CN108154396A - A kind of reagent consumptive material intelligently pushing method in biology research experiments platform - Google Patents
A kind of reagent consumptive material intelligently pushing method in biology research experiments platform Download PDFInfo
- Publication number
- CN108154396A CN108154396A CN201711434762.2A CN201711434762A CN108154396A CN 108154396 A CN108154396 A CN 108154396A CN 201711434762 A CN201711434762 A CN 201711434762A CN 108154396 A CN108154396 A CN 108154396A
- Authority
- CN
- China
- Prior art keywords
- product
- reagent
- user
- consumptive material
- platform
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention discloses a kind of reagent consumptive material intelligently pushing method in biological research experiments platform, the method includes：Corresponding label is set to each reagent consumable product；Using content-based recommendation algorithm, to newly registering the reagent consumable product of platform, pass through the Product labelling of reagent consumptive material, the similarity of statistical product；According to the similarity of product, the product information was pushed to user that is previous browsed or buying similar products；It solves existing deficiency, realizes the technique effect that reagent consumptive material is pushed to researcher for being capable of precise and high efficiency.
Description
Technical field
The present invention relates to reagent consumptive material fields, and in particular, to the reagent consumptive material intelligence in a kind of biology research experiments platform
It can method for pushing.
Background technology
Reagent consumptive material is to be engaged in the ordinary articles of life science personnel development experiment and be related to scientific experiment to be
One important process of no correctness, lab assistant safety and carrying capacity of environment.Due to reagent consumptive material broad categories, update
Variation is fast, single-piece price difference is larger, how to obtain valuable, practicability reagent consumable information, how to buy reliable in quality
Reagent consumptive material, how expedited purchase is a urgent problem to be solved.
The researcher of life science is currently undertaken by when purchasing reagent consumptive material, typically using universal electric store
Browsing, the mode searched, find corresponding reagent consumable product and agent, directly contact purchase under purchase or line.At present
Reagent consumptive material platform on line does not all provide intelligent personalized proposed algorithm, generally just only enumerates common reagent consumable information.
In the prior art, the selection of the reagent consumptive material in biological scientific experiment is mainly consumed by researcher in numerous reagents
Manual artificial selection is carried out in material, it is less efficient, and be not easy accurately to choose best reagent consumptive material.
Invention content
The present invention provides a kind of reagent consumptive material intelligently pushing methods in biological research experiments platform, solve existing
Deficiency realizes the technique effect that reagent consumptive material is pushed to researcher for being capable of precise and high efficiency.
For achieving the above object, this application provides the reagent consumptive materials in a kind of biological research experiments platform intelligently to push away
Delivery method, the method includes：
Corresponding label is set to each reagent consumable product；
Using content-based recommendation algorithm, to newly registering the reagent consumable product of platform, pass through the production of reagent consumptive material
Product label, the similarity of statistical product；
According to the similarity of product, the product information was pushed to user that is previous browsed or buying similar products.
Further, push mode includes but not limited to：Short message, mail, wechat.
Further, corresponding label is set to each reagent consumable product, specifically includes：
The characteristic information of each reagent consumable product, feature based information generation key combination, based on pass are extracted first
The corresponding label of key word combination producing.
Further, the method is applied in biological research experiments platform, when quantity on order is less than the first threshold in platform
When being worth, and browsing amount of collection higher than second threshold, using following recommendation process：
Collection of the field user to reagent consumable product is counted by direction of scientific rersearch, it is similar between statistical product
Degree；
When user browses reagent consumable product details, using the collaborative filtering based on article, product similarity
The product for meeting preset condition is shown in the recommendation column of current reagent consumable product, and recommended user browses like product.
Further, the method is applied in biological research experiments platform, when platform order is more than first threshold, adopts
With following recommendation process：
Common reagent consumable product is counted under same classification as recommended products library；
By the scoring of geographic coverage and direction of scientific rersearch statistics different user to each product in recommended products library, user is built
Rating matrix；
Using the proposed algorithm based on matrix decomposition, the rating matrix after study is calculated using stochastic gradient descent method；
When user browses reagent consumable product, according to the user location and direction of scientific rersearch, according to commenting after study
Sub-matrix, selection score satisfactory several Products Shows to user.
Wherein, proposed algorithm is exactly some behaviors using user, passes through some mathematical algorithms, thus it is speculated that going out user may like
Joyous thing.Proposed algorithm includes many types, mainly includes：Algorithm, collaborative filtering based on popularity, based on content
Algorithm, the algorithm based on model, hybrid algorithm etc..
Used in this application is content-based recommendation algorithm, collaborative filtering and the proposed algorithm (base based on model
In the proposed algorithm of matrix decomposition be a kind of algorithm therein).
1st, the proposed algorithm based on content (content-based), mainly according to the similitude between recommendation items property.
2nd, the proposed algorithm based on collaborative filtering (collaborative filtering), Main Basiss be user or
Similitude between person.
The measure of similitude generally uses：Euclidean distance and cosine similarity.
Euclidean distance：Euclidean distance between two n-dimensional vector a (x11, x12 ..., x1n) and b (x21, x22 ..., x2n)：
d12Represent the Euclidean distance between vector a and vector b.
Cosine similarity：It, can be with for two n dimension sample point a (x11, x12 ..., x1n) and b (x21, x22 ..., x2n)
The similarity degree between them is weighed using the concept similar to included angle cosine：
Cos (θ) represents the similarity between sample a and sample b.
3rd, the proposed algorithm based on matrix decomposition：
During matrix decomposition, original rating matrix Rm × n is resolved into multiplying for two matrixes Pm × k and Qk × n
Product：
Rm×nRepresent original rating matrix, R^m×nRepresent the rating matrix by being rebuild after returning, Pm×kAnd Qk×n
For two matrixes decomposed after recurrence, and Pm×kAnd Qk×nMatrix multiple is equal to R^m×n。
How each element of solution matrix Pm × k and Qk × n, it is possible to the regression problem being converted in machine learning
It is solved.
(1) loss function is defined
Using the error between original rating matrix Rm × n and the rating matrix R^m × n rebuild square as
Loss function, i.e.,：
e2 i,jRepresent loss function, the difference square of rating matrix rebuild for original rating matrix and after returning.
Finally, need to solve the minimum value of the sum of all losses of non-"-" item：
Min loss are the minimum value of all loss functions.
(2) gradient, which declines, solves
Solve the negative gradient of loss function：
Respectively loss function e2 i,jTo pi,k、qk,jPartial derivative.
According to the direction of negative gradient more new variables：
It is that P is updated according to negative gradient respectivelym×kAnd Qk×n, it is iterated.
By iteration, until algorithm is finally restrained.
(3) prediction is recommended
Using above-mentioned process, matrix Pm × k and Qk × n can be obtained, in this way can be user i to commodity j carry out
Marking is recommended further according to marking height.
The formula of marking：
For the rating matrix rebuild after recurrence, each value is Pm×kAnd Qk×nCorresponding matrix multiple.
One or more technical solutions that the application provides, have at least the following technical effects or advantages：
It solves existing deficiency, realizes the technology that reagent consumptive material is pushed to the researcher effect for being capable of precise and high efficiency
Fruit.
Description of the drawings
Attached drawing described herein is used for providing further understanding the embodiment of the present invention, forms one of the application
Point, do not form the restriction to the embodiment of the present invention；
Fig. 1 is the flow diagram of the reagent consumptive material intelligently pushing method in biological research experiments platform in the application.
Specific embodiment
The present invention provides a kind of reagent consumptive material intelligently pushing methods in biological research experiments platform, solve existing
Deficiency realizes the technique effect that reagent consumptive material is pushed to researcher for being capable of precise and high efficiency.
It is to better understand the objects, features and advantages of the present invention, below in conjunction with the accompanying drawings and specific real
Mode is applied the present invention is further described in detail.It should be noted that in the case where not conflicting mutually, the application's
Feature in embodiment and embodiment can be combined with each other.
Many details are elaborated in the following description to facilitate a thorough understanding of the present invention, still, the present invention may be used also
To be implemented using other different from the other modes in the range of being described herein, therefore, protection scope of the present invention is not by under
The limitation of specific embodiment disclosed in face.
It please refers to Fig.1, this application provides a kind of reagent consumptive material intelligently pushing method in biological research experiments platform, packets
It includes：
Step 1：Corresponding label is set to each reagent consumable product；
Such as the label of " Aurum tm total serum IgE X Mini Kits " is BIO-RAD, quantitative fluorescent PCR, RNA extraction.It is " thin
The label of born of the same parents/tissue gene group DNA extraction kit (centrifugation column type) (with Proteinase K) " is hundred Tykes, gene cloning, DNA are carried
It takes.
The label of product " RNAprep pure cultivate cell/bacterium total RNA extraction reagent box " newly registered is Tiangeng, glimmering
Fluorescent Quantitative PCR, RNA extractions.
Step 2：To newly registering the reagent consumable product of platform, by the Product labelling of reagent consumptive material, statistical product
Similarity.According to the similarity of product, the product information was pushed to user that is previous browsed or buying similar products.
Using Euclidean distance or cosine similarity come the similarity of statistical product.For the product " RNAprep newly registered
Pure cultivates cell/bacterium total RNA extraction reagent box ", it is higher with the similarity of " Aurum tm total serum IgE X Mini Kits ".
Therefore, " RNAprep is pushed to the once user of purchase or browsed " Aurum tm total serum IgE X Mini Kits " product
Pure cultivates cell/bacterium total RNA extraction reagent box " product information.
Recommendation process when the 2nd, browsing product in biological research experiments platform is described as follows：
1st, when order is less, browsing collection is more in platform, using following recommendation process：
(1) collection of the field user to reagent consumable product is counted by direction of scientific rersearch, the phase between statistical product
Like degree；
(2) it is using the collaborative filtering based on article, product is similar when user browses reagent consumable product details
The higher product of degree is shown in the recommendation column of current reagent consumable product, and recommended user browses like product.
It is as follows：
Step 1：Collection of the field user to reagent consumable product is counted by direction of scientific rersearch, between statistical product
Similarity；
Such as " molecule experiments service " directional statistics field scientific research clients to the collection feelings of reagent consumable product
Condition.Such as user 1 has collected " the first chains of miRNA cDNA synthetic agent box "；The collection of user 2 " the first chains of miRNA cDNA conjunction
Into kit ", " FastKing cDNA the first chain synthetic agent box (removing genome) ", " RNAprep pure cultures cell/thin
Bacterium total RNA extraction reagent box "；User 3 has collected " the first chains of miRNA cDNA synthetic agent box ", " RNAprep pure cultures
Cell/bacterium total RNA extraction reagent box ".The similarity of collection product is calculated using cosine similarity, can be calculated
" the first chains of miRNA cDNA synthetic agent box " and " RNAprep pure cultivate cell/bacterium total RNA extraction reagent box " this two
The similarity of a product is higher.
Step 2：When user browses reagent consumable product details, the higher product of product similarity is shown in current examination
User is recommended in the recommendation column of agent consumable product.
For user when browsing " the first chains of miRNA cDNA synthetic agent box " product details, platform automatically can be by product
" RNAprep pure cultivate cell/bacterium total RNA extraction reagent box " is placed on bottom and recommends column, and guiding user browses related production
Product.
2nd, when platform order is more, using following recommendation process：
(1) common reagent consumable product is counted under same major class as recommended products library；
(2) by the scoring of geographic coverage and direction of scientific rersearch statistics different user to each product in recommended products library, structure
User's rating matrix；
(3) proposed algorithm based on matrix decomposition is used, the rating matrix after study is calculated using stochastic gradient descent method；
(4) when user browses reagent consumable product, according to the user location and direction of scientific rersearch, after study
Rating matrix, selection score higher several Products Shows to user.
It is as follows：
Step 1：Common reagent consumable product is counted under same major class as recommended products library；
Step 2：Scoring after placing an order according to user's purchase to each product counts different by geographic coverage and direction of scientific rersearch
Scoring of the user to each product in recommended products library builds user's rating matrix；
Such as the scoring square of 5 users to 4 reagent consumable products in " molecule experiments service " direction is engaged in Sichuan province
Battle array (it is 1-5 points to score ,-represent not score) as follows：
Table 1
Step 3：Using the proposed algorithm based on matrix decomposition, the scoring square after study is calculated using stochastic gradient descent method
Battle array；
Such as the rating matrix after reconstruct is as follows：
Table 2
Step 4：When user browses reagent consumable product, according to the user location and direction of scientific rersearch, according to study
Rating matrix afterwards, selection score higher several Products Shows to user.
Such as user 1, when browsing reagent consumable product, platform can be automatically " miRNA cDNA the first chain synthetic agents
Box ", " RNAprep pure cultivate cell/bacterium total RNA extraction reagent box " are placed on bottom and recommend column, and guiding user browses related
Product.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know basic creation
Property concept, then additional changes and modifications may be made to these embodiments.So appended claims be intended to be construed to include it is excellent
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (5)
1. a kind of reagent consumptive material intelligently pushing method in biology research experiments platform, which is characterized in that the method includes：
Corresponding label is set to each reagent consumable product；
Using content-based recommendation algorithm, to newly registering the reagent consumable product of platform, pass through the product mark of reagent consumptive material
Label, the similarity of statistical product；
According to the similarity of product, the product information was pushed to user that is previous browsed or buying similar products.
2. the reagent consumptive material intelligently pushing method in biology scientific experiment according to claim 1, which is characterized in that push
Mode includes but not limited to：Short message, mail, wechat.
3. the reagent consumptive material intelligently pushing method in biology scientific experiment according to claim 1, which is characterized in that every
Kind reagent consumable product sets corresponding label, specifically includes：
The characteristic information of each reagent consumable product, feature based information generation key combination, based on keyword are extracted first
The corresponding label of combination producing.
4. the reagent consumptive material intelligently pushing method in biology scientific experiment according to claim 1, which is characterized in that described
Method is applied in biological research experiments platform, when quantity on order is less than first threshold in platform, and browses amount of collection higher than the
During two threshold values, using following recommendation process：
Collection of the field user to reagent consumable product is counted by direction of scientific rersearch, the similarity between statistical product；
When user browses reagent consumable product details, using the collaborative filtering based on article, product similarity is met
The product of preset condition is shown in the recommendation column of current reagent consumable product, and recommended user browses like product.
5. the reagent consumptive material intelligently pushing method in biology scientific experiment according to claim 1, which is characterized in that described
Method is applied in biological research experiments platform, when platform order is more than first threshold, using following recommendation process：
Common reagent consumable product is counted under same classification as recommended products library；
By the scoring of geographic coverage and direction of scientific rersearch statistics different user to each product in recommended products library, structure user's scoring
Matrix；
Using the proposed algorithm based on matrix decomposition, the rating matrix after study is calculated using stochastic gradient descent method；
When user browses reagent consumable product, according to the user location and direction of scientific rersearch, according to the scoring square after study
Battle array, selection score satisfactory several Products Shows to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711434762.2A CN108154396A (en) | 2017-12-26 | 2017-12-26 | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711434762.2A CN108154396A (en) | 2017-12-26 | 2017-12-26 | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108154396A true CN108154396A (en) | 2018-06-12 |
Family
ID=62462850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711434762.2A Pending CN108154396A (en) | 2017-12-26 | 2017-12-26 | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108154396A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283697A (en) * | 2021-04-21 | 2021-08-20 | 耐优生物技术(上海)有限公司 | Intelligent generation method of experiment system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
| CN103473354A (en) * | 2013-09-25 | 2013-12-25 | 焦点科技股份有限公司 | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform |
| CN103886487A (en) * | 2014-03-28 | 2014-06-25 | 焦点科技股份有限公司 | Individualized recommendation method and system based on distributed B2B platform |
| CN105976229A (en) * | 2016-05-13 | 2016-09-28 | 云南大学 | Collaborative filtering algorithm based on user and project mixing |
| CN105975440A (en) * | 2016-05-05 | 2016-09-28 | 浙江理工大学 | Matrix decomposition parallelization method based on graph calculation model |
| CN106846106A (en) * | 2017-01-16 | 2017-06-13 | 南京师范大学 | A kind of figure builds the matrix decomposition recommendation method under framework |
-
2017
- 2017-12-26 CN CN201711434762.2A patent/CN108154396A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609523A (en) * | 2012-02-10 | 2012-07-25 | 上海视畅信息科技有限公司 | Collaborative filtering recommendation algorithm based on article sorting and user sorting |
| CN103473354A (en) * | 2013-09-25 | 2013-12-25 | 焦点科技股份有限公司 | Insurance recommendation system framework and insurance recommendation method based on e-commerce platform |
| CN103886487A (en) * | 2014-03-28 | 2014-06-25 | 焦点科技股份有限公司 | Individualized recommendation method and system based on distributed B2B platform |
| CN105975440A (en) * | 2016-05-05 | 2016-09-28 | 浙江理工大学 | Matrix decomposition parallelization method based on graph calculation model |
| CN105976229A (en) * | 2016-05-13 | 2016-09-28 | 云南大学 | Collaborative filtering algorithm based on user and project mixing |
| CN106846106A (en) * | 2017-01-16 | 2017-06-13 | 南京师范大学 | A kind of figure builds the matrix decomposition recommendation method under framework |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283697A (en) * | 2021-04-21 | 2021-08-20 | 耐优生物技术(上海)有限公司 | Intelligent generation method of experiment system |
| CN113283697B (en) * | 2021-04-21 | 2023-11-24 | 耐优生物技术(上海)有限公司 | Intelligent generation method of experiment system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105740430B (en) | A kind of personalized recommendation method of mosaic society's information | |
| CN107402993B (en) | The cross-module state search method for maximizing Hash is associated with based on identification | |
| Luo et al. | Application of random matrix theory to biological networks | |
| Qian et al. | Introducing self-organized maps (SOM) as a visualization tool for materials research and education | |
| Chen et al. | Prediction of solvent accessibility and sites of deleterious mutations from protein sequence | |
| Wang et al. | Evolutionary extreme learning machine ensembles with size control | |
| Zhang et al. | A multi-objective evolutionary approach for mining frequent and high utility itemsets | |
| CN106022865A (en) | Goods recommendation method based on scores and user behaviors | |
| CN106202377B (en) | A kind of online collaboration sort method based on stochastic gradient descent | |
| CN108268464A (en) | A kind of personalized recommendation method and device returned based on collaborative filtering and logistic | |
| CN107239993A (en) | A kind of matrix decomposition recommendation method and system based on expansion label | |
| Cintia Ganesha Putri et al. | Design of an unsupervised machine learning-based movie recommender system | |
| CN108563690A (en) | A kind of collaborative filtering recommending method based on object-oriented cluster | |
| CN112102029B (en) | Knowledge graph-based long-tail recommendation calculation method | |
| Khanal et al. | i6ma-stack: a stacking ensemble-based computational prediction of dna n6-methyladenine (6ma) sites in the rosaceae genome | |
| CN112347362A (en) | Personalized recommendation method based on graph self-encoder | |
| Zhao et al. | Improving recommendation accuracy using networks of substitutable and complementary products | |
| Yang et al. | Sixteen years of DNA barcoding in China: What has been done? What can be done? | |
| CN102521420A (en) | Socialized filtering method on basis of preference model | |
| Kovács et al. | Machine-learning prediction of infrared spectra of interstellar polycyclic aromatic hydrocarbons | |
| Chen et al. | DensityPath: an algorithm to visualize and reconstruct cell state-transition path on density landscape for single-cell RNA sequencing data | |
| CN106919699A (en) | A kind of recommendation method for personalized information towards large-scale consumer | |
| Li et al. | Deep forest ensemble learning for classification of alignments of non-coding RNA sequences based on multi-view structure representations | |
| CN108154396A (en) | A kind of reagent consumptive material intelligently pushing method in biology research experiments platform | |
| Vinodkumar et al. | Prediction of sgrna off-target activity in crispr/cas9 gene editing using graph convolution network |
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 |
Application publication date: 20180612 |
|
| RJ01 | Rejection of invention patent application after publication |