise's keyword；For each text sentence, determine event keyword to the influence type of each enterprise's keyword in text sentence respectively；Influence type by event keyword to enterprise's keyword is determined as the influence type that the enterprise to be analyzed that enterprise's keyword is belonged to generates；The number for every kind of influence type that event to be analyzed generates enterprise to be analyzed is counted respectively；According to the number for every kind of influence type that event to be analyzed generates enterprise to be analyzed, the influence information that event to be analyzed generates enterprise to be analyzed is determined.The embodiment of the present invention improves the precision of analysis for the influence information that event generates enterprise, and the scope of application is not limited to marketing enterprises.
Description
Technical field
The present invention relates to computer field, in particular to the analysis method for the influence information that a kind of event generates enterprise and
Device.
Background technique
The influence information that some event generates enterprise, e.g., influence degree, and influence to be positive influences or negative shadow
Ring etc..Wherein, event includes policy event, financial events, natural calamity event etc..For example, " Beijing quotient's house limit purchase political affairs
Plan " is maximum to which business impact after coming out, it is necessary to analyze " Beijing quotient's house limit purchase policy " and promulgate this event to enterprise
The influence information that industry generates.
In the prior art, the method for the influence information that analysis event generates enterprise are as follows: by event generation time
The volatility situation of marketing enterprises is analyzed in preset time range, to determine that the event believes the influence that enterprise generates
Breath.
Inventor has found that the volatility situation of marketing enterprises is affected by many factors, if according to listing under study for action
The volatility situation of enterprise will lead to the accuracy for the influence information that a certain event analyzed generates marketing enterprises
It is low, also, existing this kind of event is only applicable to marketing enterprises to the analysis mode for the influence information that enterprise generates, so that this kind
The scope of application of analysis mode is limited.
Summary of the invention
In view of the above problems, it proposes on the present invention overcomes the above problem or at least be partially solved in order to provide one kind
The analysis method and device of the influence information that a kind of event of problem generates enterprise are stated, concrete scheme is as follows:
A kind of analysis method for the influence information that event generates enterprise, comprising:
It obtains the corresponding event keyword of event to be analyzed and at least one corresponding enterprise, enterprise to be analyzed closes
Keyword set；Enterprise's keyword set includes at least one enterprise's keyword；
Obtain multiple text sentences comprising the event keyword and at least one enterprise's keyword；
For each text sentence, determine the event keyword to described in each of described text sentence respectively
The influence type of enterprise's keyword；
By the event keyword to the influence type of enterprise's keyword, it is determined as enterprise's keyword and is belonged to
Enterprise to be analyzed generate influence type；The influence type includes positive influences, neutral influence and negative effect；
The number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed is counted respectively；
According to the number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed, determine it is described to
The influence information that analysis event generates the enterprise to be analyzed.
Wherein, the multiple texts obtained comprising the event keyword and at least one enterprise's keyword
Sentence, comprising:
In web data from news data and comprising stock market information, obtaining includes the event keyword and at least one
The text data of a enterprise's keyword；
It is extracted from the text data comprising the event keyword and at least one enterprise's keyword
Multiple text sentences.
Wherein, described to be directed to each text sentence, determine the event keyword in the text sentence respectively
Each of enterprise's keyword influence type, comprising:
Respectively by each word in the text sentence in addition to the event keyword and each enterprise's keyword
Be converted to vector；
If there is the object vector range comprising the vector after the conversion in the multiple ranges of vectors pre-established, root
According to the ranges of vectors pre-established and the corresponding relationship between type is influenced, by the corresponding influence type of the object vector range
It is determined as the influence type for each enterprise's keyword that the event keyword includes to the text sentence.
Wherein, the ranges of vectors pre-established and the corresponding relationship influenced between type are to having marked corresponding relationship
Multiple vectors and multiple influence types be trained.
Wherein, the number of every kind of influence type that the enterprise to be analyzed is generated according to the event to be analyzed,
Determine the influence information that the event to be analyzed generates the enterprise to be analyzed, comprising:
Determine every kind of maximum times for influencing type and occurring that the event to be analyzed generates the enterprise to be analyzed；
By the corresponding influence type of the maximum times and the maximum times, it is determined as the event to be analyzed to institute
State the influence information that enterprise to be analyzed generates.
The present invention also provides a kind of analytical equipment for the influence information that event generates enterprise, which includes:
First acquisition unit, for obtaining the corresponding event keyword of event to be analyzed and at least one enterprise to be analyzed
Corresponding enterprise's keyword set；Enterprise's keyword set includes at least one enterprise's keyword；
Second acquisition unit includes the more of the event keyword and at least one enterprise's keyword for obtaining
A text sentence；
First determination unit determines the event keyword to the text respectively for being directed to each text sentence
The influence type of each of this sentence enterprise's keyword；
Second determination unit is determined as institute for the influence type by the event keyword to enterprise's keyword
State the influence type that the enterprise to be analyzed that enterprise's keyword is belonged to generates；The influence type includes positive influences, neutral shadow
It rings and negatively affects；
Statistic unit, every kind of influence type that the enterprise to be analyzed is generated for counting the event to be analyzed respectively
Number；
Third determination unit, every kind of influence type for being generated according to the event to be analyzed on the enterprise to be analyzed
Number, determine the influence information that the event to be analyzed generates the enterprise to be analyzed.
Wherein, the second acquisition unit includes:
Subelement is obtained, includes the event for obtaining in the web data from news data and comprising stock market information
The text data of keyword and at least one enterprise's keyword；
Subelement is extracted, for being extracted from the text data comprising the event keyword and at least one institute
State multiple text sentences of enterprise's keyword.
Wherein, first determination unit includes:
Conversion subunit, for being extracted from the text data comprising the event keyword and at least one institute
State multiple text sentences of enterprise's keyword；
Subelement is determined, if there is the mesh comprising the vector after the conversion in multiple ranges of vectors for pre-establishing
When marking ranges of vectors, according to the ranges of vectors pre-established and the corresponding relationship between type is influenced, by the object vector model
Enclose the influence that corresponding influence type is determined as each enterprise's keyword that the event keyword includes to the text sentence
Type.
A kind of storage medium, the storage medium include the program of storage, wherein described program executes above-mentioned event pair
The analysis method for the influence information that enterprise generates.
A kind of processor, the processor is for running program, wherein described program executes above-mentioned event pair when running
The analysis method for the influence information that enterprise generates.
By above-mentioned technical proposal, a kind of analysis method reality for the influence information that event generates enterprise provided by the invention
It applies in example, from multiple text sentences comprising event keyword and at least one enterprise's keyword, obtains each text language
Event keyword is to the influence type of each enterprise's keyword in sentence, and is directed to each enterprise's keyword, by event keyword pair
The influence type of the generation of enterprise's keyword is determined as the enterprise to be analyzed that event to be analyzed belongs to enterprise's keyword
The influence type of generation.And count the number for every class influence type that event to be analyzed generates each enterprise to be analyzed, foundation
The corresponding every class of enterprise to be analyzed influences the number that type occurs, and determines influence letter of the event to be analyzed to enterprise to be analyzed
Breath.Since influence type of the event keyword to enterprise to be analyzed is only generated by the event in each text sentence, it is undoped
Therefore the influence of his factor can overcome in the prior art since the volatility situation of marketing enterprises is affected by many factors,
Influence information of a certain event to marketing enterprises is analyzed according to the volatility situation of marketing enterprises, leads to the influence analyzed
The low disadvantage of accuracy of information；In addition, text sentence come by way of judging influence information of the event to enterprise to be analyzed, it can
To be suitable for any enterprise, and it is not limited to marketing enterprises.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 shows a kind of process of the analysis method embodiment for the influence information that event generates enterprise in the present invention
Figure；
The process of the analysis method embodiment for the influence information that Fig. 2 shows another events in the present invention to generate enterprise
Figure；
The structure that Fig. 3 shows a kind of analytical equipment embodiment for the influence information that event generates enterprise in the present invention is shown
It is intended to.
Specific embodiment
Exemplary embodiments of the present disclosure are described in more detail below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
It is fully disclosed to those skilled in the art.
With reference to Fig. 1, the analysis method embodiment for the influence information that a kind of event of the invention generates enterprise is shown
Flow chart can specifically include following steps:
Step 101: obtaining the corresponding event keyword of event to be analyzed and at least one enterprise to be analyzed respectively corresponds to
Enterprise's keyword set.
In the present embodiment, event to be analyzed can be determined by user, such as analysis personnel, and event to be analyzed
Quantity is generally one.Enterprise to be analyzed is also to be determined by user, and the quantity of enterprise to be analyzed is generally at least one.
Event to be analyzed can be policy event, financial events, natural calamity event etc., for example, " Beijing quotient's house limits purchase policy "
It is exactly an event.After user has determined event to be analyzed and at least one enterprise to be analyzed, it is thus necessary to determine that event to be analyzed
Corresponding event keyword and at least one corresponding enterprise's keyword of enterprise to be analyzed, each enterprise pair to be analyzed
The number for the enterprise's keyword answered is at least one, in the present embodiment, by least one corresponding enterprise, each enterprise to be analyzed
Keyword is known as the corresponding enterprise's keyword set of the enterprise to be analyzed.For example, the event to be analyzed that user determines is " Beijing quotient
House limits purchase policy ", enterprise to be analyzed is " limited liability company, Wanke ", " greenery patches limited liability company ", " Poly share is limited
Company ", then user's definite event keyword can be " purchase of Beijing quotient's house limit ".Assuming that " Wanke's share has for enterprise to be analyzed
The corresponding enterprise's keyword of limit company " can be " company, Wanke ", " Wanke " etc., at this point, " Wanke's share is limited for enterprise to be analyzed
The corresponding enterprise's keyword set of company " includes: " company, Wanke " and " Wanke " etc..Assuming that " greenery patches share has for enterprise to be analyzed
The corresponding enterprise's keyword of limit company " only has " greenery patches ", then corresponding enterprise, enterprise to be analyzed " greenery patches limited liability company "
Keyword set only includes " greenery patches ".The corresponding keyword of event to be analyzed has been determined in user and at least one is to be analyzed
After the corresponding enterprise's keyword set of enterprise, this step needs to obtain the corresponding key of event to be analyzed that user determines
Word and at least one corresponding enterprise's keyword set of enterprise to be analyzed.
Step 102: in the web data from news data and comprising stock market information, acquisition is comprising event keyword and extremely
The text data of few enterprise's keyword.
Text data in this step is made of multiple text sentences, for example, one section of news report, commenting one section of stock market
By etc..Obtaining the corresponding event keyword of event to be analyzed and at least one corresponding enterprise's key of enterprise to be analyzed
After set of words, in this step, need to obtain the text data comprising event keyword and at least one enterprise's keyword,
In, at least one enterprise's keyword is at least one of the corresponding all enterprise's keywords of enterprise to be analyzed of all determinations,
For example, enterprise to be analyzed includes " limited liability company, Wanke ", " greenery patches limited liability company " and " Poly limited liability company ",
Wherein, " limited liability company, Wanke " corresponding enterprise's keyword set only includes " Wanke ", and " greenery patches limited liability company " is right
The enterprise's keyword answered only includes " greenery patches ", " Poly limited liability company " corresponding enterprise's keyword set is only included and " protected
Benefit ", at this point, at least one enterprise's keyword is at least one of " Wanke ", " greenery patches " and " Poly " these three keywords.Tool
Body, can in the web data from news data and comprising stock market information, obtain comprising event keyword and at least one
The text data of enterprise's keyword.
Step 103: being extracted from text data multiple comprising event keyword and at least one enterprise's keyword
Text sentence.
After obtaining the text data comprising event keyword and at least one enterprise's keyword, for example, getting one
Section news report, includes event keyword in the news report and at least one enterprise's keyword, text data include
Multiple text sentences are then obtained more comprising event keyword and at least one enterprise's keyword from this article notebook data
A text sentence.Specifically, being extracted from text data more comprising event keyword and at least one enterprise's keyword
A text sentence may include:
Firstly, according to the punctuation mark in text data, using the sentence between two neighboring terminating symbol as a text
Sentence, wherein terminating symbol indicates that the symbol of a word can be terminated, for example, fullstop, question mark, exclamation mark etc., at this point, obtaining
Multiple text sentences；Then, it filters out from obtained multiple text sentences while being looked forward to comprising event keyword at least one
The text sentence of industry keyword, at this point, containing event keyword and at least one enterprise in each text sentence filtered out
Industry keyword.
For example, event keyword is " Beijing quotient's house limit purchase ", the corresponding all enterprise's keywords of all enterprises to be analyzed
For " Wanke " and " greenery patches ", then the text sentence extracted can be for " by Beijing quotient's house limit purchase policy implication, Wanke is in business
Is whom aspect meeting atrophy ", " quotient's house limit purchase in Beijing put into effect and is most afraid of? multiple text sentences such as greenery patches and Wanke ".
The purpose of 102~step 103 of above-mentioned steps is: obtaining includes event keyword and at least one enterprise's keyword
Multiple text sentences.
Step 104: being directed to each text sentence, determine that event keyword closes each enterprise in text sentence respectively
The influence type of keyword.
After obtaining multiple multiple text sentences comprising event keyword and at least one enterprise's keyword, this step
For each text sentence, determine event keyword to the influence type of each enterprise's keyword in text sentence, this reality
Applying the influence type in example may include " positive influences ", " neutrality influences " and " negative effect ", specifically determine event keyword
Process to the influence type of each enterprise's keyword in text sentence may include step A1~step A5:
Step A1: it is directed to each text sentence, determines event keyword included in text sentence and each enterprise
Industry keyword.
For each text sentence, the event keyword and each enterprise's keyword that text sentence is included are determined,
For example, text sentence be " Beijing quotient's house limit purchase put into effect who be most afraid of? greenery patches and Wanke " in, corresponding event keyword are as follows:
" purchase of Beijing quotient's house limit ", enterprise's keyword is " greenery patches " and " Wanke ".
Step A2: converting vector for the word in text sentence in addition to event keyword and each enterprise's keyword,
Vector after obtaining multiple conversions.
For each text sentence, in the event keyword and each enterprise key for determining that text sentence is included
After word, vector is converted by the word in text sentence other than event keyword and each enterprise's keyword.For example, literary
This sentence be " whom quotient's house limit purchase in Beijing put into effect and is most afraid of? greenery patches and Wanke ", event keyword is " Beijing quotient in text sentence
House limit purchase ", enterprise's keyword is " Wanke " and " greenery patches ", therefore, in addition to " Beijing quotient lives event keyword in text sentence
Outside, remaining word is " whom puts into effect most to be afraid of ", and " whom should put into effect most for room limit purchase ", enterprise's keyword " Wanke " and " greenery patches "
Be afraid of " in it is any in text composed by continuous two words or three words be separately converted to vector, at this point, obtaining multiple words pair
Vector after the multiple conversions answered.
Step A3: judge in the multiple ranges of vectors pre-established with the presence or absence of the object vector comprising the vector after conversion
Range, and if it exists, then follow the steps A4.
In the present embodiment, the multiple influence types of multiple vector sums of corresponding relationship have been marked, wherein vector is
The corresponding vector of word is trained the vector and corresponding influence type that have marked, for example, using support vector machines into
Row training obtains a kind of type that influences and corresponds to a ranges of vectors, that is to say, that for belonging to a kind of word for influencing type
Corresponding vector belongs to a ranges of vectors.For example, word is " gain ", " income ", " benefit " etc., mark corresponding for the word
The influence type of note is " positive influences ", then, converts vector for the words such as " gain ", " income ", " benefit " correspondence, carries out
Training, obtains " positive influences " corresponding ranges of vectors, this step referred to as builds the corresponding ranges of vectors of the positive influences in advance
Vertical ranges of vectors, at this point, just establishing the corresponding relationship between " positive influences " this influence type and ranges of vectors.
It should be noted that the present embodiment by taking " gain ", " income ", " benefit " and " positive influences " as an example, is introduced and is established
The corresponding relationship influenced between type and default ranges of vectors in practical applications can also be with other words and influence
Type is come the corresponding relationship established between influence type and ranges of vectors, and the present embodiment is not on specific word and influence type work
It limits.
After step A2 obtains the corresponding multiple vectors of word, then, in this step, the multiple vectors pre-established are judged
In range whether comprising conversion after vector object vector range, then follow the steps A4 if it exists, for example, it is assumed that in advance establish
Multiple ranges of vectors in object vector range comprising " most be afraid of " corresponding vector of this word when, obtain the object vector model
It encloses.
Step A4: according to the ranges of vectors established in advance and the corresponding relationship between type is influenced, determines object vector model
Enclose corresponding influence type.
After obtaining object vector range, then, according to corresponding between the ranges of vectors established in advance and influence type
Relationship determines the corresponding influence type of the object vector range.For example, getting vector model belonging to " being most afraid of " corresponding vector
It encloses for object vector range, also, the corresponding type that influences of the object vector range is " negative in the multiple ranges of vectors established in advance
Face is rung ", then the corresponding influence type of the object vector range is " negative effect ".
Step A5: by the corresponding influence type of object vector range, it is determined as event keyword to every in text sentence
The influence type of a enterprise's keyword.
After determining the corresponding influence type of object vector range, for example, " being most afraid of " corresponding object vector range pair
The influence type answered be " negative effect ", at this point, obtain text sentence " Beijing quotient's house limit purchase put into effect who be most afraid of? greenery patches with
In Wanke ", event keyword " purchase of Beijing quotient's house limit " is " negative to the influence type of enterprise's keyword " greenery patches " and " Wanke "
It influences ".
Step 105: the influence type by event keyword to enterprise's keyword is determined as the event to be analyzed to the enterprise
The influence type for the enterprise to be analyzed that keyword is belonged to.
In this step, for each enterprise's keyword in each text sentence, event keyword is to enterprise's keyword
Influence type, be determined as the influence type for the enterprise to be analyzed that event to be analyzed belongs to enterprise's keyword.For example, thing
Part keyword " purchase of Beijing quotient's house limit " is " negative effect " to the influence type of enterprise's keyword " greenery patches " and " Wanke ", then originally
In step, determine " quotient's house limit purchase in Beijing is put into effect " this event to " greenery patches limited liability company ", " the limited public affairs of Wanke's share
The influence type of department " is all " negative effect ".
Step 106: counting the number for every kind of influence type that event to be analyzed generates enterprise to be analyzed respectively.
It is defined by step 104 and step 105 each comprising event keyword and at least one enterprise's keyword
Text sentence in, enterprise to be analyzed that each enterprise's keyword that event to be analyzed is included to text sentence is belonged to
Type is influenced, then, in this step, the enterprise to be analyzed is generated for each enterprise statistics to be analyzed event to be analyzed
Every kind influence type number.
For example, enterprise " limited liability company, Wanke " to be analyzed, " greenery patches limited liability company " and " the limited public affairs of Poly share
The corresponding number of the corresponding every kind of influence type of department " is as shown in table 1.
Table 1
Step 107: according to the number for every kind of influence type that event to be analyzed generates enterprise to be analyzed, determining to be analyzed
Influence information of the event to each enterprise to be analyzed.
After the number for counting the influence type that event to be analyzed generates each enterprise to be analyzed, then, this step
Event to be analyzed is determined to the influence information of each enterprise to be analyzed, which may include the event to be analyzed to each
The influence size of enterprise to be analyzed and influence are positive influence or negative sense influence etc..
Specifically, the number of the every kind of influence type generated according to event to be analyzed on each enterprise to be analyzed, determine to
The step of analysis event is to the influence information of each enterprise to be analyzed may include:
Step B1: the maximum time that event to be analyzed influences type and occur on every kind that each enterprise to be analyzed generates is determined
Number.
After determining event to be analyzed on the corresponding number of every kind of influence type of each enterprise's generation to be analyzed, determine
The event to be analyzed is to the maximum times in the corresponding influence type generated of each enterprise to be analyzed, for example, shown in the table 1
" limited liability company, Wanke ", " greenery patches limited liability company " and " Poly limited liability company " corresponding every kind of influence type pair
It in the number answered, can determine that maximum times are 1063 in " limited liability company, Wanke " corresponding every kind of influence type, together
It manages, maximum times are 803 in " greenery patches limited liability company " corresponding every kind of influence type, and " Poly limited liability company " is corresponding
Every kind of influence type in maximum times be 553.
Step B2: by the corresponding influence type of maximum times and the maximum times, it is determined as the event to be analyzed
To the influence information of the enterprise to be analyzed.
After the maximum times for obtaining every kind of influence type that event to be analyzed generates each enterprise to be analyzed, this is waited for
The influence type and the maximum times for the maximum times that analysis event generates the enterprise to be analyzed, are determined as the thing to be analyzed
Influence information of the part to the enterprise to be analyzed.Also by taking the information of table 1 as an example, it can determine that " limited liability company, Wanke " is corresponding
The influence types of maximum times be " positive influences ", therefore, this step is by biggest impact number 1063 and " positive influences "
As event to be analyzed to the influence information of enterprise to be analyzed " limited liability company, Wanke ", wherein maximum times characterize to
Influence size of the analysis event to the enterprise to be analyzed；Similarly, biggest impact number 803 and " positive influences " are as to be analyzed
Influence information of the event to enterprise to be analyzed " greenery patches limited liability company "；Biggest impact number 553 and " positive influences " are made
It is event to be analyzed to the influence information of enterprise to be analyzed " Poly limited liability company ".
The purpose of 106~step 107 of above-mentioned steps is: every kind generated according to event to be analyzed to each enterprise to be analyzed
The number for influencing type determines the influence information that event to be analyzed generates each enterprise to be analyzed, detailed process such as Fig. 2 institute
Show.
Through this embodiment, from multiple text sentences comprising event keyword and at least one enterprise's keyword,
Event keyword in each text sentence is obtained to the influence type of each enterprise's keyword, and is directed to each enterprise's keyword,
Influence type by event keyword to the generation of enterprise's keyword is determined as event to be analyzed and is returned to enterprise's keyword
The influence type that the enterprise to be analyzed belonged to generates.And count every class influence class that event to be analyzed generates each enterprise to be analyzed
The number of type influences the number that type occurs according to the corresponding every class of enterprise to be analyzed, determines the event to be analyzed to be analyzed
The influence information of enterprise.Since influence type of the event keyword to enterprise to be analyzed is only produced by the event in each text sentence
Raw, therefore the influence for the other factors that undope can overcome in the prior art since the volatility situation of marketing enterprises is by more
Kind factor influences, and analyzes influence information of a certain event to marketing enterprises according to the volatility situation of marketing enterprises, causes
What is analyzed influences the low disadvantage of accuracy of information；In addition, judging influence of the event to enterprise to be analyzed by text sentence
The mode of information can be adapted for any enterprise, and be not limited to marketing enterprises.
With reference to Fig. 3, a kind of analytical equipment embodiment for the influence information that event generates enterprise in the present invention is shown
Flow chart, the Installation practice may include:
First acquisition unit 301, for obtaining the corresponding event keyword of event to be analyzed and at least one is to be analyzed
The corresponding enterprise's keyword set of enterprise；Enterprise's keyword set includes at least one enterprise's keyword；
Second acquisition unit 302 includes the event keyword and at least one described enterprise's keyword for obtaining
Multiple text sentences；
Wherein, the second acquisition unit 302, can specifically include:
Subelement is obtained, includes the event for obtaining in the web data from news data and comprising stock market information
The text data of keyword and at least one enterprise's keyword；
Subelement is extracted, for being extracted from the text data comprising the event keyword and at least one institute
State multiple text sentences of enterprise's keyword.
First determination unit 303 determines the event keyword to described respectively for being directed to each text sentence
The influence type of each of text sentence enterprise's keyword；
Wherein, which may include:
Conversion subunit, for the event keyword and each enterprise's key will to be removed in the text sentence respectively
Each word outside word is converted to vector；
Subelement is determined, if there is the mesh comprising the vector after the conversion in multiple ranges of vectors for pre-establishing
When marking ranges of vectors, according to the ranges of vectors pre-established and the corresponding relationship between type is influenced, by the object vector model
Enclose the influence that corresponding influence type is determined as each enterprise's keyword that the event keyword includes to the text sentence
Type.
Wherein, the ranges of vectors that pre-establishes and the corresponding relationship for influencing between type are to having marked the more of corresponding relationship
What a vector and multiple influence types were trained.
Second determination unit 304 is determined as the influence type by the event keyword to enterprise's keyword
The influence type that the enterprise to be analyzed that enterprise's keyword is belonged to generates；The influence type includes positive influences, neutrality
It influences and negatively affects；
Statistic unit 305, every kind of influence that the enterprise to be analyzed is generated for counting the event to be analyzed respectively
The number of type；
Third determination unit 306, every kind of influence for being generated according to the event to be analyzed on the enterprise to be analyzed
The number of type determines the influence information that the event to be analyzed generates the enterprise to be analyzed.
Wherein, third determination unit 306 may include:
Maximum times determine subelement, the every kind of shadow generated for determining the event to be analyzed to the enterprise to be analyzed
Ring the maximum times that type occurs；
It influences information and determines subelement, be used for the corresponding influence type of the maximum times and the maximum times,
It is determined as the influence information that the event to be analyzed generates the enterprise to be analyzed.
A kind of event includes processor and memory to the analytical equipment for the influence information that enterprise generates, and above-mentioned first
Acquiring unit, second acquisition unit, the first determination unit, the second determination unit, statistic unit and third determination unit etc. are made
In memory for program unit storage, above procedure unit stored in memory is executed by processor to realize accordingly
Function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be set one
Or more, the precision of analysis for the influence information that event generates enterprise, and the side of analysis are improved by adjusting kernel parameter
Method is suitable for any enterprise, is not limited to marketing enterprises.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM), memory includes at least one storage
Chip.
The embodiment of the invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The analysis method for the influence information that the existing event generates enterprise.
The embodiment of the invention provides a kind of processor, the processor is for running program, wherein described program operation
The analysis method for the influence information that event described in Shi Zhihang generates enterprise.
The embodiment of the invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor perform the steps of when executing program
It obtains the corresponding event keyword of event to be analyzed and at least one corresponding enterprise, enterprise to be analyzed closes
Keyword set；Enterprise's keyword set includes at least one enterprise's keyword；
Obtain multiple text sentences comprising the event keyword and at least one enterprise's keyword；
For each text sentence, determine the event keyword to described in each of described text sentence respectively
The influence type of enterprise's keyword；
By the event keyword to the influence type of enterprise's keyword, it is determined as enterprise's keyword and is belonged to
Enterprise to be analyzed generate influence type；The influence type includes positive influences, neutral influence and negative effect；
The number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed is counted respectively；
According to the number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed, determine it is described to
The influence information that analysis event generates the enterprise to be analyzed.
Wherein, the multiple texts obtained comprising the event keyword and at least one enterprise's keyword
Sentence, comprising:
In web data from news data and comprising stock market information, obtaining includes the event keyword and at least one
The text data of a enterprise's keyword；
It is extracted from the text data comprising the event keyword and at least one enterprise's keyword
Multiple text sentences.
Wherein, described to be directed to each text sentence, determine the event keyword in the text sentence respectively
Each of enterprise's keyword influence type, comprising:
Respectively by each word in the text sentence in addition to the event keyword and each enterprise's keyword
Be converted to vector；
If there is the object vector range comprising the vector after the conversion in the multiple ranges of vectors pre-established, root
According to the ranges of vectors pre-established and the corresponding relationship between type is influenced, by the corresponding influence type of the object vector range
It is determined as the influence type for each enterprise's keyword that the event keyword includes to the text sentence.
Wherein, the ranges of vectors pre-established and the corresponding relationship influenced between type are to having marked corresponding relationship
Multiple vectors and multiple influence types be trained.
Wherein, the number of every kind of influence type that the enterprise to be analyzed is generated according to the event to be analyzed,
Determine the influence information that the event to be analyzed generates the enterprise to be analyzed, comprising:
Determine every kind of maximum times for influencing type and occurring that the event to be analyzed generates the enterprise to be analyzed；
By the corresponding influence type of the maximum times and the maximum times, it is determined as the event to be analyzed to institute
State the influence information that enterprise to be analyzed generates.
Equipment herein can be server, PC, PAD, mobile phone etc..
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flashRAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can provide as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The above is only embodiments herein, are not intended to limit this application.To those skilled in the art,
Various changes and changes are possible in this application.It is all within the spirit and principles of the present application made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of the claims of this application.
Claims (10)
1. a kind of analysis method for the influence information that event generates enterprise, which is characterized in that the described method includes:
Obtain the corresponding event keyword of event to be analyzed and at least one corresponding enterprise's keyword of enterprise to be analyzed
Set；Enterprise's keyword set includes at least one enterprise's keyword；
Obtain multiple text sentences comprising the event keyword and at least one enterprise's keyword；
For each text sentence, determine the event keyword to each of the text sentence enterprise respectively
The influence type of keyword；
By the event keyword to the influence type of enterprise's keyword, be determined as that enterprise's keyword belonged to
Analyze the influence type that enterprise generates；The influence type includes positive influences, neutral influence and negative effect；
The number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed is counted respectively；
According to the number for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed, determine described to be analyzed
The influence information that event generates the enterprise to be analyzed.
2. the method according to claim 1, wherein described obtain includes the event keyword, and at least
Multiple text sentences of one enterprise's keyword, comprising:
In web data from news data and comprising stock market information, obtaining includes the event keyword and at least one institute
State the text data of enterprise's keyword；
It is extracted from the text data multiple comprising the event keyword and at least one enterprise's keyword
Text sentence.
3. determining institute respectively the method according to claim 1, wherein described be directed to each text sentence
Event keyword is stated to the influence type of each of text sentence enterprise's keyword, comprising:
Each word in the text sentence in addition to the event keyword and each enterprise's keyword is converted respectively
For vector；
If there is the object vector range comprising the vector after the conversion in the multiple ranges of vectors pre-established, according to pre-
Corresponding relationship between the ranges of vectors first established and influence type determines the corresponding influence type of the object vector range
For the influence type for each enterprise's keyword that the event keyword includes to the text sentence.
4. according to the method described in claim 3, it is characterized in that, between the ranges of vectors pre-established and influence type
Corresponding relationship be on marked corresponding relationship multiple vectors and multiple influence types be trained.
5. the method according to claim 1, wherein it is described according to the event to be analyzed to the enterprise to be analyzed
The number for every kind of influence type that industry generates determines the influence information that the event to be analyzed generates the enterprise to be analyzed,
Include:
Determine every kind of maximum times for influencing type and occurring that the event to be analyzed generates the enterprise to be analyzed；
By the corresponding influence type of the maximum times and the maximum times, be determined as the event to be analyzed to it is described to
Analyze the influence information that enterprise generates.
6. a kind of analytical equipment for the influence information that event generates enterprise, which is characterized in that described device includes:
First acquisition unit, for obtaining the corresponding event keyword of event to be analyzed and at least one enterprise to be analyzed respectively
Corresponding enterprise's keyword set；Enterprise's keyword set includes at least one enterprise's keyword；
Second acquisition unit, for obtaining multiple texts comprising the event keyword and at least one enterprise's keyword
This sentence；
First determination unit determines the event keyword to the text language respectively for being directed to each text sentence
The influence type of each of sentence enterprise's keyword；
Second determination unit is determined as the enterprise for the influence type by the event keyword to enterprise's keyword
The influence type that the enterprise to be analyzed that industry keyword is belonged to generates；The influence type include positive influences, it is neutral influence and
Negative effect；
Statistic unit, for counting time for every kind of influence type that the event to be analyzed generates the enterprise to be analyzed respectively
Number；
Third determination unit, time of every kind of influence type for being generated according to the event to be analyzed on the enterprise to be analyzed
Number determines the influence information that the event to be analyzed generates the enterprise to be analyzed.
7. device according to claim 6, which is characterized in that the second acquisition unit includes:
Subelement is obtained, it is crucial comprising the event for obtaining in the web data from news data and comprising stock market information
The text data of word and at least one enterprise's keyword；
Subelement is extracted, for being extracted from the text data comprising the event keyword and at least one described enterprise
Multiple text sentences of industry keyword.
8. device according to claim 6, which is characterized in that first determination unit includes:
Conversion subunit, for respectively by the text sentence in addition to the event keyword and each enterprise's keyword
Each word be converted to vector；
Determine subelement, if in multiple ranges of vectors for pre-establishing exist the target comprising the vector after the conversion to
When measuring range, according to the ranges of vectors pre-established and the corresponding relationship between type is influenced, by the object vector range pair
The influence type answered is determined as the influence type for each enterprise's keyword that the event keyword includes to the text sentence.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein described program right of execution
Benefit require any one of 1 to 5 described in the event analysis method of influence information that enterprise is generated.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit require any one of 1 to 5 described in the event analysis method of influence information that enterprise is generated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710915307.8A CN109598393A (en) | 2017-09-30 | 2017-09-30 | A kind of analysis method and device of the influence information that event generates enterprise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710915307.8A CN109598393A (en) | 2017-09-30 | 2017-09-30 | A kind of analysis method and device of the influence information that event generates enterprise |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598393A true CN109598393A (en) | 2019-04-09 |
Family
ID=65955570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710915307.8A Pending CN109598393A (en) | 2017-09-30 | 2017-09-30 | A kind of analysis method and device of the influence information that event generates enterprise |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598393A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461775A (en) * | 2020-03-30 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining influence of event on traffic |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003005200A1 (en) * | 2001-07-06 | 2003-01-16 | Computer Associates Think, Inc. | Method and system for correlating and determining root causes of system and enterprise events |
| US20050071217A1 (en) * | 2003-09-30 | 2005-03-31 | General Electric Company | Method, system and computer product for analyzing business risk using event information extracted from natural language sources |
| JP2007183796A (en) * | 2006-01-06 | 2007-07-19 | Pma:Kk | Business evaluation value calculation system |
| JP2011123795A (en) * | 2009-12-14 | 2011-06-23 | Nomura Research Institute Ltd | Stock price affecting company detection system and program |
| US20120226627A1 (en) * | 2011-03-04 | 2012-09-06 | Edward Ming-Yu Yang | System and method for business reputation scoring |
| WO2012172561A1 (en) * | 2011-06-14 | 2012-12-20 | Tata Consultancy Services Limited | Enterprise information fusion |
| CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
-
2017
- 2017-09-30 CN CN201710915307.8A patent/CN109598393A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003005200A1 (en) * | 2001-07-06 | 2003-01-16 | Computer Associates Think, Inc. | Method and system for correlating and determining root causes of system and enterprise events |
| US20050071217A1 (en) * | 2003-09-30 | 2005-03-31 | General Electric Company | Method, system and computer product for analyzing business risk using event information extracted from natural language sources |
| JP2007183796A (en) * | 2006-01-06 | 2007-07-19 | Pma:Kk | Business evaluation value calculation system |
| JP2011123795A (en) * | 2009-12-14 | 2011-06-23 | Nomura Research Institute Ltd | Stock price affecting company detection system and program |
| US20120226627A1 (en) * | 2011-03-04 | 2012-09-06 | Edward Ming-Yu Yang | System and method for business reputation scoring |
| WO2012172561A1 (en) * | 2011-06-14 | 2012-12-20 | Tata Consultancy Services Limited | Enterprise information fusion |
| CN105975491A (en) * | 2016-04-26 | 2016-09-28 | 重庆誉存企业信用管理有限公司 | Enterprise news analysis method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461775A (en) * | 2020-03-30 | 2020-07-28 | 支付宝(杭州)信息技术有限公司 | Method and device for determining influence of event on traffic |
| CN111461775B (en) * | 2020-03-30 | 2023-03-24 | 支付宝(杭州)信息技术有限公司 | Method and device for determining influence of event on traffic |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276066B (en) | Entity association relation analysis method and related device | |
| TW202029079A (en) | Method and device for identifying irregular group | |
| CA3010267C (en) | Systems and methods to analyze open source components in software products | |
| CN109561052B (en) | Method and device for detecting abnormal flow of website | |
| US20210112101A1 (en) | Data set and algorithm validation, bias characterization, and valuation | |
| US10303690B1 (en) | Automated identification and classification of critical data elements | |
| EP3640814A1 (en) | User-friendly explanation production using generative adversarial networks | |
| CN111143551A (en) | Text preprocessing method, classification method, device and equipment | |
| CN110457182A (en) | A kind of load balancing cluster example operating index monitoring system | |
| CN106649210B (en) | Data conversion method and device | |
| CN112734046A (en) | Model training and data detection method, device, equipment and medium | |
| CN110019784A (en) | A kind of file classification method and device | |
| CN112988698A (en) | Data processing method and device | |
| CN109992652A (en) | A kind of information replying method, device, equipment and storage medium | |
| CN111061870B (en) | Article quality evaluation method and device | |
| CN109598393A (en) | A kind of analysis method and device of the influence information that event generates enterprise | |
| CN107038193B (en) | Text information processing method and device | |
| Ono et al. | Improving risk assessments in conservation ecology | |
| Pasupuleti | Problems from the Past, Problems from the Future, and Data Science Solutions | |
| AU2018204545B2 (en) | System and method for analysis of information technology production service support metrics | |
| EP3751500B1 (en) | System and method for technology recommendations | |
| CN111738864B (en) | Method, device and equipment for identifying group to which business entity belongs | |
| US20200357049A1 (en) | Tuning hyperparameters for predicting spending behaviors | |
| CN108228560A (en) | A kind of determining method and device of data type | |
| CN110019771B (en) | Text processing method and device |
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 | ||
| CB02 | Change of applicant information |
Address after: 100080 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Applicant after: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Applicant before: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |