CN109829033A - Method for exhibiting data and terminal device - Google Patents
Method for exhibiting data and terminal device Download PDFInfo
- Publication number
- CN109829033A CN109829033A CN201711182131.6A CN201711182131A CN109829033A CN 109829033 A CN109829033 A CN 109829033A CN 201711182131 A CN201711182131 A CN 201711182131A CN 109829033 A CN109829033 A CN 109829033A
- Authority
- CN
- China
- Prior art keywords
- attribute
- emotion
- word
- data
- feeling polarities
- 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.)
- Granted
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application provides a kind of method for exhibiting data and terminal devices, wherein the method for exhibiting data comprises determining that target object；Obtain the multi-medium data relevant to the target object from multiple data sources；Feature Words relevant to the target object are determined from the multi-medium data；The Feature Words determined are shown.Data are only obtained by a data source compared to existing, and the Feature Words shown are all that pre-set mode is compared, protocol source provided by this example is random, the result of displaying is also random, it can be convenient for large-scale data statistics, it applies it in public sentiment data, may be implemented to effectively integrate utilization to public sentiment data.
Description
Technical field
The application belongs to Internet technical field more particularly to a kind of method for exhibiting data and terminal device.
Background technique
With the rapid development of science and technology, the especially fast development of information technology.People rely on internet more and more
Information is obtained, also more and more people are by evaluation of the internet publication to the hobby of some product or effect etc., in these
Appearance can be referred to as public sentiment.
If can effectively integrate utilization for these public sentiment datas, can be provided for people more fully and objectively
Cognition.The existing mode for providing product cognition for user based on public sentiment data is opposite or relatively simple, generally also only
It is to have the evaluation content of directive property as data source on a website using user, the result integrated is also based in advance
What the Feature Words of setting carried out.For example, the evaluation to a dining room, user is namely based on some websites to the finger in the dining room
Tropism evaluation content is polymerize, and the result polymerizeing is also pre-set frame, is gathered based on the word in frame
Classification is closed, evaluation of the user to the dining room under the website is obtained, for example, marking, evaluation content etc..
This requires the data source of a fixed directive property, and shows that result is relatively fixed, can not be to public sentiment data
Carry out effective analysis and utilization.
For this problem, currently no effective solution has been proposed.
Summary of the invention
The application is designed to provide a kind of method for exhibiting data and terminal device, may be implemented to the effective of public sentiment data
Integration utilizes.
The application provides a kind of method for exhibiting data and terminal device is achieved in that
A kind of method for exhibiting data, comprising:
Determine target object；
Obtain the multi-medium data relevant to the target object from multiple data sources；
Feature Words relevant to the target object are determined from the multi-medium data；
The Feature Words determined are shown.
A kind of terminal device, including processor and for the memory of storage processor executable instruction, the processing
Device realizes following steps when executing described instruction:
Determine target object；
Obtain the multi-medium data relevant to the target object from multiple data sources；
Feature Words relevant to the target object are determined from the multi-medium data；
The Feature Words determined are shown.
A kind of computer readable storage medium is stored thereon with computer instruction, and it is above-mentioned that described instruction is performed realization
The step of method.
Method for exhibiting data provided by the present application after the target object of inquiry has been determined is obtained from multiple data sources
Relevant multi-medium data is taken, and is to determine the Feature Words of target object from these multi-medium datas of acquisition and opened up
Show.Data are only obtained by a data source compared to existing, and the Feature Words shown are all pre-set modes
Compare, protocol source provided by this example is random, the result of displaying be also it is random, can be convenient for a wide range of
Data statistics, apply it in public sentiment data, may be implemented to effectively integrate utilization to public sentiment data.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, in the premise of not making the creative labor property
Under, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of configuration diagram of embodiment of public sentiment data processing system provided by the present application；
Fig. 2 is that cluster result provided by the present application shows a kind of schematic diagram of embodiment in interface；
Fig. 3 is the analysis processing flow schematic diagram provided by the present application based on public sentiment data；
Fig. 4 is a kind of schematic diagram of embodiment of interdependent syntax tree provided by the present application；
Fig. 5 is the illustrative diagram that cluster result provided by the present application shows interface；
Fig. 6 is a kind of configuration diagram of embodiment of terminal device provided by the present application；
Fig. 7 is that data provided by the present application show a kind of modular structure schematic diagram of embodiment of device.
Specific embodiment
In order to make those skilled in the art better understand the technical solutions in the application, below in conjunction with the application reality
The attached drawing in example is applied, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described implementation
Example is merely a part but not all of the embodiments of the present application.Based on the embodiment in the application, this field is common
The application protection all should belong in technical staff's every other embodiment obtained without creative efforts
Range.
In this example, it is contemplated that if can be obtained from the data of internet mass it is relevant to specific products description or
Data are evaluated, the attribute and emotion information of the multiple dimensions of the specific products are then obtained from these data, and to these attributes
Carry out aggregate statistics with emotion information, to be formed to the evaluation cognitive informations of the multiple dimensions of the specific products, in this way general so that with
Family can more comprehensively recognize the specific products.
Based on this, a kind of public sentiment data processing system is provided in this example, as shown in Figure 1, may include: server
101, terminal 102.The available multimedia number relevant to the target object from multiple data sources of server 101
According to determining Feature Words relevant to target object from multi-medium data, and pushed to terminal 102 and be shown.?
Can be these operations is all that terminal 102 executes, that is, obtains data from multiple data sources, carries out integration to data and show all
It is executed by terminal 102.Which kind of mode is specifically used, can according to actual needs, the application is not construed as limiting this.
In one embodiment, above-mentioned server 101 can be single server, be also possible to server cluster,
It is also possible to the processor etc. in cloud, can be specifically selected according to actual needs using which kind of mode.
In one embodiment, above-mentioned terminal 102 can be the terminal device or software that user's operation uses.Specifically
, terminal 102 can be with smart phone, tablet computer, laptop, desktop computer, smartwatch or other wearable
The terminal devices such as equipment.Certainly, terminal 102 is also possible to the software that can be run in above-mentioned terminal device.Such as: mobile phone is washed in a pan
The application software such as precious, Alipay or browser.
In one embodiment, above-mentioned multi-medium data can be text data, be also possible to voice data, video counts
According to etc..For example, can identify the text wherein carried by speech recognition if the multi-medium data obtained is voice data
Word can be understood by image, semantic if the multi-medium data obtained is video data and identify the text wherein carried.?
When realization, select any or a plurality of types of data that can select according to actual needs as the multi-medium data obtained
It selects, the application is not construed as limiting this.
It is illustrated for realizing data acquisition, polymerization on server 101, it, can also for terminal 102
To be carried out as follows acquisition and the converging operation of data.
Specifically, method for exhibiting data may include steps of:
S1: target object is determined；
In one embodiment, it can be the keyword for receiving user's input, using the keyword of user's input as mesh
Object is marked, is also possible to preset a lists of keywords, user clicks, and the keyword that user is clicked is as target
Object.Can certainly be before user directly selects the keyword that once inputs as target object etc.,
It is important to note, however, that enumerating the mode for the object that sets the goal really listed by above-mentioned is only a kind of exemplary description,
, can also be in such a way that others determine target object when actually realizing, the application is not construed as limiting this.
By taking " small A automobile " as an example, user can input " small A automobile ", that is, using " small A automobile " as keyword, also with regard to phase
The object that should set the goal really is " small A automobile ".
S2: the multi-medium data relevant to the target object from multiple data sources is obtained；
After target object " small A automobile " has been determined, so that it may obtain number relevant to target object from internet
According to.Specifically, can be from multiple website platforms when obtaining data and crawl data.For example, can be only from News Network
Data are obtained on standing, and are also possible to obtain and target object phase from platforms such as news website, forum, discussion bar, electric business platform, microbloggings
The data of pass.I.e., it is possible to data be obtained from multiple data sources, so that the data about " small A automobile " obtained are more complete
Face.
When determining data source, it can be and be determined according to actual requirements which data source as target data source.Example
Such as, if it is need see " small A automobile " entire traffic-operating period, on internet either news report or forum, paste
As soon as, the user of electric business website require to carry out the user comprehensively understood using feedback, then needs are from multiple networks
Platform crawls data, to obtain to " small A automobile " more comprehensively statistical result.
That is, acquired data are obtained from multiple data sources in this example, these data can be news data, can
To be the data etc. of discussion bar, these data be all it is non-direction, and only pass through own website in existing comment website
Data carry out polymerization display and are different, and the data of existing comment website generally also all have directive property, for the object
The data of evaluation are exclusively carried out, therefore, data source is entirely different.
S3: Feature Words relevant to the target object are determined from above-mentioned multi-medium data；
Features described above word can include but is not limited at least one of: attribute word, emotion word, attribute classification.
Specifically, can first be extracted from the data of magnanimity after getting the data of magnanimity from multiple data sources
Sentence containing emotional expression can reduce the complexity of subsequent processing, save the time of data processing.Certainly, this is only one
A optional step can not also first pre-process data when actually realizing, but directly by all data
It is regarded as the sentence containing emotional expression, is sent directly into subsequent treatment process.It specifically can be according to being using which kind of mode
The ability and actual needs selection, the application of the processing of system are not construed as limiting this.
Such as: target object is small A automobile, " small A automotive subjects are the automobiles from XX country " and " small A automobile
It is especially comfortable " two words, first is not just emotion sentence, and second is exactly emotion sentence.When carrying out data prediction, just
" small A automobile is especially comfortable " only is extracted, and " small A automotive subjects are the automobiles from XX country " is then given up.
It pre-processes to data, during therefrom extracting the sentence containing emotional expression, can pass through
Fasttext text classification algorithm identifies emotion sentence.Wherein, fasttext text classification algorithm is a kind of disclosed text point
Class algorithm, by extracting various dimensions feature from sentence, learning classification function passes through to predict classification belonging to sentence
Fasttext text classification algorithm can help to establish the solution of quantization for text representation and classification.
It should be noted, however, that fasttext text classification algorithm involved in above-mentioned is only a kind of exemplary description,
When actually realizing, it can also identify to obtain emotion sentence using other text classification algorithms, in this regard, not applying not making
It is specific to limit.
After determining emotion sentence, attribute-emotion pair can be extracted from the emotion sentence of acquisition, and determine attribute-feelings
Sense is to affiliated attribute classification.
For example, emotion sentence are as follows: " after breaking through 500 yuan in 14 solar disk of August, small A automobile is not stood firm this share price, hereafter several
Day in oscillating in quotations situation, by August 18th, small A automobile close at 489.65 yuan it is per share ", can be extracted from the emotion sentence
Attribute word is " share price ", and corresponding emotion descriptor is " oscillating in quotations ", then the attribute-emotion pair extracted based on the emotion sentence
For " share price-oscillates in quotations ".
Further, the attribute-emotion can be determined to affiliated attribute classification " market value ".
Specifically, so-called attribute classification can be previously according to the attribute volume of target object more core when realizing
It is preset.For example, for " small A automobile ", may include but be not limited to following attribute classification " comfort ",
" appearance " " history culture ", " market value ", " strategic decision " etc..These all can serve as attribute-emotion word to affiliated category
Property classification.
In one embodiment, it can be based on entire attribute-emotion to affiliated attribute classification is determined, be also possible to
It is based only upon attribute-emotion centering attribute word and determines affiliated attribute classification.
The other characteristic of each Attribute class can be in advance based on and excavate the corresponding attribute word of each attribute classification either category
Property-emotion is to set.It, can be based on attribute word either attribute-emotion to respectively in this way during determining that Attribute class is other
It is matched in the corresponding set of a attribute classification, the highest attribute classification of similarity is selected, as determining attribute classification.
It should be noted, however, that above-mentioned cited determination Attribute class is only a kind of exemplary description otherwise,
It can be realized using other way when practical realization, the application be not construed as limiting this.
Further, it can be determined that attribute or attribute-emotion pair feeling polarities.That is, it is judged that be it is positive, neutral,
Or negative sense.
Such as: " oscillating in quotations " is negative sense, and " comfortable " is positive.
For each attribute-emotion pair, the attribute-emotion can be first extracted to the text words and expressions at place, then basis should
The feeling polarities of words and expressions and the attribute-emotion centering emotion word polarity joint judge the feeling polarities of the attribute, can also be with
It is that attribute-emotion pair polarity is judged to corresponding polarity according to attribute-emotion.Specifically obtaining which kind of judging result can root
It is selected according to actual needs, the application is not construed as limiting this.
For the feeling polarities of words and expressions, can be judged by fasttext text classification algorithm, for the emotion of emotion word
Polarity can be judged by the sentiment dictionary pre-established and manual features etc..
It should be noted, however, that the above-mentioned cited method for judging feeling polarities is only a kind of exemplary description,
When practical realization, it can be judged using other way, the application be not construed as limiting this.
After being handled by the above-mentioned network data to magnanimity, available multiple attribute emotions pair, and determine
Feeling polarities of the attribute emotion to affiliated classification and attribute emotion pair.It, can be to progress attribute classification in feelings based on this
Feel the classification integration of sentence, checks the corresponding public sentiment distribution of target convenient for user.
S4: the Feature Words determined are shown.
In one embodiment, it can be shown according to mode as shown in Figure 2, that is, can be on showing interface
Show the quantity of emotion sentence under each attribute classification of target object, attribute emotion to, feeling polarities of attribute emotion pair etc..
Further, it may also respond to some attribute emotion of user query to request the displaying of corresponding emotion sentence, exhibition
Show that selected attribute emotion, can be with the source web of these emotion sentences of simultaneous display to corresponding emotion sentence, and will be directed to
Attribute emotion to being highlighted so that user can effectively check the source of the attribute emotion pair and corresponding
Multimedia data information.
In one embodiment, it is contemplated that the height of the feeling polarities of attribute emotion pair can also be shown in showing interface
It is low, for example, can either indicate that ratio etc. indicates polarity height, can also indicate emotion by color all attributes in sequence
Polar height is specifically chosen which kind of mode can select according to actual needs, and the application is not construed as limiting this.
For attribute emotion for, some attribute emotions are especially more to the number of appearance, indicate that temperature is relatively high, some
Attribute emotion is fewer to frequency of occurrence, and opposite temperature is with regard to lower.In order to characterize the height of temperature, can by quantity,
Ratio etc. is identified, and can also be identified by the distance apart from core word (that is, target object).Which kind of is specifically chosen
Mode can select according to actual needs, and the application is not construed as limiting this.
In one embodiment, as a result showing can be Templated exhibition method, that is, pre-define display interface
In each display module content type to be shown, and can with action-item, according to this exhibition method predefined into
Row is shown.
In one embodiment, after being shown to result, multiple options can be provided, for example, can mention
For period options, user can choose the period.With selection " within three days ", then this when can only show three
The result that data aggregate in it obtains.I.e., it is possible to receive the period of selection；Show target signature word, wherein target signature
Word is to be located at the multimedia relevant to the target object in the period according in the issuing time in the data source
What data determined.In this way, allow viewer that the data in the period is selected to be shown according to actual needs,
The period for being limited to system setting themselves is not needed, so that more convenient to checking for result, flexibility is higher.
In one embodiment, above-mentioned method for exhibiting data can be applied and is situated between in evaluation website, Science Popularization Websites, product
Continue website etc., handles and shows by the polymerization analysis that public sentiment data may be implemented in above-mentioned processing method.
In this example, show the displaying pattern of result be also it is entirely different, existing is all that have preset displaying special
Word is levied, however, in this example, showing the result is that polymerizeing to obtain Feature Words based on the multi-medium data obtained in real time, that is, displaying
Feature Words are temporarily to polymerize to obtain based on data, rather than preset good, that is, show that result is all derived from instantly
The data of acquisition, be all random.
The method for exhibiting data of upper example can also be applied to the scene of Data Statistics Inquiry Through.For example, the boss of small A automobile is uncommon
The Market Feedback situation recent to small A automobile is hoped to see one understanding of progress, then passing through the above-mentioned data based on public sentiment data
Methods of exhibiting, so that it may see to simple, intuitive the data feedback situation of small A automobile on the internet in certain time.Example
Such as: the evaluation of acceptance of the users, stock-market change, news to it.
It is to obtain relevant multimedia number from multiple data sources after the target object of inquiry has been determined in upper example
According to, and be to determine the Feature Words of target object from these multi-medium datas of acquisition and be shown.Compared to existing
Data are only obtained by a data source, and the Feature Words shown are all that pre-set mode is compared, this example is provided
Protocol source be it is random, the result of displaying be also it is random, large-scale data statistics can be convenient for, by it
It is applied in public sentiment data, may be implemented to effectively integrate utilization to public sentiment data.
Above-mentioned data processing classification method is illustrated below with reference to a concrete scene, it is important to note, however, that
The concrete scene does not constitute an undue limitation on the present application merely to the application is better described.
In this example, it is illustrated with carrying out information extraction and classification displaying to " small A automobile ", specifically, passing through combination
Text classification and information extraction etc. handle " small A automobile " information in internet, extract the small each dimension of A automobile
The Sentiment orientation of user and emotion viewpoint in attribute, and these information are shown by the way of aggregate statistics.
As shown in figure 3, may include following process:
S1: data are grabbed in platforms such as webpage, forum, discussion bar, microbloggings；
S2: in conjunction with text classification algorithm, from a large amount of structureless multi-medium data drilled through, extracting has user's feelings
Feel the emotion sentence of expression；
In view of there is the largely text unrelated with target object (this example are as follows: small A automobile) in web page text, if can be with
The candidate sentences comprising user feeling expression are therefrom excavated, then the workload of subsequent extraction process can be effectively reduced, and
The accuracy of attribute extraction can be provided.In order to realize this purpose, a large amount of texts in web page text can be extracted,
Obtain the emotion sentence with user feeling expression relevant to target object.For example, can be through but not limited to fasttext text
This sorting algorithm, from one identification disaggregated model of the data focusing study manually marked, come determine input text sentence whether
For the emotion sentence with user feeling expression relevant to target object.
In one embodiment, the emotion sentence and subsequent information extraction with user feeling expression will can also be extracted
It is united, forms a unified extraction model.For example, LSTM (Long Short-Term Memory, length can be passed through
Short-term memory network) the emotion score of determining sentence, then CRF is added to using emotion score as the feature of a dimension
In (Conditional Random Field algorithm, condition random field algorithm) attribute extraction model.
S3: the sentiment analysis of property level is carried out to the emotion sentence with user feeling expression of extraction, may include:
A attribute word) is extracted, for example, the attribute word in sentence can be extracted by sequence labelling algorithm；
B it) extracts emotion word to extract, for example, the feelings in sentence can be extracted according to syntactic rule and sequence labelling algorithm
Feel word；
Specifically, attribute word, emotion word can be carried out with the contextual feature of bluebeard compound, part of speech feature, interdependent syntactic feature
Extraction.
Wherein, interdependent syntax is the interdependent pass analysis of sentence being depicted at an interdependent syntax tree between each word
System.That is, indicating that, in syntactical Matching Relation between word, this Matching Relation is associated with semanteme.Example
Such as: the interdependent syntax tree of sentence " meeting announces first batch of senior academician's list " can be as shown in Figure 4.As seen from Figure 4, word
" declaration " domination " meeting ", " " and " list ", therefore, using these words as the Collocation of " declaration ".
Specifically, first extracting the candidate attribute set of words in emotion sentence using CRF algorithm, and it is directed to each attribute word, made
Its candidate emotion set of words is extracted with CRF algorithm, has merged the information such as position, syntax in this process；It is then possible in conjunction with
Interdependent syntactic information extracts artificial rule, extracts attribute-emotion word pair.Finally, attribute-the feelings that will be extracted based on CRF algorithm
Feel to attribute-emotion for being extracted based on interdependent syntax to cross validation is carried out, thus finally determining attribute-emotion pair.
Attribute-emotion pair mode of above-mentioned cited extraction is only a kind of exemplary description, actually realize when
Time can extract attribute-emotion pair in other manners, and it is, for example, possible to use other sequence labelling algorithms, such as: hidden horse
Er Kefu, maximum entropy Markov model etc..Meanwhile the interdependent syntactic feature used in above-mentioned extraction section can also be with not
Same form is presented, such as: interdependent syntax tree is shown as CRF using the vector table that Recognition with Recurrent Neural Network generates dependency tree first
Mode input etc..Concrete implementation form can select according to actual needs, and the application is not construed as limiting this.
C attribute classification) is normalized, is mapped to attribute word in advance in conjunction with automatic excavating dictionary and similarity calculation
A certain attribute classification in the attribute category set of setting.
S3: attribute classification normalizing；
In view of for different industries, attribute classification is typically all different.It therefore, can be according to category of employment
Different or product differences, its corresponding attribute category set is all set for every kind of category of employment in advance.For example, with
Drinks data instance can be set but be not limited to following attribute classification: " comfort ", " appearance ", " history culture ", " market
Value ", " strategic decision " etc..
It, can be by attribute-emotion of extraction to being normalized to a certain specific Attribute class during attribute classification normalizing
Not in.For example, can first according to each attribute dimensions the characteristics of, automatic mining goes out a collection of candidate attribute-emotion to set, so
Afterwards, the average similarity that the attribute-emotion pair excavated is closed with the words pair set in each attribute classification is calculated, by similarity highest
Attribute classification, as the attribute classification of attribute classification normalizing extremely.
D) by text classification algorithm, judge the feeling polarities (such as: positive, neutral, negative sense) of the attribute；
Specifically, being directed to each attribute word, the text words and expressions where the attribute can be extracted, then passes through the feelings of the words and expressions
The polarity joint of emotion word corresponding to sense polarity and the attribute word judges the feeling polarities of the attribute.Wherein, the feelings of sentence
Sense polarity can judge by fasttext text classification algorithm, and the feeling polarities of emotion word can be by the emotion that pre-establishes
Dictionary and manual features (such as: with the presence or absence of negative word etc.) judgement.
S4: divide for the attribute emotion of the structuring of the batch of target object (certain product or certain enterprise) in a period of time
Analysis, available attribute sentiment analysis is as a result, can carry out aggregate statistics for these results.Specifically, can be according to different
Temperature, emotion degree, timeliness etc. are visualized.
It is illustrated in figure 5 a kind of schematic presentation figure that product public sentiment is shown based on statistical result, as shown in figure 5, the 1st
Divide from time dimension, user is supported to select the public sentiment within the scope of different time；Part 2 is directed to different types of consumer goods, shows
Show different attribute systems, shown in Fig. 5 be automobile industry determinant attribute；The extraction of third portion, that is, attribute word emotion word
As a result show, for each attribute classification, the higher N number of attribute-emotion word pair of wherein temperature can be shown, and respectively according to
Different colors shows its feeling polarities, and the statistics heat of the attribute can be characterized by the distance between each word to core word
Degree；User is supported to select different keywords in 4th part；The keyword that 5th part is selected according to user shows relevant news
Former sentence, and highlighted relevant text passage.
It is to be noted, however, that this, which is only that one kind is schematical, shows interface, when actually realizing, can also adopt
Show form with others polymerization, such as: it can be shown according to temperature, the emotion degree of attribute etc. of emotion word, specifically
Exhibition method can select according to actual needs, the application is not construed as limiting this.
In this example, by filtering out the text not comprising emotion information in advance, attribute is carried out based on filtered problem
The extraction of emotion pair and cross validation to improve the performance of attributes extraction, and have determined attribute emotion to corresponding feelings
Feel polarity.It is wider for the range for extracting the covering of obtained result, for example, may include that the public public sentiment to corporate level is believed
Breath, such as: " history culture " of company, " market value " " high-level leader " etc..Displaying for result provides more structure
The exhibition scheme of change shows that interface is more friendly, and content more horn of plenty.
Data processing and display methods embodiment provided by the application is above-mentioned can be in servers, terminal or similar
It is executed in arithmetic unit.For running on the terminal device, Fig. 6 is a kind of end of method for exhibiting data of the embodiment of the present invention
The hardware block diagram of end equipment.As shown in fig. 6, terminal device 10 may include at one or more (only showing one in figure)
(processor 102 can include but is not limited to the processing dress of Micro-processor MCV or programmable logic device FPGA etc. to reason device 102
Set), memory 104 for storing data and the transmission module 106 for communication function.Those of ordinary skill in the art
It is appreciated that structure shown in fig. 6 is only to illustrate, the structure of above-mentioned electronic device is not caused to limit.For example, computer
Terminal 10 may also include than shown in Fig. 6 more perhaps less component or with the configuration different from shown in Fig. 6.
Memory 104 can be used for storing the software program and module of application software, such as the data in the embodiment of the present invention
Corresponding program instruction/the module of methods of exhibiting, processor 102 by the software program that is stored in memory 104 of operation and
Module realizes the method for exhibiting data of above-mentioned application program thereby executing various function application and data processing.Storage
Device 104 may include high speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device,
Flash memory or other non-volatile solid state memories.In some instances, memory 104 can further comprise relative to processing
The remotely located memory of device 102, these remote memories can pass through network connection to terminal 10.Above-mentioned network
Example includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmission module 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of terminal 10 provide.In an example, transmission module 106 includes that a network is suitable
Orchestration (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to
Internet is communicated.In an example, transmission module 106 can be radio frequency (Radio Frequency, RF) module,
For wirelessly being communicated with internet.
Referring to FIG. 7, in Software Implementation, which shows that device is applied in terminal device, may include: the
One determination unit, acquiring unit, the second determination unit and display unit.Wherein:
First determination unit, for determining target object；
Acquiring unit, for obtaining the multi-medium data relevant to the target object from multiple data sources；
Second determination unit, for determining Feature Words relevant to the target object from the multi-medium data；
Display unit, for being shown to the Feature Words determined.
In one embodiment, the Feature Words can include but is not limited at least one of: attribute word, emotion
Word, attribute classification.
In one embodiment, the second determination unit can specifically polymerize from multi-medium data obtains multiple features
The frequency that word and each Feature Words occur；Correspondingly, display unit can specifically go out the Feature Words and Feature Words determined
The existing frequency is shown.
In one embodiment, above-mentioned apparatus can also include: the first receiving unit, for the feature determined
After word is shown, the inquiry request to target signature word is received；Display unit specifically can in response to the inquiry request,
Show multi-medium data relevant to the target signature word.
In one embodiment, above-mentioned apparatus can also include: the second receiving unit, for the feature determined
After word is shown, the period of selection is received；Display unit can specifically show target signature word, wherein the target
Feature Words are relevant to the target object more in the period according to being located in the issuing time in the data source
What media data determined.
In one embodiment, determination unit can specifically be extracted from the multi-medium data to the target object
The emotion sentence with emotional expression being described；Multiple attribute emotion words pair are found out from the emotion sentence；Described in determination
Multiple each attribute emotion words of attribute emotion word centering are to affiliated attribute classification and feeling polarities；According to the multiple attribute feelings
The each attribute emotion word of word centering is felt to affiliated attribute classification and feeling polarities, is carried out polymerization classification, is obtained each Attribute class
Not corresponding emotion sentence quantity and feeling polarities；By each attribute emotion word determined to affiliated attribute classification and emotion pole
Property, the corresponding emotion sentence quantity of each attribute classification and feeling polarities are as the Feature Words.
In one embodiment, determination unit specifically can determine one of in the following way attribute emotion word to affiliated
Attribute classification and feeling polarities:
1) according to the feeling polarities of the emotion word of the attribute emotion word centering, the emotion of the attribute emotion word pair is determined
Polarity；
2) feelings of the attribute emotion word pair are determined to the feeling polarities of the emotion sentence at place according to the attribute emotion word
Feel polarity；
3) according to the feeling polarities of the emotion word of the attribute emotion word centering and the attribute emotion word to the feelings at place
The feeling polarities for feeling sentence, determine the feeling polarities of the attribute emotion word pair.
Specifically, according to the feeling polarities of the emotion word of the attribute emotion word centering and the attribute emotion word to place
Emotion sentence feeling polarities, determine that the feeling polarities of the attribute emotion word pair may include:
S1: the feeling polarities of the emotion word of the attribute emotion word centering are determined；
S2: determine the attribute emotion word to the feeling polarities of the emotion sentence at place；
S3: the feeling polarities of feeling polarities and the emotion sentence determined to determining emotion word carry out cross validation, will hand over
Pitch feeling polarities of the result of verifying as the attribute emotion word pair.
The accuracy rate of feeling polarities identification is improved by way of cross check.
During obtaining multi-medium data, more matchmakers relevant to target object can be obtained from multiple target webpages
Then volume data extracts the emotion sentence with emotional expression that the target object is described from multi-medium data.
In one embodiment, above-mentioned attribute classification can be the preset attribute of characteristic point for target object
Class.
In one embodiment, above-mentioned attribute classification can also include: the attributive classification of target object owned enterprise.
In one embodiment, attribute emotion word is determined to affiliated attribute classification, may include: by the attribute feelings
Sense word pair carries out similarity-rough set to set for the other attribute emotion of each Attribute class with what is excavated in advance；By highest similarity
Corresponding attribute classification is determined as the attribute emotion word to affiliated attribute classification.
In one embodiment, feeling polarities can include but is not limited at least one of: positive emotion, middle disposition
Sense, negative sense emotion.
After the target object of inquiry has been determined, be obtain relevant multi-medium data from multiple data sources, and be from
The Feature Words of target object are determined in these multi-medium datas obtained and are shown.Only pass through one compared to existing
Data source obtains data, and the Feature Words shown are all that pre-set mode is compared, protocol provided by this example
Source be it is random, the result of displaying be also it is random, large-scale data statistics can be convenient for, apply it to public sentiment
In data, it may be implemented to effectively integrate utilization to public sentiment data.
Although this application provides the method operating procedure as described in embodiment or flow chart, based on conventional or noninvasive
The labour for the property made may include more or less operating procedure.The step of enumerating in embodiment sequence is only numerous steps
One of execution sequence mode, does not represent and unique executes sequence.It, can when device or client production in practice executes
To execute or parallel execute (such as at parallel processor or multithreading according to embodiment or method shown in the drawings sequence
The environment of reason).
The device or module that above-described embodiment illustrates can specifically realize by computer chip or entity, or by having
The product of certain function is realized.For convenience of description, it is divided into various modules when description apparatus above with function to describe respectively.
The function of each module can be realized in the same or multiple software and or hardware when implementing the application.It is of course also possible to
Realization the module for realizing certain function is combined by multiple submodule or subelement.
Method, apparatus or module described herein can realize that controller is pressed in a manner of computer readable program code
Any mode appropriate is realized, for example, controller can take such as microprocessor or processor and storage can be by (micro-)
The computer-readable medium of computer readable program code (such as software or firmware) that processor executes, logic gate, switch, specially
With integrated circuit (Application Specific Integrated Circuit, ASIC), programmable logic controller (PLC) and embedding
Enter the form of microcontroller, the example of controller includes but is not limited to following microcontroller: ARC 625D, Atmel AT91SAM,
Microchip PIC18F26K20 and Silicone Labs C8051F320, Memory Controller are also implemented as depositing
A part of the control logic of reservoir.It is also known in the art that in addition to real in a manner of pure computer readable program code
Other than existing controller, completely can by by method and step carry out programming in logic come so that controller with logic gate, switch, dedicated
The form of integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc. realizes identical function.Therefore this controller
It is considered a kind of hardware component, and hardware can also be considered as to the device for realizing various functions that its inside includes
Structure in component.Or even, it can will be considered as the software either implementation method for realizing the device of various functions
Module can be the structure in hardware component again.
Part of module in herein described device can be in the general of computer executable instructions
Upper and lower described in the text, such as program module.Generally, program module includes executing particular task or realization specific abstract data class
The routine of type, programs, objects, component, data structure, class etc..The application can also be practiced in a distributed computing environment,
In these distributed computing environment, by executing task by the connected remote processing devices of communication network.In distribution
It calculates in environment, program module can be located in the local and remote computer storage media including storage equipment.
As seen through the above description of the embodiments, those skilled in the art can be understood that the application can
It is realized by the mode of software plus required hardware.Based on this understanding, the technical solution of the application is substantially in other words
The part that contributes to existing technology can be embodied in the form of software products, and can also pass through the implementation of Data Migration
It embodies in the process.The computer software product can store in storage medium, such as ROM/RAM, magnetic disk, CD, packet
Some instructions are included to use so that a computer equipment (can be personal computer, mobile terminal, server or network are set
It is standby etc.) execute method described in certain parts of each embodiment of the application or embodiment.
Each embodiment in this specification is described in a progressive manner, the same or similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.The whole of the application or
Person part can be used in numerous general or special purpose computing system environments or configuration.Such as: personal computer, server calculate
Machine, handheld device or portable device, mobile communication terminal, multicomputer system, based on microprocessor are at laptop device
System, programmable electronic equipment, network PC, minicomputer, mainframe computer, the distribution including any of the above system or equipment
Formula calculates environment etc..
Although depicting the application by embodiment, it will be appreciated by the skilled addressee that the application there are many deformation and
Variation is without departing from spirit herein, it is desirable to which the attached claims include these deformations and change without departing from the application's
Spirit.
Claims (14)
1. a kind of method for exhibiting data characterized by comprising
Determine target object；
Obtain the multi-medium data relevant to the target object from multiple data sources；
Feature Words relevant to the target object are determined from the multi-medium data；
The Feature Words determined are shown.
2. the method according to claim 1, wherein the Feature Words include at least one of: attribute word, feelings
Feel word, attribute classification.
3. the method according to claim 1, wherein being determined from the multi-medium data and the target pair
As relevant Feature Words, comprising:
Polymerization obtains the frequency that multiple Feature Words and each Feature Words occur from the multi-medium data；
Correspondingly, being shown to the Feature Words determined, comprising:
The frequency occurred to the Feature Words and Feature Words determined is shown.
4. described the method according to claim 1, wherein after being shown to the Feature Words determined
Method further include:
Receive the inquiry request to target signature word；
In response to the inquiry request, multi-medium data relevant to the target signature word is shown.
5. described the method according to claim 1, wherein after being shown to the Feature Words determined
Method further include:
Receive the period of selection；
Show target signature word, wherein the target signature word is according to the issuing time in the data source positioned at described
What the multi-medium data relevant to the target object in the period determined.
6. the method according to claim 1, wherein being determined from the multi-medium data and the target pair
As relevant Feature Words, comprising:
The emotion sentence with emotional expression that the target object is described is extracted from the multi-medium data；
Multiple attribute emotion words pair are found out from the emotion sentence；
Determine each attribute emotion word of the multiple attribute emotion word centering to affiliated attribute classification and feeling polarities；
According to each attribute emotion word of the multiple attribute emotion word centering to affiliated attribute classification and feeling polarities, gathered
Classification is closed, the corresponding emotion sentence quantity of each attribute classification and feeling polarities are obtained；
By each attribute emotion word determined to affiliated attribute classification and feeling polarities, the corresponding emotion of each attribute classification
Sentence quantity and feeling polarities are as the Feature Words.
7. according to the method described in claim 6, it is characterized in that, determining attribute emotion word to affiliated attribute classification and emotion
Polarity, including at least one of:
The feeling polarities of the attribute emotion word pair are determined according to the feeling polarities of the emotion word of the attribute emotion word centering；
According to the attribute emotion word to the feeling polarities of the emotion sentence at place, the emotion pole of the attribute emotion word pair is determined
Property；
According to the feeling polarities of the emotion word of the attribute emotion word centering and the attribute emotion word to the emotion sentence at place
Feeling polarities determine the feeling polarities of the attribute emotion word pair.
8. the method according to the description of claim 7 is characterized in that according to the emotion of the emotion word of the attribute emotion word centering
Polarity and the attribute emotion word determine the feeling polarities of the attribute emotion word pair to the feeling polarities of the emotion sentence at place,
Include:
Determine the feeling polarities of the emotion word of the attribute emotion word centering；
Determine the attribute emotion word to the feeling polarities of the emotion sentence at place；
The feeling polarities of feeling polarities and the emotion sentence determined to determining emotion word carry out cross validation, by cross validation
As a result the feeling polarities as the attribute emotion word pair.
9. according to the method described in claim 6, it is characterized in that, the attribute classification is the characteristic for the target object
Preset attributive classification.
10. according to the method described in claim 9, it is characterized in that, the attribute classification further include: target object owned enterprise
Attributive classification.
11. according to the method described in claim 6, it is characterized in that, determining attribute emotion word to affiliated attribute classification, packet
It includes:
The attribute emotion word pair is subjected to similarity to set for the other attribute emotion of each Attribute class with what is excavated in advance
Compare；
By the corresponding attribute classification of highest similarity, it is determined as the attribute emotion word to affiliated attribute classification.
12. according to the method described in claim 6, it is characterized in that, the feeling polarities include at least one of: positive feelings
Sense, neutral emotion, negative sense emotion.
13. a kind of terminal device, including processor and for the memory of storage processor executable instruction, the processor
The step of realizing any one of claims 1 to 12 the method when executing described instruction.
14. a kind of computer readable storage medium is stored thereon with computer instruction, described instruction, which is performed, realizes that right is wanted
The step of seeking any one of 1 to 12 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711182131.6A CN109829033B (en) | 2017-11-23 | 2017-11-23 | Data display method and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711182131.6A CN109829033B (en) | 2017-11-23 | 2017-11-23 | Data display method and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109829033A true CN109829033A (en) | 2019-05-31 |
| CN109829033B CN109829033B (en) | 2023-04-18 |
Family
ID=66858542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711182131.6A Active CN109829033B (en) | 2017-11-23 | 2017-11-23 | Data display method and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829033B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581479A (en) * | 2020-05-11 | 2020-08-25 | 北京精准沟通传媒科技股份有限公司 | One-stop data processing method and device, storage medium and electronic equipment |
| CN112052375A (en) * | 2020-09-30 | 2020-12-08 | 北京百度网讯科技有限公司 | Public opinion acquisition and word viscosity model training method and device, server and medium |
| CN112580358A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Text information extraction method, device, storage medium and equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033910A (en) * | 2010-11-19 | 2011-04-27 | 福建富士通信息软件有限公司 | Enterprise search engine technology based on multiple data resources |
| CN102073701A (en) * | 2010-12-30 | 2011-05-25 | 浪潮集团山东通用软件有限公司 | Semantic definition-based multi-data source data querying method |
| US20130024465A1 (en) * | 2011-07-20 | 2013-01-24 | Ness Computing, Inc. | Method and apparatus for quickly evaluating entities |
| CN103678564A (en) * | 2013-12-09 | 2014-03-26 | 国家计算机网络与信息安全管理中心 | Internet product research system based on data mining |
| US20140172415A1 (en) * | 2012-12-17 | 2014-06-19 | Electronics And Telecommunications Research Institute | Apparatus, system, and method of providing sentiment analysis result based on text |
| CN105354183A (en) * | 2015-10-19 | 2016-02-24 | Tcl集团股份有限公司 | Analytic method, apparatus and system for internet comments of household electrical appliance products |
| CN105574176A (en) * | 2015-12-21 | 2016-05-11 | 北京奇虎科技有限公司 | Hot word recommending method and device with combination of multiple data sources |
| CN105824898A (en) * | 2016-03-14 | 2016-08-03 | 苏州大学 | Label extracting method and device for network comments |
| CN106599065A (en) * | 2016-11-16 | 2017-04-26 | 北京化工大学 | Food safety online public opinion early warning system based on Storm distributed framework |
-
2017
- 2017-11-23 CN CN201711182131.6A patent/CN109829033B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033910A (en) * | 2010-11-19 | 2011-04-27 | 福建富士通信息软件有限公司 | Enterprise search engine technology based on multiple data resources |
| CN102073701A (en) * | 2010-12-30 | 2011-05-25 | 浪潮集团山东通用软件有限公司 | Semantic definition-based multi-data source data querying method |
| US20130024465A1 (en) * | 2011-07-20 | 2013-01-24 | Ness Computing, Inc. | Method and apparatus for quickly evaluating entities |
| US20140172415A1 (en) * | 2012-12-17 | 2014-06-19 | Electronics And Telecommunications Research Institute | Apparatus, system, and method of providing sentiment analysis result based on text |
| CN103678564A (en) * | 2013-12-09 | 2014-03-26 | 国家计算机网络与信息安全管理中心 | Internet product research system based on data mining |
| CN105354183A (en) * | 2015-10-19 | 2016-02-24 | Tcl集团股份有限公司 | Analytic method, apparatus and system for internet comments of household electrical appliance products |
| CN105574176A (en) * | 2015-12-21 | 2016-05-11 | 北京奇虎科技有限公司 | Hot word recommending method and device with combination of multiple data sources |
| CN105824898A (en) * | 2016-03-14 | 2016-08-03 | 苏州大学 | Label extracting method and device for network comments |
| CN106599065A (en) * | 2016-11-16 | 2017-04-26 | 北京化工大学 | Food safety online public opinion early warning system based on Storm distributed framework |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580358A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Text information extraction method, device, storage medium and equipment |
| WO2021063060A1 (en) * | 2019-09-30 | 2021-04-08 | 北京国双科技有限公司 | Text information extraction method and apparatus, storage medium and device |
| CN111581479A (en) * | 2020-05-11 | 2020-08-25 | 北京精准沟通传媒科技股份有限公司 | One-stop data processing method and device, storage medium and electronic equipment |
| CN112052375A (en) * | 2020-09-30 | 2020-12-08 | 北京百度网讯科技有限公司 | Public opinion acquisition and word viscosity model training method and device, server and medium |
| KR20220044074A (en) * | 2020-09-30 | 2022-04-06 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Public opinion acquisition and word viscosity model training methods and devices, server, and medium |
| EP3979126A1 (en) * | 2020-09-30 | 2022-04-06 | Beijing Baidu Netcom Science And Technology Co. Ltd. | Public opinion acquisition and word viscosity model training methods and devices, server, and medium |
| US11610401B2 (en) | 2020-09-30 | 2023-03-21 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Acquiring public opinion and training word viscosity model |
| KR102527589B1 (en) * | 2020-09-30 | 2023-04-28 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Public opinion acquisition and word viscosity model training methods and devices, server, and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829033B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10762299B1 (en) | Conversational understanding | |
| WO2021139701A1 (en) | Application recommendation method and apparatus, storage medium and electronic device | |
| US20170368683A1 (en) | User portrait based skill package recommendation device and method | |
| JP6894534B2 (en) | Information processing method and terminal, computer storage medium | |
| US20190258722A1 (en) | Personalized deep models for smart suggestions ranking | |
| CN104636371B (en) | Information recommendation method and equipment | |
| JP6404106B2 (en) | Computing device and method for connecting people based on content and relationship distance | |
| US20150286943A1 (en) | Decision Making and Planning/Prediction System for Human Intention Resolution | |
| CN113590776B (en) | Knowledge graph-based text processing method and device, electronic equipment and medium | |
| CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
| CN109903127A (en) | A kind of group recommending method, device, storage medium and server | |
| CN108268450B (en) | Method and apparatus for generating information | |
| CN110287313A (en) | A kind of the determination method and server of risk subject | |
| CN107436916B (en) | Intelligent answer prompting method and device | |
| US10375005B2 (en) | Dynamic hashtag ordering based on projected interest | |
| CN111177462B (en) | Video distribution timeliness determination method and device | |
| CN111339406B (en) | Personalized recommendation method, device, equipment and storage medium | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| CN109829033A (en) | Method for exhibiting data and terminal device | |
| CN112417121A (en) | Client intention recognition method and device, computer equipment and storage medium | |
| CN109190116A (en) | Semantic analytic method, system, electronic equipment and storage medium | |
| CN111651989A (en) | Named entity recognition method and device, storage medium and electronic device | |
| CN116910201A (en) | Dialogue data generation method and related equipment thereof | |
| CN114461749B (en) | Data processing method and device for conversation content, electronic equipment and medium | |
| JP2023554210A (en) | Sort model training method and apparatus for intelligent recommendation, intelligent recommendation method and apparatus, electronic equipment, storage medium, and computer program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |