CN107741929A - The analysis of public opinion method and device - Google Patents
The analysis of public opinion method and device Download PDFInfo
- Publication number
- CN107741929A CN107741929A CN201710973817.0A CN201710973817A CN107741929A CN 107741929 A CN107741929 A CN 107741929A CN 201710973817 A CN201710973817 A CN 201710973817A CN 107741929 A CN107741929 A CN 107741929A
- Authority
- CN
- China
- Prior art keywords
- event class
- keyword
- predeterminable event
- analysis
- predeterminable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a kind of the analysis of public opinion method and device, it is related to data processing field.Methods described includes obtaining the analysis of public opinion request that user terminal is sent first, the analysis of public opinion request includes at least one first keyword, it is then based at least one first keyword lookup predeterminable event class corresponding with least one first keyword, finally predeterminable event class is analyzed and processed, the data characteristics of predeterminable event class is obtained, the data characteristics is used for the public feelings information for characterizing user's care.The analysis of public opinion method and device provided by the invention can reduce searching data amount and improve analysis efficiency.
Description
Technical field
The present invention relates to data processing field, in particular to a kind of the analysis of public opinion method and device.
Background technology
With the continuous development of information technology, the analysis of public opinion method also becomes variation, and Internet public opinion analysis is because its net
Quick and accurate, the determination of content analysis that network public feelings information obtains, public sentiment respond timely, have been developed as the analysis of public opinion
Mostly important means.
But prior art lacks the association matching of event data, causes data under searched event more miscellaneous, so that
When data volume is big, it is not easy to distinguish, meanwhile, for prior art when data volume is big, analysis efficiency is low, so as to cause feedback result slow
The problem of.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of the analysis of public opinion method and device, is searched with reducing
Data volume simultaneously improves analysis efficiency.
In a first aspect, the embodiments of the invention provide the analysis of public opinion method, methods described includes：User terminal is obtained to send
The analysis of public opinion request, the analysis of public opinion request includes at least one first keyword；Closed based on described at least one first
Keyword searches predeterminable event class corresponding with least one first keyword；The predeterminable event class is carried out at analysis
Reason, obtains the data characteristics that the predeterminable event class corresponds to event, and the data characteristics is corresponding for characterizing the user terminal
The public feelings information that user is concerned about.
It is above-mentioned that the predeterminable event class is analyzed and processed in preferred embodiments of the present invention, obtain described default
Event class corresponds to the data characteristics of event, including：Part of speech analysis is carried out to the predeterminable event class, obtains the predeterminable event class
The part of speech of corresponding event；And/or sentiment analysis is carried out to the predeterminable event class, obtain the predeterminable event class and correspond to event
Emotion value；And/or golden sentence extraction is carried out to the predeterminable event class, obtain the high frequency time language that the predeterminable event class corresponds to event
Sentence；Based on the part of speech, the emotion value and/or the high frequency time sentence, the data spy that the event class corresponds to event is obtained
Sign.
In preferred embodiments of the present invention, the analysis of public opinion that above-mentioned acquisition user terminal is sent is asked, the public sentiment point
Before analysis request includes at least one keyword, in addition to：Influential event is obtained, the event is subjected to configuration life
Into event class corresponding to the event；The event class is subjected to storage as the predeterminable event class；In the predeterminable event
At least four second keywords are configured under class, and generate the mapping of at least four second keyword and the predeterminable event class
Relation.
It is above-mentioned to be based at least one first keyword lookup and described at least one in preferred embodiments of the present invention
Predeterminable event class corresponding to individual first keyword, including：Judge at least one first keyword and described at least four the
Whether any one second keyword in two keywords matches；When to be, based at least four second keyword with
The mapping relationship searching of predeterminable event class predeterminable event class corresponding with least one first keyword.
It is above-mentioned that at least four second keywords are configured under the predeterminable event class in preferred embodiments of the present invention,
And the mapping relations of at least four second keyword and the predeterminable event class are generated, including：Based on logic of propositions computing
Relation configures at least four second keyword under the predeterminable event class, and generates multiple keys with logical relation
The mapping relations of phrase and the predeterminable event class.
Second aspect, the embodiments of the invention provide a kind of the analysis of public opinion device, described device includes：The analysis of public opinion is asked
Acquisition module, for obtaining the analysis of public opinion request of user terminal transmission, the analysis of public opinion request includes at least one first
Keyword；Predeterminable event class searching modul, for based at least one first keyword lookup and described at least one the
Predeterminable event class corresponding to one keyword；Data characteristics acquisition module, for being analyzed and processed to the predeterminable event class, obtain
The predeterminable event class is taken to correspond to the data characteristics of event, the data characteristics corresponds to user pass for characterizing the user terminal
The public feelings information of the heart.
In preferred embodiments of the present invention, above-mentioned data characteristics acquisition module, including：Part of speech analyzes submodule, is used for
Part of speech analysis is carried out to the predeterminable event class, obtains the part of speech that the predeterminable event class corresponds to event；And/or sentiment analysis
Module, for carrying out sentiment analysis to the predeterminable event class, obtain the emotion value that the predeterminable event class corresponds to event；With/
Or golden sentence extracting sub-module, for carrying out golden sentence extraction to the predeterminable event class, obtain the predeterminable event class and correspond to event
High frequency time sentence；Data characteristics acquisition submodule, for based on the part of speech, the emotion value and/or the high frequency time language
Sentence, obtains the data characteristics that the event class corresponds to event.
In preferred embodiments of the present invention, said apparatus, in addition to：Event class configuration module, there is shadow for obtaining
The event of power is rung, the event is carried out into configuration generates event class corresponding to the event；Predeterminable event class acquisition module, is used for
The event class is subjected to storage as the predeterminable event class；Keyword configuration module, under the predeterminable event class
At least four second keywords are configured, and the mapping for generating at least four second keyword and the predeterminable event class is closed
System.
In preferred embodiments of the present invention, above-mentioned predeterminable event class searching modul, including：Keyword judging submodule,
For judging at least one first keyword and any one second keyword at least four second keyword
Whether match；Predeterminable event class searches submodule, for when to be, based at least four second keyword with it is described pre-
If the mapping relationship searching of event class predeterminable event class corresponding with least one first keyword.
In preferred embodiments of the present invention, above-mentioned keyword configuration module, including：Keyword configures submodule, is used for
At least four second keyword is configured under the predeterminable event class based on logic of propositions operation relation, and generates to have and patrols
The multiple crucial phrases for the relation of collecting and the mapping relations of the predeterminable event class.
Compared with prior art, the analysis of public opinion method and device that various embodiments of the present invention provide obtains user terminal first
The analysis of public opinion request of transmission, the analysis of public opinion request include at least one first keyword, are then based at least one first
Keyword lookup predeterminable event class corresponding with least one first keyword, is finally analyzed and processed to predeterminable event class,
The data characteristics of predeterminable event class is obtained, the data characteristics is used for the public feelings information for characterizing user's care, looked into so as to reduce
Look for data volume and improve analysis efficiency.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the schematic diagram that server provided in an embodiment of the present invention interacts with user terminal
Fig. 2 is the structured flowchart of electronic equipment provided in an embodiment of the present invention；
Fig. 3 is the schematic flow sheet for the analysis of public opinion method that first embodiment of the invention provides；
Fig. 4 is the step S130 for the analysis of public opinion method that first embodiment of the invention provides schematic flow sheet；
Fig. 5 is the structured flowchart for the analysis of public opinion device that second embodiment of the invention provides.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Generally exist
The component of the embodiment of the present invention described and illustrated in accompanying drawing can be configured to arrange and design with a variety of herein.Cause
This, the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing.Meanwhile the present invention's
In description, term " first ", " second " etc. are only used for distinguishing description, and it is not intended that instruction or hint relative importance.
The schematic diagram that Fig. 1 interacts for user terminal 100 provided in an embodiment of the present invention with server 200, the clothes
Business device 200 is communicatively coupled by network 300 and one or more user terminals 100, to enter row data communication or interaction.Institute
It can be the webserver, database server etc. to state server 200.The user terminal 100 can be PC
(personal computer, PC), tablet personal computer, smart mobile phone, personal digital assistant (personal digital
Assistant, PDA), the terminal such as wearable device.
As shown in figure 1, it is the block diagram of electronic equipment 400.The electronic equipment 400 includes：The analysis of public opinion device,
It is memory 410, storage control 420, processor 430, Peripheral Interface 440, input-output unit 450, audio unit 460, aobvious
Show unit 470.
The memory 410, storage control 420, processor 430, Peripheral Interface 440, input-output unit 450, sound
Frequency unit 460 and 470 each element of display unit are directly or indirectly electrically connected between each other, with realize the transmission of data or
Interaction.It is electrically connected with for example, these elements can be realized by one or more communication bus or signal wire between each other.The carriage
Mutual affection analysis apparatus can be stored in the memory or be solidified in the form of software or firmware (firmware) including at least one
Software function module in the operating system (operating system, OS) of the client device.The processor 430
For performing the executable module stored in memory 410, for example, the software function module that includes of the analysis of public opinion device or
Computer program.
Wherein, memory 410 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only storage (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM)
Deng.Wherein, memory 410 is used for storage program, and the processor 430 performs described program after execute instruction is received, preceding
State the method performed by the server that the stream process that any embodiment of the embodiment of the present invention discloses defines and can apply to processor
In 430, or realized by processor 430.
Processor 430 is probably a kind of IC chip, has the disposal ability of signal.Above-mentioned processor 430 can
To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), application specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other PLDs, discrete gate or transistor logic, discrete hard
Part component.It can realize or perform disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
Can be microprocessor or the processor can also be any conventional processor etc..
Various input/output devices are coupled to processor 430 and memory 410 by the Peripheral Interface 440.One
In a little embodiments, Peripheral Interface 440, processor 430 and storage control 420 can be realized in one single chip.At other
In some examples, they can be realized by independent chip respectively.
Input-output unit 450 is used to be supplied to user input data to realize interacting for user and electronic equipment 400.It is described
Input-output unit 450 may be, but not limited to, mouse and keyboard etc..
Audio unit 460 provides a user COBBAIF, and it may include one or more microphones, one or more raises
Sound device and voicefrequency circuit.
Display unit 470 provides an interactive interface (such as user interface) between electronic equipment 400 and user
Or referred to for display image data to user.In the present embodiment, the display unit 470 can be liquid crystal display or touch
Control display.If touch control display, it can be that the capacitance type touch control screen or resistance-type for supporting single-point and multi-point touch operation touch
Control screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one or more
Individual opening position is with caused touch control operation, and the touch control operation that this is sensed transfers to processor 430 to be calculated and handled.
First embodiment
Fig. 3 is refer to, Fig. 3 is a kind of schematic flow sheet for the analysis of public opinion method that first embodiment of the invention provides.Under
The flow shown in Fig. 3 will be described in detail for face, and methods described includes：
Step S110：The analysis of public opinion request that user terminal is sent is obtained, the analysis of public opinion request includes at least one
First keyword.
In the present embodiment, influential one or more events are obtained first, wherein, it is described influential
Event can be that attendant inputs according to business demand.Further, one or more influential events are being obtained
Afterwards, event is subjected to configuration and generates event class corresponding to the event, it will be understood that the event class can be used as many great
The motif discovery mechanism of event.Further, after one or more event classes are obtained, storage conduct is carried out to the event class
Predeterminable event class, it will be understood that the predeterminable event class is used to search foundation as user.
In the present embodiment, after obtaining predeterminable event class, it is crucial that at least four second are configured under the predeterminable event class
Word, and generate the mapping relations between at least four second keywords and the predeterminable event class.Specifically, according to predeterminable event
Class, the second keyword screening rule is configured under corresponding event class, wherein, the second keyword quantity of setting can be one
It is individual, can be two, can be three etc., it is preferred that in the present embodiment, the second keyword quantity is at least four
It is individual, wherein, be provided with logical relation between at least four second keyword, its logical relation comprise at least and/or.Enter one
Step, the screening rule can be：A+B/C/D-E-F, it will be understood that the rule must include A and B and not comprising E and
F, A and C must be included and do not include E and F or A and D must be included and do not include E and F.
Further, rule the second keyword of description is defined using regular expression, the second keyword is numbered, will
The second keyword in each event class is matched with the second keyword numbering, forms event class between the second keyword
Mapping table, wherein, each independent event has the second keyword of itself, and event forms a kind of corresponding pass with the second keyword
System, i.e., the second keyword under event can operate, be increased, changed or deleted.As a preferred mode, when
When server is set, event class is managed for the ease of server, is previously provided with database, Ke Yili in the server
Solve, the mapping table being provided with the database between event class and the second keyword.
Further, specific event can carry out data acquisition by the second keyword in manual control event class, and
Store to business in storing.In the present embodiment, Keywords matching, matching are carried out by self-defined time started and end time
Rule can define multigroup keyword, specifically, Keywords matching can be fixed according to demand data with self-defined multigroup keyword
The different keywords of justice, in accordance with above-mentioned rule, by the intermediate region scope of time started and end time, collection includes this keyword
Information.
Further, the pass of the logical operation between at least four second keywords and at least four second keywords is being obtained
After system, be further event category by search key, i.e., retrieved from the event of collection, its retrieve foundation for title,
Text and information type, by set logical operation to include or comprising, do not include, screen the event containing this class keywords,
The classification of completion event, wherein, the classification of event includes：Title, text, home news, foreign news, domestic netizen, foreign countries
It is at least one in netizen, news, paper media, computer client, cell phone application and microblogging etc..
In the present embodiment, server obtains the analysis of public opinion request that user terminal is sent, and is wrapped in the analysis of public opinion request
Include at least one first keyword.It should be understood that the user terminal can be smart mobile phone, tablet personal computer etc., Yong Huke
Server is delivered to input the analysis of public opinion request Concurrency by user terminal.It should be understood that the first pass that user terminal is sent
Keyword can be one, can be two, can be three etc., not do specific restriction herein.
Step S120：It is corresponding with least one first keyword based at least one first keyword lookup
Predeterminable event class.
In the present embodiment, it is corresponding with least one first keyword default based at least one first keyword lookup
Event class.Specifically, after at least one first keyword is obtained, by least one first keyword and at least one first
Logical operation relation and the logical relation of at least four second keywords and at least four second keywords between keyword
Matched, judge whether is any one second keyword at least one first keyword and at least four second keywords
Matching.In matching, based on the mapping relations between at least four second keywords pre-set and predeterminable event class, search
Predeterminable event class corresponding with least one first keyword.
Step S130：The predeterminable event class is analyzed and processed, obtains the number that the predeterminable event class corresponds to event
According to feature, the data characteristics is used to characterize the public feelings information that the user terminal corresponds to user's care.
After predeterminable event class corresponding to the analysis of public opinion request of user's transmission is obtained, the predeterminable event class is carried out
Comprehensive analysis processing, to obtain the data characteristics of the predeterminable event class, wherein it is possible to understand, the data characteristics is used for table
Take over user's public feelings information of concern corresponding to the terminal of family for use.
Fig. 4 is refer to, Fig. 4 shows the step S130 for the analysis of public opinion method that first embodiment of the invention provides flow
Schematic diagram.It will be explained in detail below for the flow shown in Fig. 4, methods described includes：
Step S131：Part of speech analysis is carried out to the predeterminable event class, obtains the word that the predeterminable event class corresponds to event
Property.
Specifically, event is handled using the different keyword of the event matches after screening, and by segmenting analytical technology, will
Title and text are by traveling through dictionary, matching title and the word occurred in text, it is assumed that each word be respectively n, v, a, c,
H, and n c, h counting statistics are carried out, v c, h counting statistics, a c, h counting statistics, n is the name occurred in article
Word, v are the verb occurred, and a is the adjective occurred, and c is word frequency, and h is temperature, is passed through formula R=k- (nch+vch+ach)
Statistics set is calculated, wherein k is keyword, determines the participle analysis in event.
Specifically, part of speech n, v, a, analyzed according to c, h calculating, count k values, COMPREHENSIVE CALCULATING principle, draw R word
Property summary information, such as：N, c/40464, h/1, construction, v, c/8026, h0.618, cooperation, n, c/4811, h/0.426 etc..
Step S132：Sentiment analysis is carried out to the predeterminable event class, obtains the feelings that the predeterminable event class corresponds to event
Inductance value.
In the present embodiment, sentiment analysis can also be carried out to predeterminable event class, event is corresponded to obtain predeterminable event class
Emotion value.Specifically, title and text after traversal retrieval, by DBScan algorithms, calculate analysis each article title, just
The emotion value of text, it is -1,0,1 to return to emotion value, wherein, -1 is negative, and 0 is neutrality, and 1 is front.It is appreciated that DBScan
Algorithm is based on a fact, and a cluster can be uniquely determined by any kernel object therein, and equivalence can be expressed as：It is any
Meet the data object p of kernel object condition, the set that all data object os reachable from p density are formed in database D
A complete cluster C is constituted, and p belongs to C.Positive (happy, happy, happy etc.), negative (unhappy, disagreeable etc.) dictionary
Matching, that is, analyze tendentiousness.
It should be understood that sentiment analysis segments to text or title first, and segments data to traversal, word is matched
Allusion quotation, emotion tendency judgement is carried out, is analyzed by ratio calculation, if tendentiousness<- 1, Sentiment orientation value is negative, if inclined
Tropism>1, Sentiment orientation value is front, is otherwise 0, and Sentiment orientation value is neutrality, for example, there is happiness, happy etc., as just
Face, occurs unhappy, disagreeable etc., is negatively, when positive word number>Negative word number, it is front, otherwise to be negative, when
Front word=negation words, it is neutrality.
Step S133：Golden sentence extraction is carried out to the predeterminable event class, obtains the height that the predeterminable event class corresponds to event
Frequency sentence.
In the present embodiment, golden sentence extraction can also be carried out to predeterminable event class, it is corresponding to obtain the predeterminable event class
The high frequency time sentence of event.Specifically, extracting high frequency sentence from each article, by traveling through article, each sentence is analyzed
Occurrence number, and statistics number is carried out, number then importance in the top is notable, and sentence gradually successively decreases according to occurrence number,
Importance gradually weakens.As a kind of mode, the content in article body part is divided into some sentences according to punctuate or space,
Reject to be less than and preset the minimum default sentence of sentence importance, ranking is carried out for remaining sentence, such as, 10 sentence before ranking
Son, as golden sentence.
Step S134：Based on the part of speech, the emotion value and/or the high frequency time sentence, the event class pair is obtained
Answer the data characteristics of event.
In the present embodiment, the analysis of event class progress part of speech, sentiment analysis and/or golden sentence are being extracted and obtaining the thing
After the part of speech of part class, emotion value and/or high frequency time sentence, based on part of speech, emotion value and/or high frequency time sentence, event class is obtained
The data characteristics of corresponding event, and the public feelings information that the data characteristics is concerned about as user.Specifically, count D=β+
γ+λ, while the data analysis classification under different event is handled, D is data characteristics after analysis, wherein, β is the word in article
Property, γ is the emotion value of article, and λ is article medium-high frequency time sentence, then it is the public feelings information that user is concerned about to regard as the D attributes.
The analysis of public opinion method that first embodiment of the invention provides obtains the analysis of public opinion request of user terminal transmission first,
The analysis of public opinion request include at least one first keyword, be then based at least one first keyword lookup with it is at least one
Predeterminable event class corresponding to first keyword, is finally analyzed and processed to predeterminable event class, obtains the data of predeterminable event class
Feature, the data characteristics are used for the public feelings information for characterizing user's care, so as to reduce searching data amount and improve analysis effect
Rate.
Second embodiment
Fig. 5 is refer to, Fig. 5 shows a kind of structural frames for the analysis of public opinion device 500 that second embodiment of the invention provides
Figure.The structured flowchart shown in Fig. 5 will be illustrated below, shown the analysis of public opinion device 500 includes：Event class configuration module
510th, predeterminable event class acquisition module 520, keyword configuration module 530, the analysis of public opinion acquisition request module 540, predeterminable event
Class searching modul 550, data characteristics acquisition module 560, wherein：
Event class configuration module 510, for obtaining influential event, the event is carried out described in configuration generation
Event class corresponding to event.
Predeterminable event class acquisition module 520, for the event class to be carried out into storage as the predeterminable event class.As
A kind of mode, the predeterminable event class, which searches submodule 520, to be included：Keyword judging submodule 521 and predeterminable event class are searched
Submodule 522, wherein：
Keyword judging submodule 521, for judging at least one first keyword and described at least four second
Whether any one second keyword in keyword matches.
Predeterminable event class searches submodule 522, for when to be, based at least four second keyword with it is described
The mapping relationship searching of predeterminable event class predeterminable event class corresponding with least one first keyword.
Keyword configuration module 530, for configuring at least four second keywords under the predeterminable event class, and generate
The mapping relations of at least four second keyword and the predeterminable event class.As a kind of mode, the keyword configuration
Module 530 includes：Keyword configures submodule 531, wherein：
Keyword configures submodule 531, for configuring institute under the predeterminable event class based on logic of propositions operation relation
At least four second keywords are stated, and the mapping for generating multiple crucial phrases and the predeterminable event class with logical relation is closed
System.
The analysis of public opinion acquisition request module 540, for obtaining the analysis of public opinion request of user terminal transmission, the public sentiment point
Analysis request includes at least one first keyword.
Predeterminable event class searching modul 550, for based at least one first keyword lookup and described at least one
Predeterminable event class corresponding to individual first keyword.
Data characteristics acquisition module 560, for being analyzed and processed to the predeterminable event class, obtain the predeterminable event
Class corresponds to the data characteristics of event, and the data characteristics is used to characterize the public feelings information that the user terminal corresponds to user's care.
As a kind of mode, the data characteristics acquisition module 560 includes：Part of speech analysis submodule 561, sentiment analysis submodule 562,
Golden sentence extracting sub-module 563 and data characteristics acquisition submodule 564, wherein：
Part of speech analyzes submodule 561, for carrying out part of speech analysis to the predeterminable event class, obtains the predeterminable event class
The part of speech of corresponding event.
Sentiment analysis submodule 562, for carrying out sentiment analysis to the predeterminable event class, obtain the predeterminable event class
The emotion value of corresponding event.
Golden sentence extracting sub-module 563, for carrying out golden sentence extraction to the predeterminable event class, obtain the predeterminable event class
The high frequency time sentence of corresponding event.
Data characteristics acquisition submodule 564, for based on the part of speech, the emotion value and/or the high frequency time sentence,
Obtain the data characteristics that the event class corresponds to event.
The present embodiment refers to above-mentioned Fig. 1 to the process of the respective function of each Implement of Function Module of the analysis of public opinion device 500
To the content described in embodiment illustrated in fig. 4, here is omitted.
In summary, the analysis of public opinion method and device provided in an embodiment of the present invention obtains the carriage of user terminal transmission first
Feelings analysis request, the analysis of public opinion request include at least one first keyword, are then based at least one first keyword and look into
Predeterminable event class corresponding with least one first keyword is looked for, finally predeterminable event class is analyzed and processed, is obtained default
The data characteristics of event class, the data characteristics is used for the public feelings information for characterizing user's care, so as to reduce searching data amount
And improve analysis efficiency.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, can also pass through
Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing
Show the device of multiple embodiments according to the present invention, method and computer program product architectural framework in the cards,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code
Part, a part for the module, program segment or code include one or more and are used to realize holding for defined logic function
Row instruction.It should also be noted that at some as in the implementation replaced, the function that is marked in square frame can also with different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes
It can perform in the opposite order, this is depending on involved function.It is it is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, function or the special base of action as defined in performing can be used
Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
Illustrate, herein, such as first and second or the like relational terms be used merely to by an entity or operation with
Another entity or operation make a distinction, and not necessarily require or imply between these entities or operation any this reality be present
The relation or order on border.Moreover, term " comprising ", "comprising" or its any other variant are intended to the bag of nonexcludability
Contain, so that process, method, article or equipment including a series of elements not only include those key elements, but also including
The other element being not expressly set out, or also include for this process, method, article or the intrinsic key element of equipment.
In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including the key element
Process, method, other identical element also be present in article or equipment.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that：Similar label and letter exists
Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing
It is further defined and explained.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
- A kind of 1. the analysis of public opinion method, it is characterised in that methods described includes：The analysis of public opinion request that user terminal is sent is obtained, the analysis of public opinion request includes at least one first keyword；Based at least one first keyword lookup predeterminable event class corresponding with least one first keyword；The predeterminable event class is analyzed and processed, obtains the data characteristics that the predeterminable event class corresponds to event, the number The public feelings information of user's care is corresponded to for characterizing the user terminal according to feature.
- 2. according to the method for claim 1, it is characterised in that it is described that the predeterminable event class is analyzed and processed, obtain The predeterminable event class is taken to correspond to the data characteristics of event, including：Part of speech analysis is carried out to the predeterminable event class, obtains the part of speech that the predeterminable event class corresponds to event；And/orSentiment analysis is carried out to the predeterminable event class, obtains the emotion value that the predeterminable event class corresponds to event；And/orGolden sentence extraction is carried out to the predeterminable event class, obtains the high frequency time sentence that the predeterminable event class corresponds to event；Based on the part of speech, the emotion value and/or the high frequency time sentence, the data spy that the event class corresponds to event is obtained Sign.
- 3. according to the method for claim 2, it is characterised in that the analysis of public opinion request for obtaining user terminal and sending, Before the analysis of public opinion request includes at least one keyword, in addition to：Influential event is obtained, the event is carried out into configuration generates event class corresponding to the event；The event class is subjected to storage as the predeterminable event class；At least four second keywords are configured under the predeterminable event class, and generate at least four second keyword and institute State the mapping relations of predeterminable event class.
- 4. according to the method for claim 3, it is characterised in that it is described based at least one first keyword lookup with Predeterminable event class corresponding at least one first keyword, including：Judge at least one first keyword and any one second keyword at least four second keyword Whether match；When to be, based on the mapping relationship searching of at least four second keyword and the predeterminable event class with it is described extremely Predeterminable event class corresponding to few first keyword.
- 5. according to the method for claim 3, it is characterised in that configuration at least four the under the predeterminable event class Two keywords, and the mapping relations of at least four second keyword and the predeterminable event class are generated, including：At least four second keyword is configured under the predeterminable event class based on logic of propositions operation relation, and generates tool There are multiple crucial phrases of logical relation and the mapping relations of the predeterminable event class.
- 6. a kind of the analysis of public opinion device, it is characterised in that described device includes：The analysis of public opinion acquisition request module, for obtaining the analysis of public opinion request of user terminal transmission, the analysis of public opinion request Including at least one first keyword；Predeterminable event class searching modul, for being closed based at least one first keyword lookup and described at least one first Predeterminable event class corresponding to keyword；Data characteristics acquisition module, for being analyzed and processed to the predeterminable event class, it is corresponding to obtain the predeterminable event class The data characteristics of event, the data characteristics are used to characterize the public feelings information that the user terminal corresponds to user's care.
- 7. device according to claim 6, it is characterised in that the data characteristics acquisition module, including：Part of speech analyzes submodule, for carrying out part of speech analysis to the predeterminable event class, obtains the predeterminable event class and corresponds to thing The part of speech of part；And/orSentiment analysis submodule, for carrying out sentiment analysis to the predeterminable event class, obtain the predeterminable event class and correspond to thing The emotion value of part；And/orGolden sentence extracting sub-module, for carrying out golden sentence extraction to the predeterminable event class, obtain the predeterminable event class and correspond to thing The high frequency time sentence of part；Data characteristics acquisition submodule, for based on the part of speech, the emotion value and/or the high frequency time sentence, obtaining institute The event class of stating corresponds to the data characteristics of event.
- 8. device according to claim 7, it is characterised in that described device, in addition to：Event class configuration module, for obtaining influential event, the event is subjected to configuration and generates the event pair The event class answered；Predeterminable event class acquisition module, for the event class to be carried out into storage as the predeterminable event class；Keyword configuration module, for configuring at least four second keywords under the predeterminable event class, and described in generation extremely The mapping relations of few four the second keywords and the predeterminable event class.
- 9. device according to claim 8, it is characterised in that the predeterminable event class searching modul, including：Keyword judging submodule, for judging at least one first keyword and at least four second keyword Any one second keyword whether match；Predeterminable event class searches submodule, for when to be, based at least four second keyword and the default thing The mapping relationship searching of part class predeterminable event class corresponding with least one first keyword.
- 10. device according to claim 8, it is characterised in that the keyword configuration module, including：Keyword configures submodule, for described in being configured based on logic of propositions operation relation under the predeterminable event class at least four Individual second keyword, and generate the mapping relations of multiple crucial phrases and the predeterminable event class with logical relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710973817.0A CN107741929A (en) | 2017-10-18 | 2017-10-18 | The analysis of public opinion method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710973817.0A CN107741929A (en) | 2017-10-18 | 2017-10-18 | The analysis of public opinion method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107741929A true CN107741929A (en) | 2018-02-27 |
Family
ID=61236888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710973817.0A Pending CN107741929A (en) | 2017-10-18 | 2017-10-18 | The analysis of public opinion method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107741929A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112214663A (en) * | 2020-10-22 | 2021-01-12 | 上海明略人工智能(集团)有限公司 | Method, system, device, storage medium and mobile terminal for obtaining public opinion volume |
| CN112612944A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | Case information management method, terminal equipment and system |
| CN112883733A (en) * | 2020-12-09 | 2021-06-01 | 成都中科大旗软件股份有限公司 | Analysis method for quickly constructing event relation based on text entity extraction |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408883A (en) * | 2008-11-24 | 2009-04-15 | 电子科技大学 | Method for collecting network public feelings viewpoint |
| CN103186662A (en) * | 2012-12-28 | 2013-07-03 | 中联竞成（北京）科技有限公司 | System and method for extracting dynamic public sentiment keywords |
| CN103902659A (en) * | 2014-03-04 | 2014-07-02 | 深圳市至高通信技术发展有限公司 | Public opinion analysis method and corresponding device |
| CN104536956A (en) * | 2014-07-23 | 2015-04-22 | 中国科学院计算技术研究所 | A Microblog platform based event visualization method and system |
| CN104657393A (en) * | 2013-11-25 | 2015-05-27 | 深圳市至高通信技术发展有限公司 | Public opinion analysis method and corresponding device |
| CN104731812A (en) * | 2013-12-23 | 2015-06-24 | 北京华易互动科技有限公司 | Text emotion tendency recognition based public opinion detection method |
| CN104820629A (en) * | 2015-05-14 | 2015-08-05 | 中国电子科技集团公司第五十四研究所 | Intelligent system and method for emergently processing public sentiment emergency |
| US9213730B2 (en) * | 2013-08-13 | 2015-12-15 | Xerox Corporation | Method and apparatus for extracting portions of text from long social media documents |
| CN106250513A (en) * | 2016-08-02 | 2016-12-21 | 西南石油大学 | A kind of event personalization sorting technique based on event modeling and system |
| CN106557558A (en) * | 2016-11-09 | 2017-04-05 | 中国工商银行股份有限公司 | A kind of data analysing method and device |
-
2017
- 2017-10-18 CN CN201710973817.0A patent/CN107741929A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408883A (en) * | 2008-11-24 | 2009-04-15 | 电子科技大学 | Method for collecting network public feelings viewpoint |
| CN103186662A (en) * | 2012-12-28 | 2013-07-03 | 中联竞成（北京）科技有限公司 | System and method for extracting dynamic public sentiment keywords |
| US9213730B2 (en) * | 2013-08-13 | 2015-12-15 | Xerox Corporation | Method and apparatus for extracting portions of text from long social media documents |
| CN104657393A (en) * | 2013-11-25 | 2015-05-27 | 深圳市至高通信技术发展有限公司 | Public opinion analysis method and corresponding device |
| CN104731812A (en) * | 2013-12-23 | 2015-06-24 | 北京华易互动科技有限公司 | Text emotion tendency recognition based public opinion detection method |
| CN103902659A (en) * | 2014-03-04 | 2014-07-02 | 深圳市至高通信技术发展有限公司 | Public opinion analysis method and corresponding device |
| CN104536956A (en) * | 2014-07-23 | 2015-04-22 | 中国科学院计算技术研究所 | A Microblog platform based event visualization method and system |
| CN104820629A (en) * | 2015-05-14 | 2015-08-05 | 中国电子科技集团公司第五十四研究所 | Intelligent system and method for emergently processing public sentiment emergency |
| CN106250513A (en) * | 2016-08-02 | 2016-12-21 | 西南石油大学 | A kind of event personalization sorting technique based on event modeling and system |
| CN106557558A (en) * | 2016-11-09 | 2017-04-05 | 中国工商银行股份有限公司 | A kind of data analysing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 田丽君: "《电子信息资源与检索》", 31 October 2020, 人民教育出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112214663A (en) * | 2020-10-22 | 2021-01-12 | 上海明略人工智能(集团)有限公司 | Method, system, device, storage medium and mobile terminal for obtaining public opinion volume |
| CN112612944A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | Case information management method, terminal equipment and system |
| CN112612944B (en) * | 2020-12-07 | 2024-05-31 | 深圳价值在线信息科技股份有限公司 | Case information management method, terminal equipment and system |
| CN112883733A (en) * | 2020-12-09 | 2021-06-01 | 成都中科大旗软件股份有限公司 | Analysis method for quickly constructing event relation based on text entity extraction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8725717B2 (en) | System and method for identifying topics for short text communications | |
| Sun et al. | Multivis: Content-based social network exploration through multi-way visual analysis | |
| WO2021164618A1 (en) | Knowledge graph-based question answering method and apparatus, computer device, and medium | |
| CN106951494A (en) | A kind of information recommendation method and device | |
| US20160299955A1 (en) | Text mining system and tool | |
| CN107077486A (en) | Affective Evaluation system and method | |
| CN106815307A (en) | Public Culture knowledge mapping platform and its use method | |
| CN112597182B (en) | Optimization method, device, terminal and storage medium of data query statement | |
| CN110162522B (en) | Distributed data search system and method | |
| EP2831770A1 (en) | A method and apparatus for computer assisted innovation | |
| CN111475625A (en) | News manuscript generation method and system based on knowledge graph | |
| US11295078B2 (en) | Portfolio-based text analytics tool | |
| KR20120014277A (en) | The method and system for automatically constructing positive/negative feature-predicate dictionary for polarity classification of product reviews | |
| CN107741929A (en) | The analysis of public opinion method and device | |
| CN112487161A (en) | Enterprise demand oriented expert recommendation method, device, medium and equipment | |
| CN107330111A (en) | The search method and device of domain body based on common version body | |
| CN109783815A (en) | A kind of various dimensions network public-opinion big data comparative analysis method | |
| Garg | A survey on different dimensions for graphical keyword extraction techniques: Issues and challenges | |
| Tabassum et al. | Semantic analysis of Urdu english tweets empowered by machine learning | |
| Arasu et al. | A grammar-based entity representation framework for data cleaning | |
| Vieira et al. | On finding templates on web collections | |
| Prathyusha et al. | Normalization Methods for Multiple Sources of Data | |
| CN108984513A (en) | A kind of word string recognition methods and server | |
| Dhanjal et al. | Gravity based Punjabi question answering system | |
| CN108846103B (en) | Data query 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 |