CN110428296A - Recommended method, device and the computer readable storage medium of article - Google Patents
Recommended method, device and the computer readable storage medium of article Download PDFInfo
- Publication number
- CN110428296A CN110428296A CN201810868063.7A CN201810868063A CN110428296A CN 110428296 A CN110428296 A CN 110428296A CN 201810868063 A CN201810868063 A CN 201810868063A CN 110428296 A CN110428296 A CN 110428296A
- Authority
- CN
- China
- Prior art keywords
- article
- target user
- service life
- order data
- history order
- 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]
- G06Q30/0631—Item recommendations
Abstract
This disclosure relates to which a kind of recommended method of article, device and computer readable storage medium, are related to technical field of data processing.It is output, training machine learning model with the service life of article this method comprises: being input with the relevant information of the ID of article and the user for buying article；The ID of article in the relevant information of target user and the History Order data of target user is inputted into machine learning model, to obtain the service life of the article in History Order data；According to the service life on nearest the purchase date and the article of the article in History Order data, it is determined whether recommend the article to target user.The technical solution of the disclosure can be improved the accuracy of article recommendation.
Description
Technical field
This disclosure relates to technical field of data processing, the in particular to device and meter of a kind of recommended method of article, article
Calculation machine readable storage medium storing program for executing.
Background technique
In e-commerce field, often need to recommend different articles according to different users, to promote sales volume and user's body
It tests.
The relevant technologies, which are specifically included that, carries out recommendation sequence to article based on sales volume, region, price, time setting weight；It chases after
The article browsed is recommended in the real-time behavior of track user to user；Collaborative filtering based on article, for example, user A and user
B has bought identical items a, and user B has also bought other articles b and article c, then article b and article c can be recommended to user A.
Summary of the invention
Inventor's discovery of the disclosure is above-mentioned, and there are the following problems in the related technology: could not deep layer excavation user demand and object
Internal association between product, the accuracy rate for causing article to be recommended are low.
In consideration of it, can be improved the accuracy rate of article recommendation the present disclosure proposes a kind of recommended technology scheme of article.
According to some embodiments of the present disclosure, a kind of recommended method of article is provided, comprising: with the ID of article and purchase
The relevant information of the user of the article is crossed as input, is output, training machine learning model with the service life of the article；
The ID of article in the relevant information of target user and the History Order data of the target user is inputted into the machine learning
Model, to obtain the service life of the article in the History Order data；According to the article in the History Order data
The service life on purchase date and the article recently, it is determined whether Xiang Suoshu target user recommends the article.
In some embodiments, the nearest purchase date of the article in the History Order data makes plus the article
In the case where being more than current date after the period, Xiang Suoshu target user recommends the article；In the History Order data
In the case that the nearest purchase date of article is plus current date is less than after the service life of the article, do not used to the target
Recommend the article in family.
In some embodiments, according to the History Order data of the relevant information of the target user and the target user
First set is generated, includes the key-value pair being made of the ID of article and the nearest purchase date of the article in the first set；
Second set is generated according to the service life of article in the History Order data, includes the ID by article in the second set
The key-value pair formed with the service life of the article；According to the first set and the second set, determine to target user
The article of recommendation.
In some embodiments, the relevant information include the gender information of user, age information, location message, etc.
It is one or more in grade information, the quantity of purchase article.
In some embodiments, the gender information is handled by one-hot encoding mode.
According to other embodiments of the disclosure, provide a kind of recommendation apparatus of article, comprising: training unit, for
The ID of article and the relevant information for buying the user of the article are input, are output, instruction with the service life of the article
Practice machine learning model；Acquiring unit, for by the History Order data of the relevant information of target user and the target user
In the ID of article input the machine learning model, to obtain the service life of the article in the History Order data；It pushes away
Unit is recommended, for the service life according to nearest the purchase date and the article of the article in the History Order data, is determined
Whether to the target user article is recommended.
In some embodiments, the nearest purchase date of article of the recommendation unit in the History Order data adds
In the case where being more than current date after the service life of the upper article, Xiang Suoshu target user recommends the article, in the history
In the case that the nearest purchase date of article in order data is plus current date is less than after the service life of the article, no
Recommend the article to the target user.
In some embodiments, the recommendation unit is according to the relevant information of the target user and the target user
History Order data generate first set, include the nearest purchase date group of the ID and the article by article in the first set
At key-value pair, second set is generated according to the service life of article in the History Order data, is wrapped in the second set
The key-value pair being made of the ID of article and the service life of the article is included, according to the first set and the second set, really
The article that directional aim user recommends.
According to the other embodiment of the disclosure, a kind of recommendation apparatus of article is provided, comprising: memory；Be coupled to
The processor of the memory, the processor is configured to based on the instruction being stored in the memory device, in execution
State one or more steps in the recommended method of the article in any one embodiment.
According to the still other embodiments of the disclosure, a kind of computer readable storage medium is provided, computer is stored thereon with
Program, the program realize one or more of the recommended method of article in any of the above-described a embodiment when being executed by processor
Step.
In the above-described embodiments, by machine learning method meter obtain user information, article ID and article service life it
Between relational model, according to the model estimate user whether need to buy the article in its History Order again, thus to user
Recommend corresponding article.It records in this way, can be done shopping according to the history of user, the various dimensions information combination user of article to user
Recommend article, to improve the accuracy of article recommendation.
Detailed description of the invention
The attached drawing for constituting part of specification describes embodiment of the disclosure, and together with the description for solving
Release the principle of the disclosure.
The disclosure can be more clearly understood according to following detailed description referring to attached drawing, in which:
Fig. 1 shows the flow chart of some embodiments of the recommended method of the article of the disclosure；
Fig. 2 shows the flow charts of other embodiments of the recommended method of the article of the disclosure；
Fig. 3 shows the flow chart of some embodiments of Fig. 1 or the step 130 in Fig. 2；
Fig. 4 shows the block diagram of some embodiments of the recommendation apparatus of the article of the disclosure；
Fig. 5 shows the block diagram of other embodiments of the recommendation apparatus of the article of the disclosure；
Fig. 6 shows the block diagram of the other embodiment of the recommendation apparatus of the article of the disclosure.
Specific embodiment
The various exemplary embodiments of the disclosure are described in detail now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
Scope of disclosure.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the disclosure
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as authorizing part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
As previously mentioned, the relevant technologies can not excavate the actual demand of user and want the inherent pass between the article bought
Connection.In view of the above-mentioned problems, the disclosure inventor find article have certain service life, to a time point need by
Again it buys, i.e. service life.It is consequently possible to calculate the service life of article is as the foundation for recommending article to user out.
For example, the technical solution of the disclosure can be realized using the following examples.
Fig. 1 shows the flow chart of some embodiments of the recommended method of the article of the disclosure.
As shown in Figure 1, this method comprises: step 110, training machine learning model；Step 120, the use of article is obtained
Period；With step 130, determines and recommend article.
It in step 110, is input with the relevant information of the ID of article and the user for buying the article, with the article
Service life is output, training machine learning model.For example, the relevant information and History Order data of each user can be acquired,
And to the information and the similar merging of data progress that acquisition comes.The relevant information of user may include the gender information of user, age
Information, location message, class information, buy article quantity in it is one or more.
In some embodiments, following matrix X can be constructed:
sku_idnFeature is SKU (Stock Keeping Unit, keeper unit) ID, num of article nnFeature is to use
Buy the quantity of article n, gender in familynFeature is to buy the gender of the user of article n, agenFeature is to buy the user of article n
Age, provincenFeature is the ID, user_level in province where buying the user of article nnFeature is purchase article n
The grade of user.For example, gender can be handled by the way of one-hot (one-hot encoding)nFeature, can also be to each in matrix
The data of feature are normalized, to ensure that each feature can indicate under same data distribution.
In some embodiments, following vector Y can be constructed:
dnFor the service life of article n.
It in some embodiments, can be using matrix X as input, using the vector Y that marked as exporting training machine
Learning model.For example, machine learning model can be neural network, which includes input layer (for input feature vector number
According to), hidden layer (is used for fine-characterization data), output layer (for exporting result).
For example, matrix X can be inputted to the input layer of neural network, by adjusting hyper parameter (for example, hidden layer quantity, hidden
Slice width degree, learning rate etc.), it (is asked to evade over-fitting in conjunction with Dropout technology and Batch Normalization technology
Topic), optimization algorithm (such as Adam algorithm etc., to promote pace of learning) and mean square error loss function carry out training machine
Practise model.It can also be by cross validation mode come the accuracy of verifier learning model.
For example, the time interval that can repeatedly buy same article according to user is labeled the data in Y, according to mark
The Y of note verifies trained machine learning model, to guarantee the accuracy of machine learning model.
In the step 120, by the ID of the article in the relevant information of target user and the History Order data of target user
Machine learning model is inputted, to obtain the service life of the article in History Order data.
In step 130, according to the service life on nearest the purchase date and the article of the article in History Order data,
Determine whether that target user recommends the article.
In some embodiments, the technical solution of the disclosure can be realized by the embodiment in Fig. 2.
Fig. 2 shows the flow charts of other embodiments of the recommended method of the article of the disclosure.
As shown in Fig. 2, this method comprises: step 110, training machine learning model；Step 120, the use of article is obtained
Period；Step 1310, the purchase date adds whether service life is more than current date recently；Step 1320, recommend the article；With
Step 1330, the article is not recommended.
The execution of step 110 and step 120 is identical as the embodiment in Fig. 1, and details are not described herein.
In step 1310, judge that the nearest purchase date of article adds whether service life is more than current date.For example,
The ID of the article in the History Order of target user can be read, target user is obtained and the date is bought recently accordingly for the ID
Service life corresponding with the ID.If it does, thening follow the steps 1320.If be less than, 1330 are thened follow the steps.
In step 1320, recommend the corresponding article of the ID to user.
In step 1330, the corresponding article of the ID is not recommended to user.
In some embodiments, the step 130 in Fig. 1 or Fig. 2 can be realized by the embodiment in Fig. 3.
Fig. 3 shows the flow chart of some embodiments of Fig. 1 or the step 130 in Fig. 2.
As shown in figure 3, step 130 includes: step 1301, first set is generated；Step 1302, second set is generated；Step
Rapid 1303, read the key-value pair with same article ID respectively from first set and second set；Step 1310, purchase recently
Whether the date is more than current date plus service life；Step 1320, recommend the article；Step 1330, the article is not recommended；Step
Rapid 1340, judge whether there is unread key-value pair in first set and second set；Step 1350, it generates and recommends columns of items
Table.
In step 1301, the first collection is generated according to the relevant information of target user and the History Order data of target user
It closes, includes the key-value pair being made of the ID of article and the nearest purchase date of the article in first set.For example, key-value pair can be with
For < sku_idn,buy_timen>, buy_timenBuy the date of article n recently for target user.For example, can be used with target
The User ID at family marks first set, indicates that the article in the first set generated is the relevant each article of target user.Step
1301 are not carried out sequence with step 110 and step 120.
In step 1302, second set is generated according to the service life of article in History Order data, in second set
Including the key-value pair being made of the ID of article and the service life of the article.For example, key-value pair can be < sku_idn,life_
timen>, life_timenFor the service life of article n.For example, second set, table can be marked with the User ID of target user
Show that the article in the second set of generation is the relevant each article of target user.
In step 1303, the key-value pair with the ID of same article is read respectively from first set and second set,
To obtain sku_idnCorresponding buy_timenAnd life_timen。
Step 1310- step 1330 is identical as Fig. 2, and details are not described herein.
In step 1340, judge whether there is unread key-value pair in first set and second set.If so, then returning
Receipt row step 1303；If it is not, executing step 1350.
In step 1350, the recommendation item lists of target user are generated.For example, recommending includes each recommendation in item lists
The sku_id of articlen.In this way, the recommendation article of target user can be obtained by the User ID of target user.
In above-described embodiment, obtained between user information, article ID and article service life by machine learning method meter
Relational model, according to the model estimate user whether need to buy the article in its History Order again, to be pushed away to user
Recommend corresponding article.In this way, the record that can be done shopping according to the history of user, the various dimensions information combination user of article is pushed away to user
Article is recommended, to improve the accuracy of article recommendation.
Fig. 4 shows the block diagram of some embodiments of the recommendation apparatus of the article of the disclosure.
As shown in figure 4, recommendation apparatus 4 includes training unit 41, acquiring unit 42 and recommendation unit 43.
Training unit 41 is input with the relevant information of the ID of article and the user for buying article, uses week with article
Phase is output, training machine learning model.
Acquiring unit 42 is defeated by the ID of the article in the relevant information of target user and the History Order data of target user
Enter machine learning model, to obtain the service life of the article in History Order data.
Recommendation unit 43 is according to the service life on nearest the purchase date and the article of the article in History Order data, really
It is fixed whether to target user to recommend the article.
In some embodiments, the nearest purchase date of article of the recommendation unit 43 in History Order data adds the object
In the case where being more than current date after the service life of product, recommend the article to target user.Recommendation unit 43 is in History Order
In the case that the nearest purchase date of article in data is plus current date is less than after the service life of the article, not to mesh
Mark user recommends the article.
In some embodiments, recommendation unit 43 is according to the relevant information of target user and the History Order number of target user
According to generation first set.It include the key-value pair being made of the ID of article and the nearest purchase date of the article in first set.It pushes away
It recommends unit 43 and second set is generated according to the service life of article in History Order data.It include the ID by article in second set
The key-value pair formed with the service life of the article.Recommendation unit 43 is used according to first set and second set, true directional aim
The article that family is recommended.
In above-described embodiment, obtained between user information, article ID and article service life by machine learning method meter
Relational model, according to the model estimate user whether need to buy the article in its History Order again, to be pushed away to user
Recommend corresponding article.In this way, the record that can be done shopping according to the history of user, the various dimensions information combination user of article is pushed away to user
Article is recommended, to improve the accuracy of article recommendation.
Fig. 5 shows the block diagram of other embodiments of the recommendation apparatus of the article of the disclosure.
As shown in figure 5, the recommendation apparatus 5 of the article of the embodiment includes: memory 51 and is coupled to the memory 51
Processor 52, processor 52 is configured as executing any one reality in the disclosure based on the instruction being stored in memory 51
Apply one or more steps in the recommended method of the article in example.
Wherein, memory 51 is such as may include system storage, fixed non-volatile memory medium.System storage
Such as be stored with operating system, application program, Boot loader (Boot Loader), database and other programs etc..
Fig. 6 shows the block diagram of the other embodiment of the recommendation apparatus of the article of the disclosure.
As shown in fig. 6, the recommendation apparatus 6 of the article of the embodiment includes: memory 610 and is coupled to the memory
610 processor 620, processor 620 are configured as based on the instruction being stored in memory 610, execute it is aforementioned any one
The recommended method of article in embodiment.
Memory 610 is such as may include system storage, fixed non-volatile memory medium.System storage is for example
It is stored with operating system, application program, Boot loader (Boot Loader) and other programs etc..
The recommendation apparatus 6 of article can also include input/output interface 630, network interface 640, memory interface 650 etc..This
It can for example be connected by bus 860 between a little interfaces 630,640,650 and memory 610 and processor 620.Wherein, defeated
Enter output interface 630 and provides connecting interface for input-output equipment such as display, mouse, keyboard, touch screens.Network interface 640
Connecting interface is provided for various networked devices.The external storages such as memory interface 640 is SD card, USB flash disk provide connecting interface.
Those skilled in the art should be understood that embodiment of the disclosure can provide as method, system or computer journey
Sequence product.Therefore, complete hardware embodiment, complete software embodiment or combining software and hardware aspects can be used in the disclosure
The form of embodiment.Moreover, it wherein includes the calculating of computer usable program code that the disclosure, which can be used in one or more,
Machine can use the meter implemented in non-transient storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of calculation machine program product.
So far, recommended method, device and the computer-readable storage medium of the article according to the disclosure is described in detail
Matter.In order to avoid covering the design of the disclosure, some details known in the field are not described.Those skilled in the art according to
Above description, completely it can be appreciated how implementing technical solution disclosed herein.
Disclosed method and system may be achieved in many ways.For example, can by software, hardware, firmware or
Software, hardware, firmware any combination realize disclosed method and system.The said sequence of the step of for the method
Merely to be illustrated, the step of disclosed method, is not limited to sequence described in detail above, special unless otherwise
It does not mentionlet alone bright.In addition, in some embodiments, also the disclosure can be embodied as to record program in the recording medium, these programs
Including for realizing according to the machine readable instructions of disclosed method.Thus, the disclosure also covers storage for executing basis
The recording medium of the program of disclosed method.
Although being described in detail by some specific embodiments of the example to the disclosure, the skill of this field
Art personnel it should be understood that above example merely to be illustrated, rather than in order to limit the scope of the present disclosure.The skill of this field
Art personnel are it should be understood that can modify to above embodiments in the case where not departing from the scope of the present disclosure and spirit.This public affairs
The range opened is defined by the following claims.
Claims (10)
1. a kind of recommended method of article, comprising:
It is input with the relevant information of the ID of article and the user for buying the article, is defeated with the service life of the article
Out, training machine learning model；
The ID of article in the relevant information of target user and the History Order data of the target user is inputted into the machine
Learning model, to obtain the service life of the article in the History Order data；
According to the service life on nearest the purchase date and the article of the article in the History Order data, it is determined whether to institute
It states target user and recommends the article.
2. recommended method according to claim 1, wherein described to determine whether that the target user recommends the article packet
It includes:
It is more than to work as the day before yesterday after the service life that the nearest purchase date of the article in the History Order data adds the article
In the case where phase, Xiang Suoshu target user recommends the article；
It is less than after the service life that the nearest purchase date of the article in the History Order data adds the article current
In the case where date, the article is not recommended to the target user.
3. recommended method according to claim 1 or 2, wherein described to determine whether that the target user recommends the object
Product include:
First set is generated according to the relevant information of the target user and the History Order data of the target user, described the
It include the key-value pair being made of the ID of article and the nearest purchase date of the article in one set；
Second set is generated according to the service life of article in the History Order data, includes by article in the second set
ID and the article service life form key-value pair；
According to the first set and the second set, the article recommended to the target user is determined.
4. recommended method according to claim 1 or 2, wherein
The relevant information includes the gender information of user, age information, location message, class information, the number for buying article
It is one or more in amount.
5. recommended method according to claim 4, wherein
The gender information is handled by one-hot encoding mode.
6. a kind of recommendation apparatus of article, comprising:
Training unit, for being input with the relevant information of the ID of article and the user for buying the article, with the article
Service life be output, training machine learning model；
Acquiring unit, for by the ID of the article in the History Order data of the relevant information of target user and the target user
The machine learning model is inputted, to obtain the service life of the article in the History Order data；
Recommendation unit, for the nearest purchase date according to the article in the History Order data with the article using all
Phase, it is determined whether Xiang Suoshu target user recommends the article.
7. recommendation apparatus according to claim 6, wherein
The nearest purchase date of article of the recommendation unit in the History Order data adds the service life of the article
In the case where being more than current date afterwards, Xiang Suoshu target user recommends the article, the article in the History Order data
In the case where the date is bought recently plus current date is less than after the service life of the article, do not recommend to the target user
The article.
8. recommendation apparatus according to claim 6 or 7, wherein
The recommendation unit generates the according to the relevant information of the target user and the History Order data of the target user
One gathers, and includes the key-value pair being made of the ID of article and the nearest purchase date of the article in the first set, according to institute
The service life for stating article in History Order data generates second set, includes ID and the object by article in the second set
The key-value pair of the service life composition of product, recommends according to the first set and the second set, determination to target user
Article.
9. a kind of recommendation apparatus of article, comprising:
Memory；With
It is coupled to the processor of the memory, the processor is configured to based on the finger being stored in the memory device
It enables, perform claim requires one or more steps in the recommended method of the described in any item articles of 1-5.
10. a kind of computer readable storage medium, is stored thereon with computer program, power is realized when which is executed by processor
Benefit requires one or more steps in the recommended method of the described in any item articles of 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868063.7A CN110428296A (en) | 2018-08-02 | 2018-08-02 | Recommended method, device and the computer readable storage medium of article |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810868063.7A CN110428296A (en) | 2018-08-02 | 2018-08-02 | Recommended method, device and the computer readable storage medium of article |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110428296A true CN110428296A (en) | 2019-11-08 |
Family
ID=68407222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810868063.7A Pending CN110428296A (en) | 2018-08-02 | 2018-08-02 | Recommended method, device and the computer readable storage medium of article |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110428296A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763076A (en) * | 2020-07-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data filtering method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110016001A1 (en) * | 2006-11-08 | 2011-01-20 | 24/8 Llc | Method and apparatus for recommending beauty-related products |
| US20130191241A1 (en) * | 2012-01-23 | 2013-07-25 | Oracle International Corporation | Subject matter intelligence for business applications |
| CN105869024A (en) * | 2016-04-20 | 2016-08-17 | 北京小米移动软件有限公司 | Commodity recommending method and device |
| US20160292769A1 (en) * | 2015-03-31 | 2016-10-06 | Stitch Fix, Inc. | Systems and methods that employ adaptive machine learning to provide recommendations |
| CN106327240A (en) * | 2016-08-11 | 2017-01-11 | 中国船舶重工集团公司第七0九研究所 | Recommendation method and recommendation system based on GRU neural network |
| US20170270593A1 (en) * | 2016-03-21 | 2017-09-21 | The Procter & Gamble Company | Systems and Methods For Providing Customized Product Recommendations |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN108280115A (en) * | 2017-10-24 | 2018-07-13 | 腾讯科技（深圳）有限公司 | Identify the method and device of customer relationship |
-
2018
- 2018-08-02 CN CN201810868063.7A patent/CN110428296A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110016001A1 (en) * | 2006-11-08 | 2011-01-20 | 24/8 Llc | Method and apparatus for recommending beauty-related products |
| US20130191241A1 (en) * | 2012-01-23 | 2013-07-25 | Oracle International Corporation | Subject matter intelligence for business applications |
| US20160292769A1 (en) * | 2015-03-31 | 2016-10-06 | Stitch Fix, Inc. | Systems and methods that employ adaptive machine learning to provide recommendations |
| US20170270593A1 (en) * | 2016-03-21 | 2017-09-21 | The Procter & Gamble Company | Systems and Methods For Providing Customized Product Recommendations |
| CN105869024A (en) * | 2016-04-20 | 2016-08-17 | 北京小米移动软件有限公司 | Commodity recommending method and device |
| CN106327240A (en) * | 2016-08-11 | 2017-01-11 | 中国船舶重工集团公司第七0九研究所 | Recommendation method and recommendation system based on GRU neural network |
| CN107705183A (en) * | 2017-09-30 | 2018-02-16 | 深圳乐信软件技术有限公司 | Recommendation method, apparatus, storage medium and the server of a kind of commodity |
| CN108280115A (en) * | 2017-10-24 | 2018-07-13 | 腾讯科技（深圳）有限公司 | Identify the method and device of customer relationship |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113763076A (en) * | 2020-07-21 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data filtering method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Henard et al. | Bypassing the combinatorial explosion: Using similarity to generate and prioritize t-wise test configurations for software product lines | |
| KR20180091043A (en) | Method and apparatus for obtaining user portraits | |
| WO2019154108A1 (en) | Method and apparatus for processing transaction data | |
| CN103140868A (en) | Determining a likelihood of suitability based on historical data | |
| CN105900121A (en) | Methods for generating an activity stream | |
| CN110428295A (en) | Method of Commodity Recommendation and system | |
| US20200380524A1 (en) | Transaction feature generation | |
| WO2020221022A1 (en) | Service object recommendation method | |
| CN108734587A (en) | The recommendation method and terminal device of financial product | |
| CN109711931A (en) | Method of Commodity Recommendation, device, equipment and storage medium based on user's portrait | |
| CN106251178A (en) | Data digging method and device | |
| US20150142511A1 (en) | Recommending and pricing datasets | |
| Balk et al. | An evaluation of cross-efficiency methods: With an application to warehouse performance | |
| CN105488072B (en) | Target object method for selecting, apparatus and system in a kind of object library | |
| Samreen et al. | Transferable knowledge for low-cost decision making in cloud environments | |
| Li et al. | Laplacian damping for projective dynamics | |
| Dinh et al. | A survey of privacy preserving utility mining | |
| CN110428296A (en) | Recommended method, device and the computer readable storage medium of article | |
| Brambilla et al. | An explorative approach for crowdsourcing tasks design | |
| US20140075279A1 (en) | Data-Value Centered Programming | |
| Mitheran et al. | Introducing Self-Attention to Target Attentive Graph Neural Networks | |
| Maiti et al. | An EOQ model of an item with imprecise seasonal time via genetic algorithm | |
| Mitheran et al. | Improved representation learning for session-based recommendation | |
| Ozaki et al. | Modeling and simulation of Japanese inter-firm network | |
| CN107688979A (en) | Method and apparatus for providing credit reference information |
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: 20191108 |
|
| RJ01 | Rejection of invention patent application after publication |