CN106503228A - A kind of packet scarcity appraisal procedure and its system - Google Patents
A kind of packet scarcity appraisal procedure and its system Download PDFInfo
- Publication number
- CN106503228A CN106503228A CN201610970543.5A CN201610970543A CN106503228A CN 106503228 A CN106503228 A CN 106503228A CN 201610970543 A CN201610970543 A CN 201610970543A CN 106503228 A CN106503228 A CN 106503228A
- Authority
- CN
- China
- Prior art keywords
- packet
- assessed
- data
- similarity
- scarcity
- 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
- G06F16/951—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)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention provides a kind of packet scarcity appraisal procedure and its system, and the method is comprised the following steps:S100:Obtain multiple related data packets related to given content;S200:Determine packet to be assessed, and determine the similarity between packet to be assessed and other packets, choose with the similarity between packet to be assessed higher than predetermined threshold packet as comparing packet;S300:The scarcity of packet to be assessed is determined using default processing method.The present invention is by being estimated to the scarcity of packet such that it is able to understand the quality of packet, the value assessment for data provides certain reference frame.
Description
Technical field
The present invention relates to big data field, and in particular to a kind of packet scarcity appraisal procedure and its system.
Background technology
Data trade is currently in the industry initial stage, and development is very fast, but lacks the theoretical direction of maturation.By data value
Quantization is an extremely difficult thing, this be by data substitutive characteristics and current business environment determined.Meanwhile, this
One work will be also hindered by numerous objective factors, such as the accurate assessment of data compiling costs, the devaluation of data and Life Cycle
Phase changes, and the surcharge of data etc..With data product conclude the business increasingly prevailing, how to judge the value of data, this
The puzzlement for not only bringing to data selling business, also brings puzzlement to buyer.
Well-known viewpoint is that thing which is rare is dear, for data no exception.More rare data, its value are also corresponding
About big.The scarcity of data message resource is divided at 2 points, and one is rare root source, i.e., data message resource is objective
Sexual valence value;Two is the rare form of expression, the serviceability of data message resource cause rare be possibly realized, data message resource
Nonhomogeneity causes rare becoming necessarily.
Therefore, how the scarcity of data is estimated, preferably to provide preferably service as data trade market
Become problem urgently to be resolved hurrily.
Content of the invention
For above-mentioned technical problem, the present invention provides a kind of packet scarcity appraisal procedure and its system.
The technical solution used in the present invention is:
Embodiments of the invention provide a kind of packet scarcity appraisal procedure, including:
S100:Obtain multiple related data packets related to given content;
S200:Determine packet to be assessed, and determine the similarity between packet to be assessed and other packets, choose
With the similarity between packet to be assessed higher than predetermined threshold packet as comparing packet;
S300:The scarcity of packet to be assessed is determined using default processing method, is assessed especially by equation below
The scarcity of packet to be assessed:
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y be except packet to be assessed with
All data strip number sums in other outer packets;X is the data strip number in packet to be assessed.
Preferably, calculated between packet to be assessed and other packets using text similarity measurement algorithm in step s 200
Similarity, specifically include:
S210:Packet to be assessed and the text compared in packet are read in R LISP program LISPs, by participle instrument
Or the text in each packet is split into single word by user-defined word segmentation regulation, determine Feature Words and count each spy
The word frequency of word appearance is levied, and sets up document entry matrix;
S220:Packet to be assessed and the similarity compared between packet are calculated based on below equation:
Wherein, G is the similarity between packet to be assessed and other packets, and scope is [0,1];N1, N2…NmWith
M1, M2…MmThe number of times that each Feature Words in packet respectively to be assessed and other packets occur.
Preferably, when G is more than 0.5, represent that packet to be assessed has similarity with packet is compared;When G is more than
When 0.85, packet to be assessed is represented with to compare packet highly similar.
Preferably, as f=0, represent that the data in packet to be assessed are not rare;As f=1, number to be assessed is represented
Data according to bag compare in packet at other and do not exist, very rare.
Preferably, related to given content multiple to obtain by crawling the network data of the multiple data platforms in the Internet
Related data packets.
Another embodiment of the present invention provides a kind of packet scarcity assessment system, including:
Data acquisition module, obtains multiple related data packets related to given content;Similarity assessment module, determination are treated
Assessment packet, and determine the similarity between packet to be assessed and other packets, choose and packet to be assessed between
Similarity higher than predetermined threshold packet as comparing packet;Scarcity evaluation module, using default processing method come
Determine the scarcity of packet to be assessed, especially by the scarcity that equation below assesses packet to be assessed:
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y be except packet to be assessed with
All data strip number sums in other outer packets;X is the data strip number in packet to be assessed.
Alternatively, the similarity assessment module includes:Feature extraction unit, by keyword extraction instrument or makes by oneself
Justice determines the Feature Words between packet to be assessed and the text compared in packet;Entry document matrix sets up unit, will treat
Assessment packet is read in R LISP program LISPs with the text compared in packet, by participle instrument or user-defined participle
Text in each packet is split into single word by rule, is counted the word frequency that each Feature Words occurs, and is set up document word
Bar matrix;Similarity calculated, calculates packet to be assessed and the similarity compared between packet based on below equation:
Wherein, G is the similarity between packet to be assessed and other packets, and scope is [0,1];N1, N2…NmWith
M1, M2…MmThe number of times that each Feature Words in packet respectively to be assessed and other packets occur.
Alternatively, the predetermined threshold is 0.5, and when G is more than 0.5, expression packet to be assessed has with packet is compared
There is similarity;When G is more than 0.85, packet to be assessed is represented with to compare packet highly similar.
Alternatively, as f=0, represent that the data in packet to be assessed are not rare;As f=1, number to be assessed is represented
Data according to bag compare in packet at other and do not exist, very rare.
Alternatively, the data acquisition module is obtained and refers to by crawling the network data of the multiple data platforms in the Internet
Determine the related multiple related data packets of content.
The present invention is by being estimated to the scarcity of packet such that it is able to understands the quality of packet, is data
Value assessment provides certain reference frame.
Description of the drawings
Fig. 1 is the schematic flow sheet of packet scarcity appraisal procedure provided in an embodiment of the present invention;
Fig. 2 is the structural representation of packet scarcity assessment system provided in an embodiment of the present invention.
Specific embodiment
Hereinafter, the specific embodiment of the present invention is described in conjunction with accompanying drawing.
【Embodiment 1】Packet scarcity appraisal procedure
Fig. 1 is the schematic flow sheet of packet scarcity appraisal procedure provided in an embodiment of the present invention.As shown in figure 1, this
The packet scarcity appraisal procedure that embodiment is provided, including:
S100:Obtain related data packets
Specifically, given content can be based on, the phase on each big data business site is crawled using Python programming
Packet is closed, and the data for crawling are stored in relevant database MySQL database, can be included inside packet various
The file of data type, such as JSON, picture, video, audio frequency etc. file.The detailed process for crawling is:User input network address
Afterwards, through dns server, server host being found, a request being sent to server, server is sent out after parsing
The files such as browser HTML, JS, CSS of user are given, browser resolves are out.Therefore, the webpage that user sees substantially be by
HTML code is constituted, and it is these contents that reptile climbs come, by analyzing and filtering these HTML codes, realize to picture,
Crawling for the resource such as word and upload adnexa, thus can illustrate for packet to the website that each big data is concluded the business
Related content is crawled.Thus, the multiple related data packets comprising same body content can be obtained.It is of course also possible to will
The packet that obtained is chosen before evaluation operation to be estimated, rather than is crawled in evaluation operation in real time.
S200:The similarity between packet is calculated, the packet that similarity exceedes predetermined threshold is chosen
Specifically, a packet to be assessed can be determined according to practical situation, for example, it is desired to certain data provision platform
The scarcity of data be estimated, the packet that the data provision platform is provided can be appointed as packet to be assessed, then
The similarity between the packet to be assessed and other packets is calculated using text similarity measurement algorithm, similarity is chosen and is surpassed
The packet of predetermined threshold is crossed, as comparing packet.Step S200 may particularly include:
S210:Text in packet is read in R LISP program LISPs, is advised by participle instrument or user-defined participle
The text in each packet in the related data packets is split into single word then, Feature Words is determined and is counted each spy
The word frequency of word appearance is levied, and sets up document entry matrix, for example, with regard to the packet of three import and export products, the entry of foundation
Document matrix can be as shown in table 1 below:
Table 1:Entry document matrix
Feature | Declaration | Outlet | Port | Provinces and cities | Quantity | Originate in | Species | The amount of money | Specification |
Text 1 | 2 | 4 | 1 | 2 | 6 | 2 | 2 | 7 | 0 |
Text 2 | 1 | 5 | 4 | 3 | 8 | 2 | 2 | 5 | 1 |
Text 3 | 3 | 1 | 4 | 0 | 1 | 8 | 7 | 2 | 3 |
Numeral wherein in table 1 represents the number of times of the Feature Words occurred in corresponding text.
S230:Calculate the similarity between packet
The similarity between two packets can be calculated using following formula 1:
【Formula 1】
Wherein, G is the similarity between two packets, and scope is [0,1];N1, N2…NmAnd M1, M2…MmRespectively compare
Compared with two packets in the number of times that occurs of each Feature Words.In the present embodiment, predetermined threshold can be 0.5, i.e., when G is more than
When 0.5, represent that two packets are similar;When G is more than 0.85, represent that two packets are highly similar.
By taking table 1 as an example, the word occurred in text 1 is:C1、C2、C3、C4……Cn;The number of times that these words occur is respectively:
N1, N2, N3 ... Nm, in text 2, the word of appearance is:C1、C2、C3、C4……Cn;The number of times that these words occur is respectively:M1、
M2、M3……Mm.Wherein, C1 represents same word in two texts, and N1 and M1 is that they distinguish corresponding number, then can base
The similarity between text 1 and text 2 is calculated in above-mentioned formula, and calculating process is as follows:
As the similarity score between text 1 and text 2 is 0.97, more than 0.85, therefore, can determine whether comprising text 1
Packet and the packet comprising text 2 between there is high similarity.If it is determined that the scarcity of needs assessment text 1,
Then can be using the data comprising text 2 as comparing packet.Equally, the similarity between text 1 and text 3 can be calculated, is led to
It is 0.4 to cross the similarity score that can be calculated between text 1 and text 3, less than 0.5, then it represents that the packet comprising text 1 with
Similarity between packet comprising text 3 is not high, can not be using the packet comprising text 3 as comparing packet.Certainly,
When the scarcity of needs assessment text 2, then it is that correlation technique is identical with text 1 according to calculating similarity with text 2, when
During the scarcity of needs assessment text 3, and so.
S300:Calculate the scarcity of packet to be assessed
When scarcity is calculated, need to select a packet to be assessed, the packet to be assessed can be according to practical situation
To determine.If homogeneous data is more, then it represents that scarcity is lower;If homogeneous data is fewer, then it represents that scarcity is higher.
For specified packet to be assessed, the scarcity of the packet can be assessed by equation below 2:
【Formula 2】
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y be except packet to be assessed with
All data strip number sums in other outer packets;X is the data strip number in packet to be assessed.Data strip number can be according to pre-
If rule is determining, for example, it can be one section of text in short or with regard to certain event etc..As f=0, number to be assessed is represented
Data according to bag are not very rare;As f=1, represent the data in packet to be assessed in other packets to be assessed
Do not exist, very rare.
The assessment of scarcity is illustrated below by way of an example.
Example
First, two data provision platforms are crawled by Python programming according to given content " information-based related "
Related data packets 1 and 2 on 1 and 2, and determine the scarcity of assessment packet 1.
Then, the content according to disclosed in step S200 sets up the entry of the packet with regard to the two data provision platforms
Document matrix, as shown in table 2 below:
Table 2
Data | Field | Information | Microblogging | Machine | Society | Time | Public sentiment | Study | Collection | |
Packet 1 | 1 | 2 | 3 | 2 | 1 | 1 | 1 | 1 | 1 | 1 |
Packet 22 | 1 | 1 | 1 | 2 | 0 | 0 | 1 | 3 | 2 | 5 |
Then, the similarity between the two packets is calculated using above-mentioned formula 1, obtain the phase between two packets
Seemingly spend and must be divided into 0.63, show that the two packets are similar.
Learnt by statistics, the total data bar number of packet 1 and 2 is 6,000,000, and the data strip number of wherein packet 1 is
5000000, the data strip number of packet 2 is 1,000,000, and the scarcity for calculating packet 1 using above-mentioned formula 2 is:
This expression, the scarcity of packet 1 are very rare.
【Embodiment 2】Packet scarcity assessment system
Fig. 2 is the structural representation of packet scarcity assessment system provided in an embodiment of the present invention.As shown in Fig. 2 this
The packet scarcity assessment system that embodiment is provided, assesses including data acquisition module, similarity assessment module and scarcity
Module.
Wherein, data acquisition module is used for obtaining multiple related data packets related to given content.Can be by passing through net
Network crawls the network data of multiple data provision platforms to obtain multiple related data packets related to given content.For example, may be used
Given content is based on, and the related data packets on each big data business site is crawled using Python programming, and will be climbed
The data for taking are stored in relevant database MySQL database, can include the file of various data types inside packet,
Such as JSON, picture, video, audio frequency etc. file.The detailed process for crawling is:After user input network address, through DNS service
Device, finds server host, sends a request to server, and server is sent to the browser of user after parsing
The files such as HTML, JS, CSS, browser resolves are out.Therefore, the webpage that user sees substantially is made up of HTML code, is climbed
What worm climbed is these contents, by analyzing and filtering these HTML codes, realizes to picture, word and uploads adnexa
Etc. crawling for resource, thus can illustrate etc. that the content of correlation is climbed for packet to website that each big data is concluded the business
Take.Thus, the multiple related data packets comprising same body content can be obtained.It is of course also possible to will choose before evaluation operation
The packet for having obtained is being estimated, rather than is crawled in evaluation operation in real time.
Similarity assessment module is used for determining packet to be assessed, and determines between packet to be assessed and other packets
Similarity, choose with the similarity between packet to be assessed higher than predetermined threshold packet as comparing packet.Phase
May include like degree evaluation module:Entry document matrix sets up unit, and packet to be assessed is read with the text compared in packet
Enter in R LISP program LISPs, the text in each packet is split into by list by participle instrument or user-defined word segmentation regulation
Individual word, determines Feature Words and counts the word frequency that each Feature Words occurs, and set up document entry matrix;Similarity Measure list
Unit, calculates packet to be assessed and the similarity compared between packet based on below equation:
Wherein, G is the similarity between packet to be assessed and other packets, and scope is [0,1];N1, N2…NmWith
M1, M2…MmThe number of times that each Feature Words in packet respectively to be assessed and other packets occur.Predetermined threshold can be
0.5, when G is more than 0.5, represent that packet to be assessed has similarity with packet is compared;When G is more than 0.85, expression is treated
Assessment packet is with to compare packet highly similar.
Scarcity evaluation module is used for utilizing default processing method to determine the scarcity of packet to be assessed, especially by
Equation below assesses the scarcity of packet to be assessed:
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y be except packet to be assessed with
All data strip number sums in other outer packets;X is the data strip number in packet to be assessed.As f=0, expression is treated
Data in assessment packet are not very rare;As f=1, represent that the data in packet to be assessed compare data at other
Do not exist in bag, very rare.
It should be noted that being related to several factors in terms of the value assessment of data file, need to consider each factor
The final valuation of data file can be just drawn, the one side of simply estimated data's scarcity that the present invention is provided, is data file
Valuation provide a reference frame.
To sum up, present invention introduces the scarcity analysis method of economics category carries out valuation to data assets, with more preferable
For Data Market behavior service, promote Data Market transaction and the quick landing of data items.
Those skilled in the art are it should be appreciated that embodiments herein can be provided as method, system or computer program
Product.Therefore, the application can adopt complete hardware embodiment, complete software embodiment or with reference to software and hardware in terms of reality
Apply the form of example.And, the application can be adopted in one or more computers for wherein including computer usable program code
The upper computer program that implements of usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) is produced
The form of product.
Although having been described for the preferred embodiment of the application, those skilled in the art once know basic creation
Property concept, then can make other change and modification to these embodiments.So, claims are intended to be construed to include excellent
Select embodiment and fall into the had altered of the application scope and change.Obviously, those skilled in the art can be to the application
Embodiment carries out the spirit and scope of various changes and modification without deviating from the embodiment of the present application.So, if the application is implemented
These modifications of example and modification belong within the scope of the application claim and its equivalent technologies, then the application is also intended to include
Including these changes and modification.
Claims (10)
1. a kind of packet scarcity appraisal procedure, it is characterised in that include:
S100:Obtain multiple related data packets related to given content;
S200:Determine packet to be assessed, and determine the similarity between packet to be assessed and other packets, choose and treat
Similarity between assessment packet higher than predetermined threshold packet as comparing packet;
S300:The scarcity of packet to be assessed is determined using default processing method, is assessed especially by equation below to be evaluated
Estimate the scarcity of packet:
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y is in addition to packet to be assessed
All data strip number sums in other packets;X is the data strip number in packet to be assessed.
2. method according to claim 1, it is characterised in that calculated using text similarity measurement algorithm in step s 200 and treated
Similarity between assessment packet and other packets, specifically includes:
S210:Packet to be assessed and the text compared in packet are read in R LISP program LISPs, by participle instrument or use
Text in each packet is split into single word by the word segmentation regulation of family definition, is determined Feature Words and is counted each Feature Words
The word frequency of appearance, and set up document entry matrix;
S220:Packet to be assessed and the similarity compared between packet are calculated based on below equation:
Wherein, G is the similarity between packet to be assessed and other packets, and scope is [0,1];N1, N2…NmAnd M1, M2…
MmThe number of times that each Feature Words in packet respectively to be assessed and other packets occur.
3. method according to claim 2, it is characterised in that when G is more than 0.5, represents packet to be assessed and compares
Packet has similarity;When G is more than 0.85, packet to be assessed is represented with to compare packet highly similar.
4. method according to claim 1, it is characterised in that as f=0, represents data in packet to be assessed not
Rare;As f=1, represent that the data in packet to be assessed compare in packet at other and do not exist, very rare.
5. method according to claim 1, it is characterised in that by crawling the network data of the multiple data platforms in the Internet
To obtain multiple related data packets related to given content.
6. a kind of packet scarcity assessment system, it is characterised in that include:
Data acquisition module, obtains multiple related data packets related to given content;
Similarity assessment module, determines packet to be assessed, and determines similar between packet to be assessed and other packets
Degree, choose with the similarity between packet to be assessed higher than predetermined threshold packet as comparing packet;
Scarcity evaluation module, determines the scarcity of packet to be assessed using default processing method, especially by following public affairs
Formula assesses the scarcity of packet to be assessed:
Wherein, f is the scarcity score of packet to be assessed, and span is [0,1];Y is in addition to packet to be assessed
All data strip number sums in other packets;X is the data strip number in packet to be assessed.
7. system according to claim 6, it is characterised in that the similarity assessment module includes:
Entry document matrix sets up unit, and packet to be assessed and the text compared in packet are read in R LISP program LISPs,
Text in each packet is split into by single word by participle instrument or user-defined word segmentation regulation, Feature Words are determined
The word frequency that each Feature Words occurs is counted and, and set up document entry matrix;
Similarity calculated, calculates packet to be assessed and the similarity compared between packet based on below equation:
Wherein, G is the similarity between packet to be assessed and other packets, and scope is [0,1];N1, N2…NmAnd M1, M2…
MmThe number of times that each Feature Words in packet respectively to be assessed and other packets occur.
8. system according to claim 7, it is characterised in that when G is more than 0.5, represents packet to be assessed and compares
Packet has similarity;When G is more than 0.85, packet to be assessed is represented with to compare packet highly similar.
9. system according to claim 6, it is characterised in that as f=0, represents data in packet to be assessed not
Rare;As f=1, represent that the data in packet to be assessed compare in packet at other and do not exist, very rare.
10. system according to claim 6, it is characterised in that the data acquisition module passes through by crawling the Internet
The network data of multiple data platforms is obtaining multiple related data packets related to given content.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610970543.5A CN106503228A (en) | 2016-10-28 | 2016-10-28 | A kind of packet scarcity appraisal procedure and its system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610970543.5A CN106503228A (en) | 2016-10-28 | 2016-10-28 | A kind of packet scarcity appraisal procedure and its system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106503228A true CN106503228A (en) | 2017-03-15 |
Family
ID=58321845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610970543.5A Pending CN106503228A (en) | 2016-10-28 | 2016-10-28 | A kind of packet scarcity appraisal procedure and its system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106503228A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109345301A (en) * | 2018-09-26 | 2019-02-15 | 国信优易数据有限公司 | A kind of data price-determining system and determining method |
CN110766428A (en) * | 2018-07-25 | 2020-02-07 | 国信优易数据有限公司 | Data value evaluation system and method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102411583A (en) * | 2010-09-20 | 2012-04-11 | 阿里巴巴集团控股有限公司 | Method and device for matching texts |
CN105488699A (en) * | 2015-12-25 | 2016-04-13 | 国信优易数据有限公司 | Data asset value assessment method |
-
2016
- 2016-10-28 CN CN201610970543.5A patent/CN106503228A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102411583A (en) * | 2010-09-20 | 2012-04-11 | 阿里巴巴集团控股有限公司 | Method and device for matching texts |
CN105488699A (en) * | 2015-12-25 | 2016-04-13 | 国信优易数据有限公司 | Data asset value assessment method |
Non-Patent Citations (1)
Title |
---|
科技日报: "全球首个数据资产评估模型发布", 《科技日报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766428A (en) * | 2018-07-25 | 2020-02-07 | 国信优易数据有限公司 | Data value evaluation system and method |
CN109345301A (en) * | 2018-09-26 | 2019-02-15 | 国信优易数据有限公司 | A kind of data price-determining system and determining method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sellers et al. | The COM‐Poisson model for count data: a survey of methods and applications | |
Althouse et al. | Differences in impact factor across fields and over time | |
Chan et al. | Evaluating online ad campaigns in a pipeline: causal models at scale | |
TWI518614B (en) | Method and Device for E - commerce Information Based on User Behavior | |
US8073865B2 (en) | System and method for content extraction from unstructured sources | |
CN106056407A (en) | Online banking user portrait drawing method and equipment based on user behavior analysis | |
US20180246880A1 (en) | System for generating synthetic sentiment using multiple points of reference within a hierarchical head noun structure | |
WO2009110550A1 (en) | Attribute extraction method, system, and program | |
JP6334431B2 (en) | Data analysis apparatus, data analysis method, and data analysis program | |
CN107273391A (en) | Document recommends method and apparatus | |
Heule et al. | Local search for fast matrix multiplication | |
CN112507212A (en) | Intelligent return visit method and device, electronic equipment and readable storage medium | |
Ashtor | Investigating cohort similarity as an ex ante alternative to patent forward citations | |
CN104111969A (en) | Method and system for measuring similarity | |
Kim et al. | Proposing a missing data method for hospitality research on online customer reviews: An application of imputation approach | |
CN106874368B (en) | RTB bidding advertisement position value analysis method and system | |
CN106503228A (en) | A kind of packet scarcity appraisal procedure and its system | |
KR20110023750A (en) | Object customization and management system | |
CN114880566A (en) | User behavior analysis method, device, equipment and medium based on graph neural network | |
CN112511632B (en) | Object pushing method, device and equipment based on multi-source data and storage medium | |
CN108959289B (en) | Website category acquisition method and device | |
CN106649748B (en) | Information recommendation method and device | |
Ramaswamy et al. | Evaluating Asian free trade agreements: What does gravity model tell us? | |
Olmedilla et al. | Identification of Influencers in eWord-of-Mouth communities using their Online Participation Features | |
CN106844718B (en) | Data set determination method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |
|
RJ01 | Rejection of invention patent application after publication |