CN106126623A - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN106126623A CN106126623A CN201610458719.9A CN201610458719A CN106126623A CN 106126623 A CN106126623 A CN 106126623A CN 201610458719 A CN201610458719 A CN 201610458719A CN 106126623 A CN106126623 A CN 106126623A
- Authority
- CN
- China
- Prior art keywords
- product
- url
- user
- evaluation information
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention provides a kind of information processing method and device, by obtaining the evaluation information of each attribute to product that user issues in the network platform, and determines the function information of product according to evaluation information.The information processing method of present invention offer and device, it is possible to determine the function information of product from user at the evaluation information to product that the network platform is issued, improve the efficiency of information processing.
Description
Technical field
The present invention relates to computer technology, particularly relate to a kind of information processing method and device.
Background technology
Product producer is in order to improve the quality of product, it usually needs commenting of each attribute to product of understanding user feedback
Valency information, determines each function information of product, to refer to according to each function information according to the evaluation information of user's attribute each to product
The improvement direction of artificial deliviery product.
In prior art, product producer obtains user to product by modes such as questionnaire survey and customer representative's communications
The evaluation information of each attribute, determines each function information of product according to the evaluation information of user's attribute each to product.
The method using prior art, information processing inefficient.
Summary of the invention
The present invention provides a kind of information processing method and device, improves the efficiency of information processing.
The present invention provides a kind of information processing method, including:
Obtain the evaluation information of each attribute to product that user issues in the network platform；
According to described evaluation information, determine the function information of product.
In an embodiment of the present invention, the described evaluation letter obtaining each attribute to product that user issues in the network platform
Breath, including:
By the evaluation information of each attribute to product that web crawlers technical limit spacing user issues in the network platform.
In an embodiment of the present invention, described by web crawlers technical limit spacing user the network platform issue to product
The evaluation information of each attribute, including:
Crawl the uniform resource position mark URL that the described network platform is corresponding；
Load webpage corresponding to described URL, obtain the described netpage user evaluation information to each attribute of product.
In an embodiment of the present invention, described in crawl the URL that the described network platform is corresponding, including:
Crawl the URL of all of webpage that user accesses in preset time period；
Filter out, from the URL of described all of webpage, the URL that the described network platform is corresponding.
In an embodiment of the present invention, described by web crawlers technical limit spacing user the network platform issue to product
The evaluation information of each attribute, including:
Crawl the URL that the described network platform is corresponding；
Resolve the scripted code in described URL；
Load described URL and described scripted code, obtain the described netpage user evaluation information to each attribute of product.
In an embodiment of the present invention, the described netpage user of described acquisition to the evaluation information of each attribute of product it
Before, also include:
Described URL is carried out deduplication process.
In an embodiment of the present invention, the described evaluation letter obtaining each attribute to product that user issues in the network platform
Breath, including:
According to emotion dictionary, obtain the evaluation information of each attribute to product that user issues in the network platform.
In an embodiment of the present invention, described according to emotion dictionary, obtain user the network platform issue to product
Before the evaluation information of each attribute, also include:
By the vocabulary use habit of user, set up described emotion dictionary.
In the above embodiment of the present invention, described determine the function information of product according to described evaluation information, including:
By neural metwork training model, described evaluation information is processed, determine the function information of product.
The present invention provides a kind of information processor, including:
Acquisition module, for obtaining the evaluation information of each attribute to product that user issues in the network platform；
Processing module, for according to described evaluation information, determines the function information of product.
In an embodiment of the present invention, acquisition module specifically for by web crawlers technical limit spacing user in the network platform
The evaluation information of each attribute to product issued.
In an embodiment of the present invention, acquisition module is stated fixed specifically for crawling unified resource corresponding to the described network platform
Position symbol URL；Load webpage corresponding to described URL, obtain the described netpage user evaluation information to each attribute of product.
In an embodiment of the present invention, acquisition module is all of specifically for crawl that user accesses in preset time period
The URL of webpage；Filter out, from the URL of described all of webpage, the URL that the described network platform is corresponding
In an embodiment of the present invention, the URL that acquisition module is corresponding specifically for crawling the described network platform；Resolve described
Scripted code in URL；Load described URL and described scripted code, obtain described netpage user to each attribute of product
Evaluation information.
In an embodiment of the present invention, acquisition module is additionally operable to described URL is carried out deduplication process.
In an embodiment of the present invention, acquisition module, specifically for according to emotion dictionary, obtains user and sends out in the network platform
The evaluation information of each attribute to product of cloth.
In an embodiment of the present invention, described acquisition module is additionally operable to the vocabulary use habit by user, sets up described
Emotion dictionary.
In the above embodiment of the present invention, described processing module specifically for by neural metwork training model to institute's commentary
Valency information processes, and determines the function information of product.
The present invention provides a kind of information processing method and device, by obtain user the network platform issue to product
The evaluation information of each attribute, and the function information of product is determined according to evaluation information.The present invention provide information processing method and
Device, it is possible to determine the function information of product from user at the evaluation information to product that the network platform is issued, improve information
The efficiency processed.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, also may be used
To obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of information processing method embodiment one of the present invention；
Fig. 2 is the schematic flow sheet of information processing method embodiment two of the present invention；
Fig. 3 is the schematic flow sheet of information processing method embodiment three of the present invention；
Fig. 4 is the structural representation of inventive network crawler system embodiment one；
Fig. 5 is the schematic flow sheet of inventive network crawler system embodiment one；
Fig. 6 is user's value models schematic diagram of the present invention；
Fig. 7 is that user's value models of the present invention sets up process schematic；
Fig. 8 is the attribute layer of the present invention mapping schematic diagram to destination layer；
Fig. 9 is the structural representation of information processor embodiment one of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, broadly falls into the scope of protection of the invention.
Term " first " in description and claims of this specification and above-mentioned accompanying drawing, " second ", " the 3rd " "
Four " etc. (if present) is for distinguishing similar object, without being used for describing specific order or precedence.Should manage
Solve the data so used can exchange in the appropriate case, in order to embodiments of the invention described herein such as can be to remove
Order beyond those that here illustrate or describe is implemented.Additionally, term " includes " and " having " and theirs is any
Deformation, it is intended that cover non-exclusive comprising, such as, contain series of steps or the process of unit, method, system, product
Product or equipment are not necessarily limited to those steps or the unit clearly listed, but can include the most clearly listing or for this
Other step that a little processes, method, product or equipment are intrinsic or unit.
Fig. 1 is the schematic flow sheet of information processing method embodiment one of the present invention.As it is shown in figure 1, at the present embodiment information
Reason method comprises the following steps:
S101: obtain the evaluation information of each attribute to product that user issues in the network platform.
Wherein, the attribute of product is user's demand to properties of product.Such as: the attribute of product may include that product electricity
The use time in pond, the degree of reliability of the shell of product, signal power during product call etc..The network platform can be micro-
The users such as rich, forum can issue the website of original information.
Obtaining a kind of possible implementation of evaluation information is, with name of product as keyword, user in the network platform
The information delivered is searched for this keyword, extracts wherein user's evaluation information to the attribute of product.
The implementation obtaining evaluation information alternatively possible is, user uses certain product to issue the evaluation for this product
Information, then this product obtains this evaluation information when user issues evaluation information.
S102: according to evaluation information, determine the function information of product.
Wherein, according to the evaluation information obtained in S101, the function information of product is determined.Function information is product design people
Member is based on user's evaluation information to the attribute of product, the feature of the product considered in design.
The present embodiment, by obtaining the evaluation information of each attribute to product that user issues in the network platform, and according to
Evaluation information determines the function information of product, it is possible to the evaluation information to product issued in the network platform from user determines product
Function information, improve the efficiency of information processing.
Fig. 2 is the schematic flow sheet of information processing method embodiment two of the present invention.As in figure 2 it is shown, at the present embodiment information
Reason method comprises the following steps:
S201: by the evaluation letter of each attribute to product that web crawlers technical limit spacing user issues in the network platform
Breath.
Wherein, web crawlers, from the beginning of some page of website, reads content of pages, and along the chain ground connection in the page
Location accesses other webpages and reads web page contents, until the content of all webpages obtained on website.
S202: according to evaluation information, determine the function information of product.
The detailed description of this step sees step S102, and here is omitted.
The present embodiment, by the evaluation of each attribute to product that web crawlers technical limit spacing user issues in the network platform
Information, and the function information of product is determined according to evaluation information, it is possible to the evaluation to product issued in the network platform from user
Information determines the function information of product, improves the efficiency of information processing.
Further, in the above-described embodiments, by web crawlers technical limit spacing user the network platform issue to product
The evaluation information of each attribute of product, including: crawl the network platform corresponding URL (Uniform Resource
Locator, is called for short: URL)；Load webpage corresponding to URL, obtain netpage user's evaluation information to each attribute of product.
Specifically, the net that the web crawlers provided in the present embodiment is corresponding with loading URL by crawling URL in the course of the work
Two processes of page are separated, and become two independent processes.First, crawling URL process from the beginning of an initial URL, circulation is climbed
Take the URL meeting specific format in webpage, and set up URL resources bank, the URL crawled is put in URL resources bank.Subsequently
Load webpage, when loading webpage, only load the webpage corresponding for URL in URL resources bank.
Alternatively, the crawling strategy and can be configured by user of the web crawlers of the present embodiment.User configured mode is permissible
Including, such as: user specifies and browses entertainment sites or news website, then, when crawling URL, only crawl entertainment sites and news website
URL；Or according to user at ordinary times browse custom, user often browses stock website, then the scope automatically crawled by URL is arranged
For only crawling the URL of stock website.Crawl strategy by user configured URL, during instructing URL to crawl, filter invalid chain
Connect and the URL meeting URL and crawling strategy is preserved to URL resources bank, thus the URL forming personalization crawls.
Alternatively, user can also arrange the scope that URL crawls.Such as, web crawlers can be for the URL of whole Wap
Carry out crawling, carry out crawling or crawling for the URL meeting ad hoc structure for the URL of targeted sites.
Further, in the above-described embodiments, the URL crawling the network platform corresponding includes: crawl user at Preset Time
The URL of all of webpage accessed in section；The URL that the network platform is corresponding is filtered out from the URL of all of webpage.
In the present embodiment, first crawl the URL of all webpages that user accesses in Preset Time, and crawl all
URL is stored within URL resources bank.The URL corresponding in order to obtain the network platform, then filter out network in URL resources bank and put down
The URL that platform is corresponding.
The present embodiment, crawls, by web crawlers technology, the URL that the network platform is corresponding, by web crawlers work process
URL crawls and loads two processes of webpage and separates, and improves the work efficiency of web crawlers；And it is corresponding by the network platform
URL obtains the evaluation information of each attribute to product that user issues in the network platform, determines the merit of product according to evaluation information
Energy information, it is possible to determine the function information of product from user at the evaluation information to product that the network platform is issued, improve letter
The efficiency that breath processes.
Fig. 3 is the schematic flow sheet of information processing method embodiment three of the present invention.As it is shown on figure 3, at the present embodiment information
Web crawlers in reason method supports the collection of dynamic page data, and the present embodiment information processing method comprises the following steps:
S301: crawl the URL that the described network platform is corresponding.
Wherein, crawling URL process from the beginning of an initial URL, circulation is crawled URL corresponding to the network platform in webpage.
S302: resolve the scripted code in described URL.
Alternatively, when the embodiment of the present invention is applied on mobile phone, use the browser that mobile phone rendering engine realizes as being
System core, during crawling URL, browser cooperates with content for script, loads HTML (HyperText
Markup Language, is called for short: HTML) webpage resolve scripted code, extracts dynamic page data when running, write this
In ground static html file, it is achieved the collection of dynamic page data.
S303: load URL and scripted code, obtains netpage user's evaluation information to each attribute of product.
Alternatively, when the embodiment of the present invention is applied on mobile phone, when browser and content for script cooperate, load
URL and corresponding scripted code, thus extract paged content by scripted code, obtain dynamic page data.And by dynamically
The data acquisition netpage user in the page evaluation information to each attribute of product.
S304: according to described evaluation information, determine the function information of product.
The detailed description of this step sees step S102, and here is omitted.
Alternatively, Fig. 4 is the structural representation of inventive network crawler system embodiment one.As shown in Figure 4, present invention letter
The network crawler system of breath processing method includes: mobile phone browser, URL crawl module, URL resources bank, script generation module, turn over
Page script and the data being stored on user local terminal (are called for short: Cookie) management.Network crawler system is browsed by mobile phone
Device accesses wireless application communication protocol, and (Wireless Application Protocol is called for short: Wap) website, to obtain Wap
On information source.Network crawler system is presented to cellie by Application Program Interface.Wherein, mobile phone browser accesses
URL, loads, resolves and renders webpage, performs the page turning script of this structure of web page corresponding, obtains paged content.URL crawls module
It is used for extracting the URL realizing redirecting in the model of dynamic page website between the different pages.URL crawls module according to certain character
Cascade filter rule crawls the URL mating specific format in webpage.Alternatively, URL crawls module and uses range in extraction process
Preferential searching method, carries out the search of next level after completing the search of current level, when the URL crawled arrives some
Rear stopping extracts.URL resources bank is a text, is used for storing URL and crawls the URL that module crawls.Script generates mould
Block passes through user's mark on web page contents and relevant parameter is arranged, and script generation module automatically generates for a certain sample
The page turning script file of the page.Page turning script is one section of scripted code, is a unique file preserved with script format, this section
Code performs in mobile phone browser, is used for location in webpage and clicks on element and simulate clicking operation, thus realizes page turning
Effect.The management work of Cookie is responsible in Cookie management, mainly includes the reading of Cookie, preservation and clear operation.
Alternatively, Fig. 5 is the schematic flow sheet of inventive network crawler system embodiment one.As it is shown in figure 5, employing mobile phone
The browser that rendering engine realizes is as the system core, and after flow process starts, mobile phone browser extracts in the page of initial URL
Hold, in the local static html file of write, and from initial URL, crawl URL and add URL resources bank, performing subsequently to crawl
To URL on page turning scripted code carry out page turning, then decide whether to obtain on this URL crawled to last page
Face, if it is not, then mobile phone browser continues to crawl URL；The most then return URL resources bank.Afterwards, it is judged that whether URL has crawled,
The most then terminate URL to crawl；If it is not, return mobile phone browser, continue the URL in initial URL is crawled.
The present embodiment, crawls, by web crawlers technology, the URL that the network platform is corresponding, by web crawlers work process
URL crawls and loads two processes of webpage and separates, and utilizes this web crawlers to gather dynamic page, improves web crawlers
Work efficiency；And the evaluation of each attribute to product that user issues is obtained in the network platform by the URL that the network platform is corresponding
Information, determines the function information of product according to evaluation information, it is possible to the evaluation to product issued in the network platform from user is believed
Breath determines the function information of product, improves the efficiency of information processing.
Further, in the above-described embodiments, before acquisition netpage user is to the evaluation information of each attribute of product, also
Including: URL is carried out deduplication process.
Wherein, URL carries out deduplication process include: complete the screening to URL duplicate contents and delete the URL of repetition.
Screen the ad content in URL and delete this URL.
The present embodiment, crawls, by web crawlers technology, the URL that the network platform is corresponding, to duplicate contents in URL and advertisement
Content is screened and is deleted, and completes the cleaning to URL, and duplicate contents and ad content are carried out by the present invention in URL aspect
Process, improve the efficiency that duplicate contents and ad content are processed；And existed by the URL acquisition user that the network platform is corresponding
The evaluation information of each attribute to product that the network platform is issued, determines the function information of product according to evaluation information, it is possible to from
User determines the function information of product at the evaluation information to product that the network platform is issued, and improves the efficiency of information processing.
Further, in the above-described embodiments, the evaluation of each attribute to product that user issues is obtained in the network platform
Information, including: according to emotion dictionary, obtain the evaluation information of each attribute to product that user issues in the network platform.
Wherein, emotion dictionary is the vocabulary that can represent emotion.Such as, user's commenting at network platform release product attribute
Valency information is: " battery is useful ".Then " handy " is the vocabulary that user expresses affirmative.
A kind of possible embodiment is that emotion dictionary sets in advance, for representing certainly, negating and the word of neutral emotion
Remittance can be divided into: vocabulary, negative vocabulary and neutral vocabulary certainly.When getting product attribute that user issues in the network platform
Evaluation information time, according to emotion dictionary judge user's evaluation information to attribute represents the vocabulary of emotion be certainly vocabulary,
Negative vocabulary or neutral vocabulary.
Further, in the above-described embodiments, according to emotion dictionary obtain user the network platform issue to product
Before the evaluation information of each attribute, also include: by the vocabulary use habit of user, set up emotion dictionary.
A kind of possible embodiment is, according to the vocabulary use habit of user, by weighting and the method for statistics, obtains
Emotion expressed when user uses corresponding vocabulary, and corresponding vocabulary is added emotion dictionary.Such as, user is used for multiple times
" point is praised " word is expressed certainly, then this vocabulary adds emotion dictionary and is used for representing certainly, put down at network when getting user
Platform issue product attribute evaluation information for " praising to battery point " time, judge the feelings expressed by user by " point is praised " word
Sense is for certainly.
Further, in the various embodiments described above, determine that according to evaluation information the function information of product includes: by nerve
Evaluation information is processed by network training model, determines the function information of product.
A kind of possible implementation is to set up user's value models, and Fig. 6 is user's value models schematic diagram of the present invention.
As shown in Figure 6, user's value models includes: attribute layer, conclusion layer and destination layer.Wherein, attribute layer is evaluation information, destination layer
For function information.Specifically, attribute layer includes the evaluation coming from the attribute each to product that user issues in the network platform
Information, obtains quantized values through pretreatment and sentiment analysis；Conclusion layer is more to describe use according to what each attribute of product was chosen
The family abstract level another characteristic to product performance demands；Destination layer is the functional character that product design personnel consider in design.
Alternatively, Fig. 7 is that user's value models of the present invention sets up process schematic, as it is shown in fig. 7, user's value models is built
Vertical process includes: model, input data, processes data, model, export data.Wherein, model is according to concrete product
Product it is defined customer value model, for the attribute defined in model, extract each to product of user from the network platform
The evaluation information of attribute is used for setting up sample.Input data are user's the commenting each attribute of product extracted from the network platform
Valency information, contains the attribute in defined model in these evaluation informations.Process data to include evaluation information is gone
Repeat, go the operations such as advertisement.It is modeled as setting up attribute layer to the modeling of destination layer, alternatively, uses based on MAPReduce thought
Back propagation (Back Propagation, be called for short: BP) neural network algorithm.Output data, by the model established, make
With statistical information, user's value of product is calculated.
Alternatively, the one or more attributes in conclusion layer may be had an impact by actual attribute layer, and conclusion layer may
One or more attributes in destination layer can be had an impact, a kind of possible realization that these incidence relations are simplified by table 1
Mode:
Table 1
Alternatively, by neural metwork training model, evaluation information is processed, determines that the function information of product includes:
The neural network model that is mapping through of product attribute layer to destination layer is realized.Fig. 8 is attribute layer reflecting to destination layer of the present invention
Penetrate schematic diagram, as shown in Figure 8, computation model is defined as a BP neutral net, by user's evaluation to each attribute of product
Information, as input, utilizes neural metwork training model, and then the output of the function information of calculating product, thus obtains in target
User's evaluation to product on layer.Wherein, the flow process of BP neutral net is, first initializes and carries out forward-propagating and error subsequently
Calculate, and whether error in judgement is less than fixed value, the most then flow process terminates；If it is not, then back propagation and repeat forward-propagating and
Error Calculation, until error terminates less than fixed value flow process.
The information processing method that the present embodiment provides, it is possible to the evaluation information to product issued in the network platform from user
Determine the function information of product, improve the efficiency of information processing.
Fig. 9 is the structural representation of information processor embodiment one of the present invention, and the device of the present embodiment includes: obtain mould
Block 901 and processing module 902, wherein acquisition module 901 is for obtaining each attribute to product that user issues in the network platform
Evaluation information, processing module 902, for according to described evaluation information, determines the function information of product.
The device of the present embodiment can be used for performing the technical scheme of embodiment of the method shown in Fig. 1 accordingly, and it realizes principle
Similar with technique effect, here is omitted.
In the above-described embodiments, acquisition module 901 specifically for by web crawlers technical limit spacing user in the network platform
The evaluation information of each attribute to product issued
The device of the present embodiment can be used for performing the technical scheme of embodiment of the method shown in Fig. 2 accordingly, and it realizes principle
Similar with technique effect, here is omitted.
In the above-described embodiments, the URL that acquisition module 901 is corresponding specifically for crawling the network platform；Load URL corresponding
Webpage, obtains netpage user's evaluation information to each attribute of product.
In the above-described embodiments, acquisition module 901 is all of specifically for crawl that user accesses in preset time period
The URL of webpage；Filter out, from the URL of described all of webpage, the URL that the described network platform is corresponding.
In the above-described embodiments, the URL that acquisition module 901 is corresponding specifically for crawling the network platform；Resolve the foot in URL
This code；Load URL and scripted code, obtain netpage user's evaluation information to each attribute of product.
The device of the present embodiment can be used for performing the technical scheme of embodiment of the method shown in Fig. 3 accordingly, and it realizes principle
Similar with technique effect, here is omitted.
In the above-described embodiments, acquisition module 901 is additionally operable to described URL is carried out deduplication process.
In the above-described embodiments, acquisition module 901, specifically for according to emotion dictionary, obtains user and issues in the network platform
The evaluation information of each attribute to product.
In the above-described embodiments, according to emotion dictionary, described acquisition module is additionally operable to the vocabulary use habit by user,
Set up described emotion dictionary.
In the various embodiments described above, processing module 902 is specifically for evaluating letter by neural metwork training model to described
Breath processes, and determines the function information of product.
The device of the present embodiment can be used for performing the technical scheme of embodiment of the method shown in Fig. 6-Fig. 8 accordingly, and it realizes
Principle is similar with technique effect, and here is omitted.
One of ordinary skill in the art will appreciate that: all or part of step realizing above-mentioned each method embodiment can be led to
The hardware crossing programmed instruction relevant completes.Aforesaid program can be stored in a computer read/write memory medium.This journey
Sequence upon execution, performs to include the step of above-mentioned each method embodiment；And aforesaid storage medium includes: ROM, RAM, magnetic disc or
The various media that can store program code such as person's CD.
Last it is noted that various embodiments above is only in order to illustrate technical scheme, it is not intended to limit；To the greatest extent
The present invention has been described in detail by pipe with reference to foregoing embodiments, it will be understood by those within the art that: it depends on
So the technical scheme described in foregoing embodiments can be modified, or the most some or all of technical characteristic is entered
Row equivalent；And these amendments or replacement, do not make the essence of appropriate technical solution depart from various embodiments of the present invention technology
The scope of scheme.
Claims (18)
1. an information processing method, it is characterised in that including:
Obtain the evaluation information of each attribute to product that user issues in the network platform；
According to described evaluation information, determine the function information of product.
Method the most according to claim 1, it is characterised in that described acquisition user the network platform issue to product
The evaluation information of each attribute, including:
By the evaluation information of each attribute to product that web crawlers technical limit spacing user issues in the network platform.
Method the most according to claim 2, it is characterised in that described flat at network by web crawlers technical limit spacing user
The evaluation information of each attribute to product that platform is issued, including:
Crawl the uniform resource position mark URL that the described network platform is corresponding；
Load webpage corresponding to described URL, obtain the described netpage user evaluation information to each attribute of product.
Method the most according to claim 3, it is characterised in that described in crawl the URL that the described network platform is corresponding, including:
Crawl the URL of all of webpage that user accesses in preset time period；
Filter out, from the URL of described all of webpage, the URL that the described network platform is corresponding.
Method the most according to claim 2, it is characterised in that described flat at network by web crawlers technical limit spacing user
The evaluation information of each attribute to product that platform is issued, including:
Crawl the URL that the described network platform is corresponding；
Resolve the scripted code in described URL；
Load described URL and described scripted code, obtain the described netpage user evaluation information to each attribute of product.
6. according to the method described in any one of claim 3～5, it is characterised in that the described netpage user of described acquisition is to product
Before the evaluation information of each attribute of product, also include:
Described URL is carried out deduplication process.
Method the most according to claim 1, it is characterised in that described acquisition user the network platform issue to product
The evaluation information of each attribute, including:
According to emotion dictionary, obtain the evaluation information of each attribute to product that user issues in the network platform.
Method the most according to claim 7, it is characterised in that described according to emotion dictionary, obtains user in the network platform
Issue to the evaluation information of each attribute of product before, also include:
By the vocabulary use habit of user, set up described emotion dictionary.
9. according to method described in any one of Claims 1 to 5,7～8, it is characterised in that described according to described evaluation information,
Determine the function information of product, including:
By neural metwork training model, described evaluation information is processed, determine the function information of product.
10. an information processor, it is characterised in that including:
Acquisition module, for obtaining the evaluation information of each attribute to product that user issues in the network platform；
Processing module, for according to described evaluation information, determines the function information of product.
11. devices according to claim 10, it is characterised in that described acquisition module is specifically for by web crawlers skill
Art obtains the evaluation information of each attribute to product that user issues in the network platform.
12. devices according to claim 11, it is characterised in that described acquisition module is put down specifically for crawling described network
The uniform resource position mark URL that platform is corresponding；Load webpage corresponding to described URL, obtain each to product of described netpage user
The evaluation information of attribute.
13. devices according to claim 12, it is characterised in that described acquisition module is being preset specifically for crawling user
The URL of all of webpage accessed in the time period；The described network platform is filtered out corresponding from the URL of described all of webpage
URL。
14. devices according to claim 11, it is characterised in that described acquisition module is put down specifically for crawling described network
The URL that platform is corresponding；Resolve the scripted code in described URL；Load described URL and described scripted code, obtain in described webpage
User's evaluation information to each attribute of product.
15. according to the device described in any one of claim 12～14, it is characterised in that described acquisition module is additionally operable to described
URL carries out deduplication process.
16. devices according to claim 10, it is characterised in that described acquisition module specifically for according to emotion dictionary,
Obtain the evaluation information of each attribute to product that user issues in the network platform.
17. devices according to claim 16, it is characterised in that the vocabulary that described acquisition module is additionally operable to by user makes
By custom, set up described emotion dictionary.
18. according to the device described in any one of claim 10～14,16～17, it is characterised in that described processing module is concrete
For described evaluation information being processed by neural metwork training model, determine the function information of product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610458719.9A CN106126623A (en) | 2016-06-23 | 2016-06-23 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610458719.9A CN106126623A (en) | 2016-06-23 | 2016-06-23 | Information processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106126623A true CN106126623A (en) | 2016-11-16 |
Family
ID=57267934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610458719.9A Pending CN106126623A (en) | 2016-06-23 | 2016-06-23 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106126623A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107580036A (en) * | 2017-08-28 | 2018-01-12 | 成都融微软件服务有限公司 | The method of the adaptive single-point acquiring of industry information service |
| CN108121751A (en) * | 2016-11-30 | 2018-06-05 | 北京国双科技有限公司 | The method and apparatus of web page crawl |
| CN108460167A (en) * | 2018-05-10 | 2018-08-28 | 东莞市波动赢机器人科技有限公司 | Transaction machine people's finance data preparation method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1410932A (en) * | 2001-09-26 | 2003-04-16 | 日本电气株式会社 | Apparatus exchange system, apparatus exchange method and apparatus performance evaluating assembly |
| CN103116619A (en) * | 2013-01-29 | 2013-05-22 | 华为技术有限公司 | Collaboration business intelligence implementation method and device |
| CN103338219A (en) * | 2013-05-15 | 2013-10-02 | 北京奇虎科技有限公司 | Terminal device performance evaluation information acquisition and processing method, and corresponding device and processing system thereof |
| US20150331856A1 (en) * | 2014-04-30 | 2015-11-19 | Cie Digital Labs, LLC | Time-based content aggregator |
| US20160055555A1 (en) * | 2014-08-21 | 2016-02-25 | Credibility Corp. | Contextual and Holistic Credibility |
| US20160070709A1 (en) * | 2014-09-09 | 2016-03-10 | Stc.Unm | Online review assessment using multiple sources |
| CN105516762A (en) * | 2014-09-24 | 2016-04-20 | Tcl集团股份有限公司 | Function distribution method and apparatus for module television |
-
2016
- 2016-06-23 CN CN201610458719.9A patent/CN106126623A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1410932A (en) * | 2001-09-26 | 2003-04-16 | 日本电气株式会社 | Apparatus exchange system, apparatus exchange method and apparatus performance evaluating assembly |
| CN103116619A (en) * | 2013-01-29 | 2013-05-22 | 华为技术有限公司 | Collaboration business intelligence implementation method and device |
| CN103338219A (en) * | 2013-05-15 | 2013-10-02 | 北京奇虎科技有限公司 | Terminal device performance evaluation information acquisition and processing method, and corresponding device and processing system thereof |
| US20150331856A1 (en) * | 2014-04-30 | 2015-11-19 | Cie Digital Labs, LLC | Time-based content aggregator |
| US20160055555A1 (en) * | 2014-08-21 | 2016-02-25 | Credibility Corp. | Contextual and Holistic Credibility |
| US20160070709A1 (en) * | 2014-09-09 | 2016-03-10 | Stc.Unm | Online review assessment using multiple sources |
| CN105516762A (en) * | 2014-09-24 | 2016-04-20 | Tcl集团股份有限公司 | Function distribution method and apparatus for module television |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121751A (en) * | 2016-11-30 | 2018-06-05 | 北京国双科技有限公司 | The method and apparatus of web page crawl |
| CN107580036A (en) * | 2017-08-28 | 2018-01-12 | 成都融微软件服务有限公司 | The method of the adaptive single-point acquiring of industry information service |
| CN108460167A (en) * | 2018-05-10 | 2018-08-28 | 东莞市波动赢机器人科技有限公司 | Transaction machine people's finance data preparation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104750789B (en) | The recommendation method and device of label | |
| CN101971172B (en) | Mobile sitemaps | |
| CN103885987B (en) | A kind of music recommends method and system | |
| CN102708174B (en) | Method and device for displaying rich media information in browser | |
| CN104239298B (en) | Text message recommends method, server, browser and system | |
| CN101599089B (en) | Method and system for automatically searching and extracting update information on content of video service website | |
| CN109785034A (en) | User's portrait generation method, device, electronic equipment and computer-readable medium | |
| CN102831199A (en) | Method and device for establishing interest model | |
| CN103136188A (en) | Method and system used for sentiment estimation of web browsing user | |
| CN103324666A (en) | Topic tracing method and device based on micro-blog data | |
| CN106844640A (en) | A kind of web data analysis and processing method | |
| CN102117331B (en) | Video search method and system | |
| CN106776860A (en) | One kind search abstraction generating method and device | |
| CN109815381A (en) | User's portrait construction method, system, computer equipment and storage medium | |
| CN110134845A (en) | Project public sentiment monitoring method, device, computer equipment and storage medium | |
| CN103150663A (en) | Method and device for placing network placement data | |
| CN104679825A (en) | Web text-based acquiring and screening method of seismic macroscopic anomaly information | |
| CN103177036A (en) | Method and system for label automatic extraction | |
| CN110209862A (en) | Text matches drawing method, electronic device and computer readable storage medium | |
| CN104484449B (en) | The context extraction method and device of Webpage | |
| CN108763313A (en) | On-line training method, server and the storage medium of model | |
| CN105320734A (en) | Web page core content extraction method | |
| CN102999511B (en) | A kind of page fast conversion method, device and system | |
| CN107491465A (en) | For searching for the method and apparatus and data handling system of content | |
| CN106126623A (en) | Information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |