CN109559199A - A kind of product methods of sampling of reflection online shopping customer quality experience - Google Patents
A kind of product methods of sampling of reflection online shopping customer quality experience Download PDFInfo
- Publication number
- CN109559199A CN109559199A CN201811378800.1A CN201811378800A CN109559199A CN 109559199 A CN109559199 A CN 109559199A CN 201811378800 A CN201811378800 A CN 201811378800A CN 109559199 A CN109559199 A CN 109559199A
- Authority
- CN
- China
- Prior art keywords
- sampling
- sample
- product
- percent defective
- online shopping
- 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
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of product methods of samplings of reflection online shopping customer quality experience, include: that (1) determines target sample；(2) sampled population and building Sampling Frame are determined；(3) sampling plan is determined；(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount is n；(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；(6) percent defective and confidence interval of sample are calculated；The present invention is according to the characteristic of shopping at network, sampling plan is determined by reasonable computation, the determination basis of sampling plan is provided for sampling observation personnel, it is sampled using mysterious sampler's online shopping sampling system, so as to effectively improve the reasonability of sampling plan selection, and then the reliability of sampling results can greatly be improved, and further pass through the reliability of authenticity guarantee's sampling results of sampling product, it is ensured that the present invention has the characteristics that sampling results reliability can be effectively improved.
Description
Technical field
The invention belongs to product quality methods of sampling technical fields, and in particular to a kind of reflection online shopping customer quality experience
The product methods of sampling.
Background technique
E-commerce is the world and China business appearance with the fastest developing speed, at the same time, the matter of network trading commodity
Amount but allows of no optimist, because the rate of complaints of quality problems accounts for the 52% of national merchandising the rate of complaints, so to online transaction quotient
Product, which carry out quality surveillance, becomes particularly significant.The difference of e-commerce and solid shop/brick and mortar store is that sellers (online merchants) do not exist
, generally by express company's delivery, transportational process is difficult to monitor product, further, since when sampler faces online merchants, only
It can see the store information and product introduction that storekeeper is unilaterally presented, cannot intuitively recognize that sample basic condition, each electric business are flat
Platform and sellers' product control level are different, and online spending product quality is irregular, and online commercial quality supervision is mainly by net
Upper commodity carry out online shopping sampling and examine to realize.But the samples selection of existing online shopping sampling is mainly or using solid shop/brick and mortar store
Sample mode carry out, since sampling samples amount is to be calculated according to quantity in stock, and the quantity in stock of online product is not under line
Must be true and magnanimity line on the dimension of product constitute the factors such as more complex than solid shop/brick and mortar store product, to be taken out under line
Original mold formula sample on line, easily causes sampling samples unreasonable, unreliable so as to cause subsequent sampling results.Therefore,
There is the insecure problems of sampling results for existing technology.
Summary of the invention
The object of the present invention is to provide a kind of product methods of samplings of reflection online shopping customer quality experience.The present invention
Have the characteristics that sampling results reliability can be effectively improved.
Technical solution of the present invention: a kind of product methods of sampling of reflection online shopping customer quality experience, including following step
It is rapid:
(1) target sample is determined；
(2) sampled population and building Sampling Frame are determined；
(3) sampling plan is determined；
(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount is n；
(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；
(6) percent defective and confidence interval of sample are calculated.
In a kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, the step (1) is in sampling pair
After determination, also needs to select the quality index that can reflect target sample product quality situation according to fixed target sample, make
For the mass property of target sample.
In a kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, determines and take out in the step (2)
Sample is overall and constructs Sampling Frame method particularly includes:
2.1) according to fixed target sample, corresponding one or more e-commerce platforms are selected；
2.2) the setting search key relevant to target sample and mass property on selected e-commerce platform, is adopted
Collect all relevant sale links；
2.3) capable processing is tapped into distribution chain, rejects the link extremely of repeated links, price and other does not meet sampling pair
As the invalid sale link required with mass property, the total quantity for obtaining effectively selling link is L；By effective sale link
Total quantity is L overall as sample, and unit product sum included in sample totality is N；
2.4) whole effective sale links is arranged and forms a register library, as Sampling Frame.
A kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, it is characterised in that: the step (4)
The detailed process sampled on the net are as follows: using mysterious sampler's online shopping matching system, from n sale of generation link according to
Sequencing buys sample, until n.
A kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, which is characterized in that the step (3)
The determination step of middle sampling plan are as follows:
3.1) the priori estimates P of overall percent defective is determined；
3.2) confidence level 1- α and absolute evaluated error e are determined；
The value of confidence level 1- α is greater than or equal to 95%, and the value of absolute evaluated error e is not higher than 3%；
3.3) sampling samples amount n is determined；
3.4) it determines the methods of sampling, i.e., is sampled in Sampling Frame according to simple random sampling method；The specific steps are,
A distribution chains all in Sampling Frame) are tapped into row serial number；
B) as total L of the sampling samples amount n less than effectively sale link, then n distribution chain is randomly selected from Sampling Frame
It connects；If sample size n is greater than or equal to effectively sale links total number L, first extract all L sale link [n/L] it is secondary, then from
L sale link of n- [n/L] is randomly selected in Sampling Frame；Wherein, [n/L] indicates the maximum integer for being not more than n/L；
C) any one sale randomly selected is linked, needs to randomly select one or more productions according to product testing
Product, as a sample.
A kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, it is characterised in that: the mystery
Sampler's online shopping matching sampling system includes buyer personage's portrait management module and type of merchandize management module, and system is according to institute
Buyer personage's portrait that the category attribute selection of product of sampling matches with such product.
A kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, which is characterized in that the step (6)
The percent defective of middle sample and the specific calculating step of confidence interval are as follows:
The first step calculates the percent defective of sampleCalculation formula is as follows,
In formula: d, the quantity of failed test sample in sample；N, sampling samples amount；
Second step calculates the confidence interval of the percent defective of sample at confidence level 1- α；The rejected product of sample
The confidence interval calculation formula of rate is,
In formula:The percent defective of sample；
1- α, confidence level；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken；
Third step calculates the accepted product percentage of sample；
The calculation formula of the accepted product percentage of sample is, sample
4th step calculates the confidence interval of the accepted product percentage of sample at confidence level 1- α；
The calculation formula of the confidence interval of the accepted product percentage of sample is,
In formula,The percent defective of sample；
1- α, confidence level；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken.
A kind of product methods of sampling of reflection online shopping customer quality experience above-mentioned, which is characterized in that the step
3.1) method of the priori estimates P of overall percent defective in are as follows: for the target sample sampled for the first time, do not conform to totally
The priori estimates P of lattice product rate is 50%；For carrying out second or more the target sample sampled, when above single sample, is obtained
The percent defective of the sample arrivedPriori estimates P as this overall percent defective.
The product methods of sampling of a kind of reflection online shopping customer quality experience above-mentioned, which is characterized in that in step 3.3)
The circular of sampling samples amount n are as follows:
Step 1 calculates initially estimate sample size as follows；
In formula: n ' initially estimates sample size；P, the priori estimates of overall percent defective；1- α, confidence level；
u1-α/2, the quantile of 1- α/2 of standardized normal distribution；E, the absolute error boundary of product percent defective estimation；
Step 2 is modified using unit product sum N included in sample totality, obtains revised sample size,
Calculation formula are as follows:
nx, revised sample size；N, the sum of unit product included in sample totality；
Step 3: sampling samples amount n, i.e. n=n are determinedx。
Compared with prior art, the present invention passes through the mutual cooperation between each step, the sampling of Lai Shixian online shopping product
And inspection, it is easy to operate, it is high-efficient, additionally it is possible to guarantee the reliability of sampling results；The present invention is led to according to the characteristic of shopping at network
Reasonable computation is crossed to determine sampling plan, provides the determination basis of sampling plan for sampling observation personnel, is taken out so as to effectively improve
The reasonability of sample Scheme Choice, and then the reliability of sampling results can greatly be improved；Meanwhile pumping is determined using this method
Sample prescription case, additionally it is possible to reduce sampling samples amount, reduce online shopping cost, improve sampling efficiency.Moreover, sample is adopted during sampling
It is sampled, can be drawn a portrait according to merchandise classification Auto-matching buyer personage with mysterious sampler's online shopping sampling system, thus
Normal consumer progress online shopping can be simulated prevents seller from practising fraud close to consumer, further passes through the true of sampling product
Property, guarantee the reliability of sampling results.In conclusion the present invention has the characteristics that sampling results reliability can be effectively improved.
Specific embodiment
Below with reference to embodiment, the present invention is further illustrated, but is not intended as the foundation limited the present invention.
A kind of embodiment 1: product methods of sampling of reflection online shopping customer quality experience, comprising the following steps:
(1) target sample is determined；
(2) sampled population and building Sampling Frame are determined；
(3) sampling plan is determined；
(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount is n；
(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；
(6) percent defective and confidence interval of sample are calculated.
The step (1) also needs to be selected to reflect sampling pair according to fixed target sample after target sample determines
Mass property as the quality index of product quality situation, as target sample.
The mass property of target sample: including brand, material, content, function, the place of production, style, charging modes, battery class
Type etc..
Sampled population is determined in the step (2) and constructs Sampling Frame method particularly includes:
2.1) according to fixed target sample, corresponding one or more e-commerce platforms are selected；
2.2) the setting search key relevant to target sample and mass property on selected e-commerce platform, is adopted
Collect all relevant sale links；
2.3) capable processing is tapped into distribution chain, rejects the link extremely of repeated links, price and other does not meet sampling pair
As the invalid sale link required with mass property, the total quantity for obtaining effectively selling link is L；By effective sale link
Total quantity is L overall as sample, and unit product sum included in sample totality is N；
When practical operation, since e-commerce stockpile number can not determine its authenticity, so we refer to be
The sales volume that the sales volume that the product of the valid link has been sold, i.e. unit product sum are the product；
Sales volume is bigger, and the ratio to be sampled is more, in accordance with fair and random principle when sampling, to be able to reflect product matter
For the purpose of measuring overall condition, but the product big to sales volume is given priority to, and sales volume is bigger, consumer to the impression of this product and
It, more can be close to consumer's actual experience using more.
2.4) whole effective sale links is arranged and forms a register library, as Sampling Frame.
The specific calculating step of the disqualification rate of sample in step (6) are as follows:
The first step calculates the percent defective of sampleCalculation formula is as follows,
In formula: d, the quantity of failed test sample in sample；N, sampling samples amount；
Second step calculates the confidence interval of the percent defective of sample at confidence level 1- α；The rejected product of sample
The confidence interval calculation formula of rate is,
In formula:The percent defective of sample；
1- α, confidence level；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken；
Third step calculates the accepted product percentage of sample；
The calculation formula of the accepted product percentage of sample is, sample
4th step calculates the confidence interval of the accepted product percentage of sample at confidence level 1- α；
The calculation formula of the confidence interval of the accepted product percentage of sample is,
In formula,--- the rejected product of sample
Rate；1- α-confidence level；u1-α/2The quantile of 1- α/2 of-standardized normal distribution；N-sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken.
The determination step of sampling plan in the step (3) are as follows:
3.1) the priori estimates P of overall percent defective is determined；
3.2) confidence level 1- α and absolute evaluated error e are determined；
The value of confidence level 1- α is greater than or equal to 95%, and the value of absolute evaluated error e is not higher than 3%；
3.3) sampling samples amount n is determined；
3.4) it determines the methods of sampling, i.e., is sampled in Sampling Frame according to simple random sampling method；The specific steps are,
A distribution chains all in Sampling Frame) are tapped into row serial number；
B) as total L of the sampling samples amount n less than effectively sale link, then n distribution chain is randomly selected from Sampling Frame
It connects；If sample size n is greater than or equal to effectively sale links total number L, first extract all L sale link [n/L] it is secondary, then from
L sale link of n- [n/L] is randomly selected in Sampling Frame；Wherein, [n/L] indicates the maximum integer for being not more than n/L；
C) any one sale randomly selected is linked, needs to randomly select one or more productions according to product testing
Product, as a sample.
The method of the priori estimates P of overall percent defective in the step 3.1) are as follows: for what is sampled for the first time
Target sample, the priori estimates P of overall percent defective are 50%；For carrying out second or more the sampling pair sampled
As the percent defective of the sample obtained when, the above single samplePriori estimates as this overall percent defective
P。
The circular of sampling samples amount n in step 3.3) are as follows:
Step 1 calculates initially estimate sample size as follows；
In formula: n ' initially estimates sample size；P, the priori estimates of overall percent defective；1- α, confidence level；
u1-α/2, the quantile of 1- α/2 of standardized normal distribution；E, the absolute error boundary of product percent defective estimation；
Step 2 is modified using unit product sum N included in sample totality, obtains revised sample size,
Calculation formula are as follows:
nx, revised sample size；N, the sum of unit product included in sample totality；
Step 3: sampling samples amount n, i.e. n=n are determinedx。
The detailed process that the step (4) is sampled on the net are as follows: using mysterious sampler's online shopping matching system, from generation
N sale link according to sequencing buy sample, until n.
Mysterious sampler's online shopping matching sampling system includes buyer personage's portrait management module and type of merchandize
Management module, system are drawn a portrait according to the selection of the category attribute for the product of being sampled and the buyer personage that such product matches.
The value of confidence level 1- α is 95%-99%, and the value of absolute evaluated error e is 1%-3%, confidence level and
The specific value of absolute evaluated error is related with sampling observation funds, and the numerical value of higher, the absolute evaluated error of confidence level is lower, sampling observation
Total amount is higher.
A kind of embodiment 2: product methods of sampling of reflection online shopping customer quality experience, comprising the following steps:
(1) target sample is determined；
(2) sampled population and building Sampling Frame are determined；
(3) sampling plan is determined；
(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount is n；
(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；
(6) percent defective and confidence interval of sample are calculated.
The step (1) also needs to be selected to reflect sampling pair according to fixed target sample after target sample determines
Mass property as the quality index of product quality situation, as target sample.
Sampled population is determined in the step (2) and constructs Sampling Frame method particularly includes:
2.1) according to fixed target sample, corresponding one or more e-commerce platforms are selected；
2.2) the setting search key relevant to target sample and mass property on selected e-commerce platform, is adopted
Collect all relevant sale links；
2.3) capable processing is tapped into distribution chain, rejects the link extremely of repeated links, price and other does not meet sampling pair
As the invalid sale link required with mass property, the total quantity for obtaining effectively selling link is L；By effective sale link
Total quantity is L overall as sample, and unit product sum included in sample totality is N (the referred to as quantity of sample totality
N)；
2.4) whole effective sale links is arranged and forms a register library, as Sampling Frame.
The determination step of sampling plan in the step (3) are as follows:
3.1) the priori estimates P of overall percent defective is determined；
The method of the priori estimates P of overall percent defective are as follows: for the target sample sampled for the first time, totally not
The priori estimates P of accepted product percentage is 50%；For carrying out second or more the target sample sampled, when the above single sample
The percent defective of obtained samplePriori estimates P as this overall percent defective.
3.2) confidence level 1- α and absolute evaluated error e are determined；
The value of confidence level 1- α is 95%, and the value of absolute evaluated error e is 3%；
3.3) sampling samples amount n is determined；
3.4) determine the methods of sampling, i.e., in Sampling Frame according to simple random sampling method (simple random sampling refer to from
N unit product is extracted in sample totality and constitutes sample, and the possibility combination for keeping n unit product all has equal be pumped to generally
The sampling of rate) it is sampled；The specific steps are,
A distribution chains all in Sampling Frame) are tapped into row serial number；
B) as total L of the sampling samples amount n less than effectively sale link, then n distribution chain is randomly selected from Sampling Frame
It connects；If sample size n is greater than or equal to effectively sale links total number L, first extract all L sale link [n/L] it is secondary, then from
L sale link of n- [n/L] is randomly selected in Sampling Frame；Wherein, [n/L] indicates the maximum integer for being not more than n/L；
C) any one sale randomly selected is linked, needs to randomly select one or more productions according to product testing
Product, as a sample.
Under conditions of 95% confidence level and absolute evaluated error 3%, sampling samples amount n is according in step 3.3
The priori estimates P of the quantity N of determining sample totality, overall percent defective, choose from table 1.
1. sampling samples amount n inquiry table of table
The detailed process that the step (4) is sampled on the net are as follows: using mysterious sampler's online shopping matching system, from generation
N sale link according to sequencing buy sample, until n.
Mysterious sampler's online shopping matching sampling system includes buyer personage's portrait management module and type of merchandize
Management module, system are drawn a portrait according to the selection of the category attribute for the product of being sampled and the buyer personage that such product matches.
The specific calculating step of the disqualification rate of sample in step (6) are as follows:
The first step calculates the percent defective of sampleCalculation formula is as follows,
In formula: d, the quantity of failed test sample in sample；N, sampling samples amount；
Second step calculates the confidence interval of the percent defective of sample at confidence level 1- α；The rejected product of sample
The confidence interval calculation formula of rate is,
In formula:The percent defective of sample；
1- α, confidence level；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken；
Third step calculates the accepted product percentage of sample；
The calculation formula of the accepted product percentage of sample is, sample
4th step calculates the confidence interval of the accepted product percentage of sample at confidence level 1- α；
The calculation formula of the confidence interval of the accepted product percentage of sample is,
In formula,The percent defective of-sample；
1- α-confidence level；u1-α/2The quantile of 1- α/2 of-standardized normal distribution；N-sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken.
Embodiment 3: it by taking children's garment as an example, is sampled.
The following steps are included:
(1) determine that children's garment are target sample；
(2) sampled population and building Sampling Frame are determined；Sale link 27500 is obtained from the search of electric business platform, to sale
Link is pre-processed, and the invalid links such as repeated links, price extremely link are rejected, and obtains effectively selling connection 27000；Sample
The quantity of this totality is calculated according to the summation that all sale link corresponding product quantity on sale, and result is 27000, i.e. N=
27000, fall in (2000030000] in range.
(3) sampling plan is determined；Determine that the priori estimates P of totality percent defective is 20%, confidence level 1- α is
95%, absolute evaluated error e are 3%；Consult table 1, obtaining sampling samples amount n is 667；
(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount n；
(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；It is detected, is obtained
The quantity of failed test sample into sample are as follows: d=126；
(6) percent defective and confidence interval of sample are calculated.
The detailed process that the step (4) is sampled on the net are as follows: using mysterious sampler's online shopping matching system, from generation
N sale link according to sequencing buy sample, until n.
Mysterious sampler's online shopping matching sampling system includes buyer personage's portrait management module and type of merchandize
Management module, system are drawn a portrait according to the selection of the category attribute for the product of being sampled and the buyer personage that such product matches.
The specific calculating step of the disqualification rate of sample in step (6) are as follows:
The first step calculates the percent defective of sampleCalculation formula are as follows:In formula: d is in sample
The quantity of failed test sample；N is sampling samples amount；Calculated result are as follows:
Second step calculates the confidence interval of the percent defective of sample under confidence level 1- α=95%；Sample is not
The confidence interval calculation formula of accepted product percentage are as follows:
In formula:The percent defective of sample；1- α, confidence level；u1-α/ 2, the quartile of 1- α/2 of standardized normal distribution
Point；N, sampling samples amount；
Calculated result are as follows:
(18.89%-2.97%, 18.89%+2.97%)=(15.92%, 21.86%)；
Third step calculates the accepted product percentage of sample；
The calculation formula of the accepted product percentage of sample are as follows:
SampleIn formula,For percent defective；
4th step calculates the confidence interval of the accepted product percentage of sample under confidence level 1- α=95%；The qualified product of sample
The calculation formula of the confidence interval of rate are as follows:
In formula:For the percent defective of sample；
1- α is confidence level；u1-α/2For the quantile of 1- α/2 of standardized normal distribution；N is sampling samples amount；Calculated result are as follows:
(100%-21.86%, 100%-15.92%)=(78.14%, 84.08%).
Claims (9)
1. a kind of product methods of sampling of reflection online shopping customer quality experience, which comprises the following steps:
(1) target sample is determined；
(2) sampled population and building Sampling Frame are determined；
(3) sampling plan is determined；
(4) online sampling is implemented according to sampling plan, obtains sampling samples, sampling samples amount is n；
(5) quality testing is carried out to sampling samples, obtains the quantity d of the failed test sample in sampling samples；
(6) percent defective and confidence interval of sample are calculated.
2. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 1, it is characterised in that:
The step (1) also needs to be selected to reflect target sample product matter according to fixed target sample after target sample determines
The quality index of amount situation, the mass property as target sample.
3. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 1, which is characterized in that
Sampled population is determined in the step (2) and constructs Sampling Frame method particularly includes:
2.1) according to fixed target sample, corresponding one or more e-commerce platforms are selected；
2.2) the setting search key relevant to target sample and mass property on selected e-commerce platform, acquires institute
There is relevant sale to link；
2.3) capable processing tapped into distribution chain, reject the link extremely of repeated links, price and other do not meet target sample and
The invalid sale link that mass property requires, the total quantity for obtaining effectively selling link is L；By the total quantity of effective sale link
Overall as sample for L, unit product sum included in sample totality is N；
2.4) whole effective sale links is arranged and forms a register library, as Sampling Frame.
4. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 1, it is characterised in that:
The detailed process that the step (4) is sampled on the net are as follows: using mysterious sampler's online shopping matching system, from n pin of generation
It sells in link and buys sample according to sequencing, until n.
5. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 3, which is characterized in that
The determination step of sampling plan in the step (3) are as follows:
3.1) the priori estimates P of overall percent defective is determined；
3.2) confidence level 1- α and absolute evaluated error e are determined；
The value of confidence level 1- α is greater than or equal to 95%, and the value of absolute evaluated error e is not higher than 3%；
3.3) sampling samples amount n is determined；
3.4) it determines the methods of sampling, i.e., is sampled in Sampling Frame according to simple random sampling method；The specific steps are,
A distribution chains all in Sampling Frame) are tapped into row serial number；
B) as total L of the sampling samples amount n less than effectively sale link, then n sale link is randomly selected from Sampling Frame；If
Sample size n is greater than or equal to effectively sale links total number L, then first extracting all L sale, to link [n/L] secondary, then from Sampling Frame
In randomly select n- [n/L] L sale link；Wherein, [n/L] indicates the maximum integer for being not more than n/L；
C) any one sale randomly selected is linked, needs to randomly select one or more products according to product testing,
As a sample.
6. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 4, it is characterised in that:
Described mysterious sampler's online shopping matching sampling system includes that buyer personage draws a portrait management module and type of merchandize management module,
System is drawn a portrait according to the selection of the category attribute for the product of being sampled and the buyer personage that such product matches.
7. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 5, which is characterized in that
The specific calculating step of the percent defective of sample and confidence interval in the step (6) are as follows:
The first step calculates the percent defective of sampleCalculation formula is as follows,
In formula: d, the quantity of failed test sample in sample；N, sampling samples amount；
Second step calculates the confidence interval of the percent defective of sample at confidence level 1- α；The percent defective of sample
Confidence interval calculation formula is,
In formula:The percent defective of sample；1- α,
Confidence level；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken；
Third step calculates the accepted product percentage of sample；
The calculation formula of the accepted product percentage of sample is, sample
4th step calculates the confidence interval of the accepted product percentage of sample at confidence level 1- α；
The calculation formula of the confidence interval of the accepted product percentage of sample is,
In formula,The percent defective of sample；1- α, sets
Letter is horizontal；u1-α/2, the quantile of 1- α/2 of standardized normal distribution；N, sampling samples amount；
When the calculated result in formula is less than 0,0 is taken；When the calculated result in formula is greater than 1,1 is taken.
8. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 5, which is characterized in that
The method of the priori estimates P of overall percent defective in the step 3.1) are as follows: for the target sample sampled for the first time,
The priori estimates P of overall percent defective is 50%；For carrying out second or more the target sample sampled, with the last time
The percent defective of the sample obtained when samplingPriori estimates P as this overall percent defective.
9. a kind of product methods of sampling of reflection online shopping customer quality experience according to claim 5, which is characterized in that
The circular of sampling samples amount n in step 3.3) are as follows:
Step 1 calculates initially estimate sample size as follows；
In formula: n ' initially estimates sample size；P, the priori estimates of overall percent defective；1- α, confidence level；u1-α/2, mark
The quantile of 1- α/2 of quasi normal distribution；E, the absolute error boundary of product percent defective estimation；
Step 2 is modified using unit product sum N included in sample totality, obtains revised sample size, is calculated
Formula are as follows:
nx, revised sample size；N, the sum of unit product included in sample totality；
Step 3: sampling samples amount n, i.e. n=n are determinedx。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811378800.1A CN109559199A (en) | 2018-11-19 | 2018-11-19 | A kind of product methods of sampling of reflection online shopping customer quality experience |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811378800.1A CN109559199A (en) | 2018-11-19 | 2018-11-19 | A kind of product methods of sampling of reflection online shopping customer quality experience |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109559199A true CN109559199A (en) | 2019-04-02 |
Family
ID=65866481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811378800.1A Pending CN109559199A (en) | 2018-11-19 | 2018-11-19 | A kind of product methods of sampling of reflection online shopping customer quality experience |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109559199A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111898924A (en) * | 2020-08-13 | 2020-11-06 | 中国人民解放军海军航空大学 | Comprehensive evaluation method and system for testability use of equipment |
| CN112749888A (en) * | 2020-12-31 | 2021-05-04 | 浙江省方大标准信息有限公司 | Random sample consensus (RANSAC) algorithm-based multivariate random spot check method, system and device |
| WO2021179957A1 (en) * | 2020-03-11 | 2021-09-16 | 中国标准化研究院 | Method and device for determining product use quality or performance |
| CN117634988A (en) * | 2024-01-25 | 2024-03-01 | 中国标准化研究院 | Commodity qualification sampling inspection method and system based on priori information |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030018501A1 (en) * | 2001-05-04 | 2003-01-23 | Shan Jerry Z. | Adaptive testing for conversion-related estimates relevant to a network accessible site |
| CN105590176A (en) * | 2016-03-07 | 2016-05-18 | 杭州国家电子商务产品质量监测处置中心 | Product quality risk monitoring sampling method based on Internet |
-
2018
- 2018-11-19 CN CN201811378800.1A patent/CN109559199A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030018501A1 (en) * | 2001-05-04 | 2003-01-23 | Shan Jerry Z. | Adaptive testing for conversion-related estimates relevant to a network accessible site |
| CN105590176A (en) * | 2016-03-07 | 2016-05-18 | 杭州国家电子商务产品质量监测处置中心 | Product quality risk monitoring sampling method based on Internet |
Non-Patent Citations (2)
| Title |
|---|
| 同济大学数学系: "《应用统计》", 30 June 2016 * |
| 杨贵军等: "《应用抽样技术》", 31 August 2015 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021179957A1 (en) * | 2020-03-11 | 2021-09-16 | 中国标准化研究院 | Method and device for determining product use quality or performance |
| CN111898924A (en) * | 2020-08-13 | 2020-11-06 | 中国人民解放军海军航空大学 | Comprehensive evaluation method and system for testability use of equipment |
| CN112749888A (en) * | 2020-12-31 | 2021-05-04 | 浙江省方大标准信息有限公司 | Random sample consensus (RANSAC) algorithm-based multivariate random spot check method, system and device |
| CN112749888B (en) * | 2020-12-31 | 2023-10-03 | 浙江省标准化研究院(金砖国家标准化(浙江)研究中心、浙江省物品编码中心) | Multi-element random spot check method, system and device based on RANSAC algorithm |
| CN117634988A (en) * | 2024-01-25 | 2024-03-01 | 中国标准化研究院 | Commodity qualification sampling inspection method and system based on priori information |
| CN117634988B (en) * | 2024-01-25 | 2024-04-12 | 中国标准化研究院 | Commodity qualification sampling inspection method and system based on priori information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109559199A (en) | A kind of product methods of sampling of reflection online shopping customer quality experience | |
| CN110874778B (en) | Abnormal order detection method and device | |
| CN108038696B (en) | Method and system for detecting bill swiping based on equipment identification code and social group information | |
| US9773275B2 (en) | Profiling auction assets and/or participants to predict auction outcome | |
| CN111898029A (en) | Internet-based online shopping product recommendation system | |
| CN106897883A (en) | One kind automation commodity sampling observation method and system | |
| CN109993544A (en) | Data processing method, system, computer system and computer readable storage medium | |
| CN115187065A (en) | Garment commodity quality analysis system based on electronic commerce platform | |
| CN103309885B (en) | The method and device and searching method and device of a kind of identification feature user in electronic trade platform | |
| CN115761457A (en) | Commodity identification method and device, electronic equipment and computer readable medium | |
| CN114493208A (en) | Method and device for evaluating engineering project full life cycle, electronic equipment and medium | |
| CN110046934A (en) | A kind of idle clothing valuation system and method based on data mining | |
| Domashova et al. | Application of machine learning methods for risk analysis of unfavorable outcome of government procurement procedure in building and grounds maintenance domain | |
| KR20210094966A (en) | Goods trading system with improved reliability via on-line, and method using the same | |
| CN107292660A (en) | A kind of jewelry artwork Valuation Method and system based on big data | |
| CN110163696A (en) | A kind of electric business shopping air navigation aid and its system based on big data | |
| CN111612630A (en) | Multi-item fund financing account profit and loss calculation method and device | |
| CN115936819A (en) | Commodity scoring system and establishment method | |
| CN115423631A (en) | Trading member scoring method and system based on trading data of industrial internet platform | |
| CN108629542B (en) | Logistics distribution-based return and exchange information synchronization method, device and equipment | |
| CN112581188A (en) | Construction method, prediction method and model of engineering project bid quotation prediction model | |
| CN111415328A (en) | Article analysis data determination method and device and electronic equipment | |
| CN116308466B (en) | Data information acquisition and intelligent analysis method, system, equipment and storage medium | |
| TWI852593B (en) | Credit scoring model evaluation method and computing device thereof | |
| CN109636111A (en) | A kind of method and system of determining enterprise's income pin item diversity factor |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190402 |