CN110309253A - Selection method, apparatus and computer readable storage medium - Google Patents
Selection method, apparatus and computer readable storage medium Download PDFInfo
- Publication number
- CN110309253A CN110309253A CN201810170587.9A CN201810170587A CN110309253A CN 110309253 A CN110309253 A CN 110309253A CN 201810170587 A CN201810170587 A CN 201810170587A CN 110309253 A CN110309253 A CN 110309253A
- Authority
- CN
- China
- Prior art keywords
- article
- temperature
- data
- target data
- emotion
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure proposes a kind of selection method, apparatus and computer readable storage medium, is related to big data technical field.A kind of selection method of the disclosure includes: to obtain target data from vertical data source, and vertical data source includes one of Vertical Website, forum or discussion bar or a variety of；Determine the temperature of article associated with target data；According to the synthesis temperature of the ratio-dependent article of the user for the visitor's portrait for meeting vertical data source in user；According to the synthesis temperature selection of article.By such method, data can be obtained from vertical data source to be analyzed, obtain the article temperature for visitor, in conjunction with the synthesis temperature of ratio-dependent article of the visitor in potential user of same type, so that the temperature to article analyzes more useful family specific aim, the reliability of selection analysis is improved.
Description
Technical field
This disclosure relates to big data technical field, especially a kind of selection method, apparatus and computer readable storage medium.
Background technique
Commodity selection is the very important important content in merchandise sales field.Often quick-fried money commodity can be brought high for businessman
Profit still if certain or certain class product have occurred unsalable, no small loss can be brought for businessman, also be unfavorable for pin
Sell the sustainable development of platform.
Businessman may tend to according to network fast sale situation selection in the related technology, or be selected according to sales situation before
Product, but due to the consumption of different crowd difference, hobby is also variant, and sale expection often has larger difference with actual conditions
It is different.
Summary of the invention
One purpose of the disclosure is to improve the reliability of selection analysis.
According to one aspect of the disclosure, a kind of selection method is proposed, comprising: target data is obtained from vertical data source,
Vertical data source includes one of Vertical Website, forum or discussion bar or a variety of；Determine article associated with target data
Temperature；According to the synthesis temperature of the ratio-dependent article of the user for the visitor's portrait for meeting vertical data source in user；According to
The synthesis temperature selection of article.
Optionally, target data is the data for obtaining article from vertical data source as keyword；Determining and number of targets
The temperature of associated article includes: to carry out sentiment analysis to target data in, counts the emotion score of article；According to emotion
The data volume of score and data determines the temperature of article.
Optionally, determine that the temperature of article includes: object in statistics target data according to the relationship of emotion score and data volume
The emotion score of product, and with predetermined emotion threshold value comparison；If emotion score is greater than predetermined emotion threshold value, it is determined that target data pair
Article is positive emotion；Article is determined according to the total amount of data of the quantity of the target data with positive emotion and target data
Temperature.
Optionally, determine that the temperature of article includes: to pass through public affairs according to the data volume of the article quantity of positive emotion and data
Formula:
H=(PN/N)*logMN
Determine the temperature of article, wherein H is the temperature of article, and N is the total amount of data of target data, PNFor target data
In be to article positive emotion quantity, M is positive number greater than 1.
Optionally it is determined that the synthesis temperature of article includes: that will meet shared by the user of visitor's portrait in temperature and user
Synthesis temperature of the product of ratio as article.
Optionally, include one or more of operation according to the synthesis temperature selection of article: comprehensive temperature being selected to be higher than
The article of predetermined comprehensive temperature lower limit；According to the sequential selection article of comprehensive temperature from high to low；Object is determined according to comprehensive temperature
The selection amount of product.
Optionally, visitor's portrait includes the age bracket of visitor；The user for meeting visitor's portrait in user includes using
Meet the user of the age bracket of visitor in family.
By such method, data can be obtained from vertical data source to be analyzed, obtain the object for visitor
Product temperature, in conjunction with the synthesis temperature of ratio-dependent article of the visitor in potential user of same type, so as to object
The temperature of product analyzes more useful family specific aim, improves the reliability of selection analysis.
According to another aspect of the disclosure, propose a kind of selection device, comprising: data capture unit, be configured as from
Vertical data source obtains target data, and vertical data source includes one of Vertical Website, forum or discussion bar or a variety of；Temperature is true
Order member, is configured to determine that the temperature of article associated with target data；Comprehensive temperature determination unit, is configured as basis
Meet the synthesis temperature of the ratio-dependent article of the user of visitor's portrait in vertical data source in user；Selection unit is matched
It is set to the synthesis temperature selection according to article.
Optionally, data capture unit is configured as obtaining number of targets from vertical data source using article as keyword
According to；Temperature determination unit is configured as: being carried out sentiment analysis to target data, is counted the emotion score of article；Count number of targets
According to the emotion score of middle article, and with predetermined emotion threshold value comparison；If emotion score is greater than predetermined emotion threshold value, it is determined that target
Data are positive emotion to article；It is determined according to the total amount of data of the quantity of the target data with positive emotion and target data
The temperature of article.
Optionally, determine that the temperature of article includes: to pass through public affairs according to the data volume of the article quantity of positive emotion and data
Formula:
H=(PN/N)*logMN
Determine the temperature of article, wherein H is the temperature of article, and N is the total amount of data of target data, PNFor target data
In be to article positive emotion quantity, M is positive number greater than 1.
Optionally, comprehensive temperature determination unit is configured as to meet in temperature and user shared by the user of visitor's portrait
Synthesis temperature of the product of ratio as article.
Optionally, selection unit is configured as executing one or more of operation: selecting comprehensive temperature comprehensive higher than making a reservation for
Close the article of temperature lower limit；According to the sequential selection article of comprehensive temperature from high to low；The choosing of article is determined according to comprehensive temperature
Product amount.
According to the another aspect of the disclosure, a kind of selection device is proposed, comprising: memory；And it is coupled to memory
Processor, processor is configured as based on being stored in the instruction execution of memory above any one selection method.
Such device can obtain data from vertical data source and be analyzed, and obtain the article heat for visitor
Degree, in conjunction with the synthesis temperature of ratio-dependent article of the visitor in potential user of same type, so as to article
Temperature analyzes more useful family specific aim, improves the reliability of selection analysis.
According to another aspect of the disclosure, a kind of computer readable storage medium is proposed, be stored thereon with computer journey
The step of sequence instructs, and above any one selection method is realized when which is executed by processor.
Such computer readable storage medium can obtain data from vertical data source by executing instruction thereon
It is analyzed, obtains the article temperature for visitor, in conjunction with ratio-dependent of the visitor in potential user of same type
The synthesis temperature of article improves the reliability of selection analysis so that the temperature to article analyzes more useful family specific aim.
Detailed description of the invention
Attached drawing described herein is used to provide further understanding of the disclosure, constitutes a part of this disclosure, this public affairs
The illustrative embodiments and their description opened do not constitute the improper restriction to the disclosure for explaining the disclosure.In the accompanying drawings:
Fig. 1 is the flow chart of one embodiment of the selection method of the disclosure.
Fig. 2 is the flow chart that one embodiment of temperature of article is determined in the selection method of the disclosure.
Fig. 3 is the flow chart of another embodiment of the selection method of the disclosure.
Fig. 4 is the schematic diagram of one embodiment of the selection device of the disclosure.
Fig. 5 is the schematic diagram of another embodiment of the selection device of the disclosure.
Fig. 6 is the schematic diagram of another embodiment of the selection device of the disclosure.
Specific embodiment
Below by drawings and examples, the technical solution of the disclosure is described in further detail.
The flow chart of one embodiment of the selection method of the disclosure is as shown in Figure 1.
In a step 101, target data is obtained from vertical data source, vertical data source includes Vertical Website, forum or patch
One of or it is a variety of.Since vertical data source often has one or a kind of theme, user group has certain
Characteristic, such as there is certain age characteristics, hobby feature or identity characteristic.It in one embodiment, can be targeted
Visitor's portrait is generated for each or several vertical datas source.In one embodiment, target data is using article as key
The data that word is obtained from vertical data source.
In a step 102, the temperature of article associated with target data is determined.It in one embodiment, can basis
The data volume of target data relevant to the article of needs determines the temperature of article in vertical data source.
In step 103, the quantity of the user to be drawn a portrait according to the visitor for meeting vertical data source in temperature and user is true
The synthesis temperature of earnest product.Due to different crowds, its do shopping channel, platform also can be different, vertically counting obtaining article
After the temperature in source, it is also necessary to determine a possibility that visitor in vertical data source does shopping from this platform or businessman.At one
In embodiment, in the identical situation of temperature, if meeting the quantity of the user of visitor's portrait in vertical data source in user
It is more, then it is higher to integrate temperature；If the quantity for meeting the user of visitor's portrait in vertical data source in user is fewer, comprehensive
It is lower to close temperature.
At step 104, according to the synthesis temperature selection of article.It in one embodiment, can be according to hot value from height
To low sequence selection, the preferential article for selecting hot value high is stocked up and is sold.In another embodiment, it can set predetermined
Hot value lower limit only selects hot value to be higher than the article of predetermined hot value lower limit；It In yet another embodiment, can also be according to heat
Angle value determines selection amount, the high increase amount of stocking up such as hot value, the low reduction amount of stocking up of hot value or does not stock up.
By such method, data can be obtained from vertical data source to be analyzed, obtain for visitor's
Article temperature, in conjunction with the synthesis temperature of ratio-dependent article of the visitor in potential user of same type, so that right
The temperature of article analyzes more useful family specific aim, improves the reliability of selection analysis.
Determine that the flow chart of one embodiment of the temperature of article is as shown in Figure 2 in the selection method of the disclosure.
In step 201, sentiment analysis is carried out to target data, counts the emotion score of article.In one embodiment,
User can be obtained by semantic analysis for the attitude of article, and the keyword and its emotion journey of front or back emotion are such as set
Degree (it is such as high-quality, can with, can manage it), the reversed word of setting (if not, it is non-, still) and degree word (such as very, very, especially),
The emotion score of article is obtained by analyzing matching.
It in one embodiment, can be using the scheme such as SVM (Support Vector Machine, support vector machines)
Emotion is done to target data just negatively classifying.Prepare a sentiment dictionary and marked the training corpus of emotion, for training language
Material does part-of-speech tagging, defines emotion word group (such as degree adverb+emotion word, negative word+emotion word etc.), and then in number of targets
According to all emotion word groups in the middle each sentence of matching.Calculate the positive negative score of emotion of all emotion word groups in sentence.And it counts
The positive negative score of emotion for calculating entire sentence, can be with reference formula:
NegNum_Neg*ScoreA_D*ScoreE
Determine emotion score, wherein Neg is negative word, and Num_Neg is the number that negative word occurs, ScoreA_DFor degree
Score of the adverbial word in sentiment dictionary, ScoreEThe score for being emotion word in sentiment dictionary.The positive negative score of the emotion of sentence is
The sum of the emotion score of all emotion word groups.
In step 202, by the emotion score of article and predetermined emotion threshold value comparison.If the emotion score of article is lower than pre-
Pledge love to feel threshold value, then it is assumed that target data is negative emotion for the article, is not exposed to the welcome of visitor, can not examine
Consider, or avoids considering the article；If the emotion score of article is higher than predetermined emotion threshold value, 204 are thened follow the steps.
In step 203, it is believed that target data is positive emotion for the article, which is that can be used as alternative object
Product execute step 205.
In step 204, the temperature of article is determined according to the data volume of the article quantity of positive emotion and the data.
In one embodiment, formula can be passed through:
H=(PN/N)*logMN
Determine the temperature of article, wherein H is the temperature of article, and N is the total amount of data of target data, such as follow-up number, article
Number or comment item number, PNFor the quantity in target data to article being positive emotion, M is the positive number (such as 10, or natural greater than 1
Constant e).On the one hand the temperature calculated in this way can react the pouplarity of article, on the other hand also can be by target data
Data volume itself account in range, improve article temperature to the accuracy of the reflection of article pouplarity.
It by such method, can not only be in view of the discussion amount about article, additionally it is possible to be carried out for target data
Sentiment analysis obtains the emotional attitude of the access user for article in vertical data source, and then the operation by quantifying obtains object
The temperature of product, calculated result is intuitive, accurate, to improve the reliability of temperature calculating.
In one embodiment, thinking that there is the visitor of negative emotion will not produce to the visitor with positive emotion
In the case where raw influence (i.e. buyer will not change view because other people are unable to say for certain), emotion score can be ignored and be lower than
The data of predetermined emotion threshold value calculate temperature by the method in figure 2 above illustrated embodiment, improve the efficiency of operation.
In another embodiment, thinking that there is the visitor of negative emotion can produce to the visitor with positive emotion
In the case where raw influence (user for holding positive attitude may change view because other people are unable to say for certain), then it can integrate and examine
The emotion score for considering all target datas obtains average result, then the total amount based on target data obtains the temperature of article, thus
It is contemplated that generated influence between different visitors, further increases the reliability of temperature calculating.
In one embodiment, the first predetermined emotion threshold value and the second predetermined emotion threshold value can be set, if emotion score
Greater than the first predetermined emotion threshold value, then it is assumed that emotion is positive emotion；If emotion score is recognized less than the second predetermined emotion threshold value
It is negative emotion for emotion, if emotion score is between the first predetermined emotion threshold value and the second predetermined emotion threshold value, then it is assumed that feelings
Sense is neutral emotion.In one embodiment, the first, second predetermined emotion threshold value can use cross validation according to training corpus
Method take optimal value.By such method, it can be realized the thinner division to article emotion, be conducive to improve fever thermometer
The accuracy of calculation and comprehensive.
The flow chart of another embodiment of the selection method of the disclosure is as shown in Figure 3.
In step 301, Item Title is determined.In one embodiment, selection range can be first determined, in selection range
Article is inside selected to be retrieved.
In step 302, target data is obtained from vertical data source using article as keyword.In one embodiment,
It can retrieve, or crawl in vertical data source using article as keyword, obtain target data.Target data can wrap
Include article, comment, model etc..
In one embodiment, vertical data source can be selected according to the use scope of article, such as article is fortune
Dynamic equipment then can choose movement forum, discussion bar etc. and obtain target data as vertical data source.
In one embodiment, vertical data source can be Vertical Website, discussion bar, forum with era characteristics etc.,
User has the lesser age range of range, its range of age, such as 70 next generations, a generation after 80s, a generation after 90s can be made
For user's portrait.
In step 303, the temperature of article is determined according to target data.It in one embodiment, can be first in every text
Chapter, each model carry out sentiment analysis to article in every comment, obtain emotion score, and then using as above any real
Apply the temperature that the mode in example determines article.
In step 304, user's proportion of portrait is met in counting user.In one embodiment, can to
Family portrait is analyzed, and such as analyzes user's feature using historic sales data or platform registration information, by user's portrait with it is vertical
Visitor's portrait of data source matches, the user to be matched ratio shared in whole users, or in whole use
Consumption proportion in family.
In step 305, using the product of user's proportion and temperature as the synthesis temperature of article.Such as the temperature of article
For H, the user's proportion or spending amount proportion that visitor's portrait is met in user are α, then integrating temperature is α *
H.Such processing mode is while considering article temperature itself, it is also considered that consuming capacity, consumption wish to its user
A possibility that with purchase, so that comprehensive temperature be enable preferably to reflect a possibility that article is purchased.
Within step 306, according to the synthesis temperature selection of article.
By such method, article can be determined as needed, and obtains corresponding target data, further obtain quotient
The temperature of product, and obtain comprehensive temperature in conjunction with user distribution, so as to from two angle estimations of article temperature and user distribution
The sales situation of article improves the reliability of selection analysis.In addition, the article and habit of user's purchase due to different age group
It differs larger, therefore the vertical data source with era characteristics is selected to carry out the calculating of article temperature, and combine corresponding age bracket
User's proportion determine comprehensive temperature, the selection scheme with era characteristics can be provided, further increase selection can
By property.
The schematic diagram of one embodiment of the selection device of the disclosure is as shown in Figure 4.Data capture unit 401 can from hang down
Straight data source obtains target data, and vertical data source includes one of Vertical Website, forum or discussion bar or a variety of.Temperature determines
Unit 403 can determine the temperature of article associated with target data.It in one embodiment, can be according to vertical data source
In the data volume of target data relevant to the article of needs determine the temperature of article.Comprehensive temperature determination unit 404 being capable of root
The quantity of the user to draw a portrait according to the visitor for meeting vertical data source in temperature and user determines the synthesis temperature of article.Due to not
Same crowd its do shopping channel, platform also can be different, therefore are obtaining article after the temperature in vertical data source, it is also necessary to really
Determine a possibility that visitor in vertical data source does shopping from this platform or businessman.Selection unit 405 can be according to the synthesis of article
Temperature selection.In one embodiment, can be according to the sequence selection of hot value from high to low, the preferential object for selecting hot value high
Product are stocked up and are sold.In another embodiment, predetermined hot value lower limit can be set, only hot value is selected to be higher than predetermined temperature
It is worth the article of lower limit；In yet another embodiment, selection amount can also be determined according to hot value, high increase is stocked up such as hot value
Amount, the low reduction amount of stocking up of hot value or does not stock up.
Such device can obtain data from vertical data source and be analyzed, and obtain the article heat for visitor
Degree, in conjunction with the synthesis temperature of ratio-dependent article of the visitor in potential user of same type, so as to article
Temperature analyzes more useful family specific aim, improves the reliability of selection analysis.
In one embodiment, it as shown in figure 4, selection device can also include portrait determination unit 402, can determine vertical
Visitor's portrait of straight data source, visitor's portrait may include the information such as the identity characteristic, age bracket, hobby of visitor.It draws
Meet vertical data as determination unit 402 can draw a portrait visitor to be supplied to comprehensive temperature determination unit 404 and determine in user
The quantity or proportion of the user of visitor's portrait in source, so as to from two angle estimations of article temperature and user distribution
The sales situation of article improves the reliability of selection analysis.
In one embodiment, data capture unit 401 can obtain mesh from vertical data source using article as keyword
Mark data.In one embodiment, it can retrieve, or crawl in vertical data source using article as keyword, obtain
Target data.Target data may include article, comment, model etc..Temperature determination unit 402 can use above any one
Kind of mode determines the temperature of article, thus can not only be in view of the discussion amount about article, additionally it is possible to for target data into
Row sentiment analysis obtains emotional attitude of the access user for article of disposition data source, and then the operation by quantifying obtains
The temperature of article, calculated result is intuitive, accurate, to improve the reliability of temperature calculating.
In one embodiment, comprehensive temperature determination unit 404 can count, and the visit in vertical data source will be met in user
Synthesis temperature of the product for the temperature that the user's proportion and temperature determination unit 402 of the person's of asking portrait determine as article.Such as
The temperature of article is H, and the user's proportion or spending amount proportion that visitor's portrait is met in purchase user are α,
Then integrating temperature is α * H.Such processing mode is while considering article temperature itself, it is also considered that the consumption of its user
A possibility that ability, consumption wish and purchase, so that comprehensive temperature be enable preferably to reflect a possibility that article is purchased.
The structural schematic diagram of one embodiment of disclosure selection device is as shown in Figure 5.Selection device includes memory 501
With processor 502.Wherein: memory 501 can be disk, flash memory or other any non-volatile memory mediums.Memory is used
Instruction in the storage above corresponding embodiment of selection method.Processor 502 is coupled to memory 501, can be used as one
A or multiple integrated circuits are implemented, such as microprocessor or microcontroller.The processor 502 is stored for executing in memory
Instruction, enable to analyze more useful family specific aim to the temperature of article, improve the reliability of selection analysis.
It in one embodiment, can be as shown in fig. 6, selection device 600 includes memory 601 and processor 602.Place
Reason device 602 is coupled to memory 601 by BUS bus 603.The selection device 600 can also be connected to by memory interface 604
External memory 605 can also be connected to network or an other meter to call external data by network interface 606
Calculation machine system (not shown).It no longer describes in detail herein.
In this embodiment, it is instructed by memory stores data, then above-metioned instruction is handled by processor, enabled to
More useful family specific aim is analyzed to the temperature of article, improves the reliability of selection analysis.
In another embodiment, a kind of computer readable storage medium, is stored thereon with computer program instructions, this refers to
The step of enabling the method realized in selection method corresponding embodiment when being executed by processor.Those skilled in the art Ying Ming
White, embodiment of the disclosure can provide as method, apparatus or computer program product.Therefore, complete hardware can be used in the disclosure
The form of embodiment, complete software embodiment or embodiment combining software and hardware aspects.Moreover, the disclosure can be used
One or more wherein includes the computer of computer usable program code can be (including but unlimited with non-transient storage medium
In magnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.
The disclosure is reference according to the method for the embodiment of the present disclosure, the flow chart of equipment (system) and computer program product
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
So far, the disclosure is described in detail.In order to avoid covering the design of the disclosure, it is public that this field institute is not described
The some details known.Those skilled in the art as described above, completely it can be appreciated how implementing technology disclosed herein
Scheme.
Disclosed method and device may be achieved in many ways.For example, can by software, hardware, firmware or
Person's software, hardware, firmware any combination realize disclosed method and device.The step of for the method it is above-mentioned
Sequence is merely to be illustrated, and the step of disclosed method is not limited to sequence described in detail above, unless with other sides
Formula illustrates.In addition, in some embodiments, the disclosure can be also embodied as recording program in the recording medium, these
Program includes for realizing according to the machine readable instructions of disclosed method.Thus, the disclosure also covers storage for executing
According to the recording medium of the program of disclosed method.
Finally it should be noted that: above embodiments are only to illustrate the technical solution of the disclosure rather than its limitations；To the greatest extent
Pipe is described in detail the disclosure referring to preferred embodiment, it should be understood by those ordinary skilled in the art that: still
It can modify to the specific embodiment of the disclosure or some technical features can be equivalently replaced；Without departing from this public affairs
The spirit of technical solution is opened, should all be covered in the claimed technical proposal scope of the disclosure.
Claims (14)
1. a kind of selection method, comprising:
From vertical data source obtain target data, the vertical data source include one of Vertical Website, forum or discussion bar or
It is a variety of；
Determine the temperature of article associated with the target data；
According to the synthesis temperature of the ratio-dependent article of the user for the visitor's portrait for meeting the vertical data source in user；
According to the comprehensive temperature selection of article.
2. according to the method described in claim 1, wherein, the target data is using article as keyword from the vertical number
The data obtained according to source；
The determination includes: with the temperature of associated article in the target data
Sentiment analysis is carried out to the target data, counts the emotion score of the article；
The temperature of article is determined according to the data volume of the emotion score and the data.
3. according to the method described in claim 2, wherein, the relationship according to the emotion score and data volume determines article
Temperature include:
Count the emotion score of article in the target data, and with predetermined emotion threshold value comparison；
If the emotion score is greater than the predetermined emotion threshold value, it is determined that the target data is positive feelings to the article
Sense；
The temperature of article is determined according to the total amount of data of the quantity of the target data with positive emotion and target data.
It is described according to the article quantity of positive emotion and the data of the data 4. according to the method described in claim 3, wherein
Amount determines that the temperature of article includes:
Pass through formula:
H=(PN/N)*logMN
Determine the temperature of article, wherein H is the temperature of article, and N is the total amount of data of target data, PNFor in the target data
It is the quantity of positive emotion to the article, M is the positive number greater than 1.
5. according to the method described in claim 4, wherein, the synthesis temperature of the determining article includes:
User's proportion of visitor's portrait and the product of the temperature will be met in user as the comprehensive of the article
Close temperature.
6. according to the method described in claim 1, wherein, described according to the comprehensive temperature selection of article includes following one kind
Or a variety of operations:
The comprehensive temperature is selected to be higher than the article of predetermined comprehensive temperature lower limit；
According to the sequence selection article of the comprehensive temperature from high to low；
The selection amount of article is determined according to the comprehensive temperature.
7. according to the method described in claim 1, wherein,
Visitor's portrait includes the age bracket of the visitor；
The user for meeting visitor's portrait in the user includes the user for meeting the age bracket of the visitor in user.
8. a kind of selection device, comprising:
Data capture unit, be configured as from vertical data source obtain target data, the vertical data source include Vertical Website,
One of forum or discussion bar are a variety of；
Temperature determination unit is configured to determine that the temperature of article associated with the target data；
Comprehensive temperature determination unit is configured as the user's to draw a portrait according to the visitor for meeting the vertical data source in user
The synthesis temperature of ratio-dependent article；
Selection unit is configured as the comprehensive temperature selection according to article.
9. device according to claim 8, wherein
The data capture unit is configured as obtaining target data from the vertical data source using article as keyword；
The temperature determination unit is configured as:
Sentiment analysis is carried out to the target data, counts the emotion score of the article；
Count the emotion score of article in the target data, and with predetermined emotion threshold value comparison；
If the emotion score is greater than the predetermined emotion threshold value, it is determined that the target data is positive feelings to the article
Sense；
The temperature of article is determined according to the total amount of data of the quantity of the target data with positive emotion and target data.
10. device according to claim 9, wherein described according to the article quantity of positive emotion and the number of the data
Include: according to the temperature for determining article is measured
Pass through formula:
H=(PN/N)*logMN
Determine the temperature of article, wherein H is the temperature of article, and N is the total amount of data of target data, PNFor in the target data
It is the quantity of positive emotion to the article, M is the positive number greater than 1.
11. device according to claim 10, wherein the comprehensive temperature determination unit is configured as to meet in user
The synthesis temperature of user's proportion of visitor's portrait and the product of the temperature as the article.
12. device according to claim 8, wherein the selection unit is configured as executing one or more of behaviour
Make:
The comprehensive temperature is selected to be higher than the article of predetermined comprehensive temperature lower limit；
According to the sequential selection article of the comprehensive temperature from high to low；
The selection amount of article is determined according to the comprehensive temperature.
13. a kind of selection device, comprising:
Memory；And
It is coupled to the processor of the memory, the processor is configured to based on the instruction execution for being stored in the memory
Method as described in any one of claim 1 to 7.
14. a kind of computer readable storage medium, is stored thereon with computer program instructions, real when which is executed by processor
The step of method described in existing claim 1 to 7 any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170587.9A CN110309253A (en) | 2018-03-01 | 2018-03-01 | Selection method, apparatus and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810170587.9A CN110309253A (en) | 2018-03-01 | 2018-03-01 | Selection method, apparatus and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110309253A true CN110309253A (en) | 2019-10-08 |
Family
ID=68073276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810170587.9A Pending CN110309253A (en) | 2018-03-01 | 2018-03-01 | Selection method, apparatus and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110309253A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763111A (en) * | 2021-02-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article collocation method, device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799587A (en) * | 2011-05-25 | 2012-11-28 | 腾讯科技（深圳）有限公司 | Forum searching method and device |
| CN103425767A (en) * | 2013-08-07 | 2013-12-04 | 北京搜狗信息服务有限公司 | Method and system for determining prompt data |
| CN104572889A (en) * | 2014-12-24 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method, device and system for recommending search terms |
| US20150135057A1 (en) * | 2013-11-08 | 2015-05-14 | Yahoo! Inc. | Media Forums for Presenting and Managing User Generated Content Regarding Articles Presented on Websites |
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN105740353A (en) * | 2016-01-26 | 2016-07-06 | 中国人民解放军国防科学技术大学 | Calculation method and system for relevance degree of individual share and article |
| CN107153697A (en) * | 2017-05-08 | 2017-09-12 | 浙江敢尚网络科技有限公司 | Product search method and device in a kind of commodity transaction website |
| CN107341176A (en) * | 2017-05-23 | 2017-11-10 | 北京三快在线科技有限公司 | A kind of sample weights method to set up and device, electronic equipment |
| CN107632989A (en) * | 2016-07-19 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of merchandise items are chosen, model determines and determines method and apparatus using temperature |
| CN107679904A (en) * | 2017-09-28 | 2018-02-09 | 山东浪潮云服务信息科技有限公司 | A kind of method and device of Recommendations |
-
2018
- 2018-03-01 CN CN201810170587.9A patent/CN110309253A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799587A (en) * | 2011-05-25 | 2012-11-28 | 腾讯科技（深圳）有限公司 | Forum searching method and device |
| CN103425767A (en) * | 2013-08-07 | 2013-12-04 | 北京搜狗信息服务有限公司 | Method and system for determining prompt data |
| US20150135057A1 (en) * | 2013-11-08 | 2015-05-14 | Yahoo! Inc. | Media Forums for Presenting and Managing User Generated Content Regarding Articles Presented on Websites |
| CN105096152A (en) * | 2014-05-20 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Commodity popularity-based operation execution method and device |
| CN104572889A (en) * | 2014-12-24 | 2015-04-29 | 深圳市腾讯计算机系统有限公司 | Method, device and system for recommending search terms |
| CN105740353A (en) * | 2016-01-26 | 2016-07-06 | 中国人民解放军国防科学技术大学 | Calculation method and system for relevance degree of individual share and article |
| CN107632989A (en) * | 2016-07-19 | 2018-01-26 | 阿里巴巴集团控股有限公司 | A kind of merchandise items are chosen, model determines and determines method and apparatus using temperature |
| CN107153697A (en) * | 2017-05-08 | 2017-09-12 | 浙江敢尚网络科技有限公司 | Product search method and device in a kind of commodity transaction website |
| CN107341176A (en) * | 2017-05-23 | 2017-11-10 | 北京三快在线科技有限公司 | A kind of sample weights method to set up and device, electronic equipment |
| CN107679904A (en) * | 2017-09-28 | 2018-02-09 | 山东浪潮云服务信息科技有限公司 | A kind of method and device of Recommendations |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763111A (en) * | 2021-02-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article collocation method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10726208B2 (en) | Consumer insights analysis using word embeddings | |
| Bell | What is machine learning? | |
| Wang et al. | Effect of online review sentiment on product sales: The moderating role of review credibility perception | |
| CN103377262B (en) | The method and apparatus being grouped to user | |
| US11315164B2 (en) | Complementary product recommendation systems | |
| CN110532479A (en) | A kind of information recommendation method, device and equipment | |
| US11182806B1 (en) | Consumer insights analysis by identifying a similarity in public sentiments for a pair of entities | |
| US10685183B1 (en) | Consumer insights analysis using word embeddings | |
| CN103140868B (en) | The possibility of applicability is determined based on historical data | |
| CN110428298A (en) | A kind of shop recommended method, device and equipment | |
| KR102635928B1 (en) | internet meme economy | |
| CN109690529A (en) | Document is compiled into timeline by event | |
| US10558759B1 (en) | Consumer insights analysis using word embeddings | |
| CN108537587A (en) | It is lost in user's method for early warning, device, computer readable storage medium and server | |
| US10803248B1 (en) | Consumer insights analysis using word embeddings | |
| CN110322300B (en) | Data processing method and device, electronic equipment and storage medium | |
| JP2015528170A (en) | Method and device for determining hot selling goods for holidays | |
| CN110413870A (en) | Method of Commodity Recommendation, device and server | |
| KR102097045B1 (en) | Method and apparatus to recommend products reflecting characteristics of users | |
| CN108153792A (en) | A kind of data processing method and relevant apparatus | |
| CN107622413A (en) | A kind of price sensitivity computational methods, device and its equipment | |
| JPWO2018142753A1 (en) | Information processing apparatus, information processing method, and information processing program using deep learning | |
| US11030539B1 (en) | Consumer insights analysis using word embeddings | |
| CN108269169A (en) | A kind of shopping guide method and system | |
| CN111861605A (en) | Business object recommendation method |
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 |