CN113129096A - High-efficiency clustering method and system based on piecing probability - Google Patents
High-efficiency clustering method and system based on piecing probability Download PDFInfo
- Publication number
- CN113129096A CN113129096A CN202110328287.0A CN202110328287A CN113129096A CN 113129096 A CN113129096 A CN 113129096A CN 202110328287 A CN202110328287 A CN 202110328287A CN 113129096 A CN113129096 A CN 113129096A
- Authority
- CN
- China
- Prior art keywords
- user
- commodity
- probability
- commodities
- key words
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007726 management method Methods 0.000 claims description 24
- 238000002372 labelling Methods 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 13
- 239000006071 cream Substances 0.000 description 3
- 230000013011 mating Effects 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
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]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0239—Online discounts or incentives
-
- 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
The application discloses a high-efficiency clustering method and system based on a clustering probability, wherein the system monitors browsing data of a user in real time, automatically adjusts the weight of a clustered product according to the browsing data, and preferentially recommends commodities with high coefficient weight; setting the commodity spelling probability in the system, wherein the spelling probability is a fixed value and is not changed in the whole group spelling process; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account. The bottom logic of the application is the change of value delivery, the past commodity transaction and the core delivery are commodities, in the Internet era, each conversion behavior of a user can be used as a value delivery object, as long as the input-output ratio is met, the thin profit and the multiple sales can be realized, the expectation of the user transaction is further improved, and the incremental consumption is created. Meanwhile, matching of suitable commodities and suitable users can be efficiently realized through matching of the keyword tags, and the value of the platform is increased.
Description
Technical Field
The application belongs to the technical field of e-commerce systems, and particularly relates to a high-efficiency clustering method and system based on a split probability.
Background
In the previous patent (CN 112419016A) application of the applicant, an efficient clustering method and system based on the split probability are disclosed, for any order placed by any user at any time, the system immediately feeds back the information of the clustered order to be committed in time; the system monitors the piecing and uniting data in real time; automatically adjusting the weight of the grouping product according to the transaction data, and preferentially recommending commodities with high coefficient weight; the system sets commodity piecing probability which can be automatically adjusted according to piecing together bargain data, through automatic analysis, sequencing and fitting of transaction data and improvement of a preposed technical scheme of a bunching logic, the bargain efficiency of the whole piecing together method is obviously optimized, waste of user flow is avoided, repurchase data and conversion data are effectively improved, and a better solution of a transaction model is realized. Meanwhile, the waiting time of the user is reduced, the operation experience of the user is obviously improved, and a more convenient technical process path is achieved.
In diversified application scenes, the system has further expanded space, particularly further expands the split probability and the change compensation logic in the commodity transaction process, and further expands the personalized recommendation algorithm and logic of the group purchase commodities in the sequencing display process, so that the system is widely suitable for various E-commerce scenes.
Disclosure of Invention
Aiming at the defects in the prior art, the technical problem to be solved by the invention is to provide an efficient grouping method based on the spelling probability, the commodity spelling probability and the full refund of non-spelling persons are set in commodity transaction, the platform compensates change from preset cost and gives the change to the non-spelling users, and meanwhile, the change can be rewarded to the spelling users, so that the ordering conversion of the users is promoted. The invention aims to solve another technical problem of providing a clustering method based on the split probability, the bottom logic of the scheme is the change of value delivery, the past commodity transaction and the core delivery are commodities, and in the internet era, each conversion behavior of a user can be used as a value delivery object, so long as the input-output ratio is met, the thin profit and the multiple sales can be realized, the expectation of the user transaction is further improved, and the incremental consumption is created. The invention also aims to solve the technical problem of providing a method for automatically adjusting the weight of the grouping product by monitoring the browsing data of the user in real time, the most important thing on the e-commerce transaction link is to match the transaction, the matching of the commodity and the user most suitable for the commodity is the key point for improving the transaction conversion, and the matching of the suitable commodity and the suitable user can be efficiently realized through the matching of the keyword label, so that the value of the platform is increased.
In order to solve the technical problems, the invention adopts the technical scheme that:
a high-efficiency clustering method based on a split probability comprises the following steps: the system monitors user browsing data in real time, automatically adjusts the weight of the grouping products according to the browsing data, and preferentially recommends commodities with high coefficient weight; the commodity spelling probability is set in the system, and the spelling probability is a fixed value and is not changed in the process of grouping; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account.
The high-efficiency clustering method based on the clustering probability can provide compensation for the clustered users by the compensation module no matter whether the users are clustering commodities or not.
The high-efficiency clustering method based on the clustering probability monitors the browsing data of the user in real time, and automatically adjusts the weight of the clustered products according to the browsing data, and the specific process is as follows:
1) the system automatically divides words for each commodity of the platform, disassembles and/or self-establishes and manages keywords during shelving;
2) the automatic word segmentation can use common word segmentation service, and the labeling management is to perform keyword management on the commodities in a manual or automatic mode;
3) the system carries out keyword labeling management on the user;
4) the system records commodity click browsing and ordering records of the user;
5) the system superposes the commodity label clicked by the user to browse or order the user requests to the keyword labeling management of the user;
6) each time a new commodity is clicked to browse or placed, a new keyword label is superposed once;
7) the system carries out updating and updating on the keyword labels superposed by clicking, browsing and ordering of the user;
8) the user labels recorded by the system need to set a certain saturation number, and after the commodities browsed by the user exceed the saturation upper limit, the commodity key words superposed by latest click browsing and ordering of the user replace the commodity key words obtained by earliest click browsing and ordering;
9) the commodity number interval is set to be 1-N commodities according to the actual requirement of the platform;
10) when the system displays the commodity for the user, the label key words of the commodity and the label key words of the user are matched, and the more the label key words of the commodity are matched with the label key words of the user, the more easily the commodity is displayed.
A clustering method based on a split probability comprises the following steps: setting commodity spelling probability in the system, wherein the spelling probability is a fixed value and is not changed in the process of grouping; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account.
According to the clustering method based on the spelling probability, no matter whether the user spells the commodity or not, the compensation module can issue compensation to the participating users.
A method for automatically adjusting the weight of a grouping product by monitoring user browsing data in real time comprises the following specific processes:
1) the system automatically divides words for each commodity of the platform, disassembles and/or self-establishes and manages keywords during shelving;
2) the automatic word segmentation can use common word segmentation service, and the labeling management is to perform keyword management on the commodities in a manual or automatic mode;
3) the system carries out keyword labeling management on the user;
4) the system records commodity click browsing and ordering records of the user;
5) the system superposes the commodity label clicked by the user to browse or order the user requests to the keyword labeling management of the user;
6) each time a new commodity is clicked to browse or placed, a new keyword label is superposed once;
7) the system carries out updating and updating on the keyword labels superposed by clicking, browsing and ordering of the user;
8) the user labels recorded by the system need to set a certain saturation number, and after the commodities browsed by the user exceed the saturation upper limit, the commodity key words superposed by latest click browsing and ordering of the user replace the commodity key words obtained by earliest click browsing and ordering;
9) the commodity number interval is set to be 1-N commodities according to the actual requirement of the platform;
10) when the system displays the commodity for the user, the label key words of the commodity and the label key words of the user are matched, and the more the label key words of the commodity are matched with the label key words of the user, the more easily the commodity is displayed.
A system for realizing the high-efficiency clustering method based on the clustering probability comprises a data server and an equipment server, wherein the equipment server is provided with a client, and a user acquires transaction link information of the data server through the client and initiates a clustering request; the data server creates transaction link information of the pieced products, realizes monitoring, calculation, analysis and storage of pieced data information, and realizes pieced probability adjustment, weight adjustment and grouping information feedback; the data server adopts an entity server or a cloud server.
Has the advantages that: compared with the prior art, the invention has the advantages that:
1) the commodity transaction sets commodity sharing probability and the refund of the non-sharing persons, the platform compensates change from preset expense and gives the change to the non-sharing users, and meanwhile, the change can be rewarded to the sharing users, and ordering conversion of the users is promoted.
2) The bottom logic of the scheme is the change of value delivery, the past commodity transaction and the core delivery are commodities, in the Internet era, each conversion behavior of a user can be used as a value delivery object, as long as the input-output ratio is met, the thin profit and the multiple sales can be realized, the expectation of the user transaction is further improved, and the incremental consumption is created.
3) The most important thing on the E-commerce transaction link is to match the transaction, the matching of the commodity and the user most suitable for the commodity is a key point for improving transaction conversion, and the matching of the suitable commodity and the suitable user can be efficiently realized through the matching of the keyword label, so that the value of the platform is increased.
Drawings
FIG. 1 is a flow chart of a first type of hit probability and change compensation logic;
FIG. 2 is a flow chart of a second type of hit probability and change compensation logic;
fig. 3 is a flow chart of tag matching management in the personalized goods recommendation algorithm.
Detailed Description
The present invention will be further described with reference to the following specific examples.
CN112419016A discloses a big data-based grouping system and method, wherein the big data-based grouping system comprises a data server and an equipment server; the equipment server is provided with client software, and a user acquires transaction link information of the data server through the client and initiates a group-combining request; the client can be downloaded through equipment servers such as a mobile phone, a PC (personal computer), a Pad and the like and is presented in the form of App software or a webpage; the user can log in/out of the client through the terminal device. The data server can create transaction link information of the pieced products, realize the monitoring, calculation, analysis and storage of pieced data information, and realize the pieced probability adjustment, weight adjustment and grouping information feedback; the data server is an entity server or a cloud server, such as an Aliskian ECS server or other cloud servers.
The group-combining method based on big data adopts a group-combining preposition method to complete the transaction, and the system immediately feeds back group-combining order information and timely completes the transaction for the order placed by any user at any time; meanwhile, the system monitors the piecing and mating data in real time, automatically adjusts the weight of the piecing and mating product according to the mating data, and preferentially recommends commodities with high coefficient weight; setting commodity sharing probability in the system, wherein the sharing probability is automatically adjusted according to the sharing bargaining data; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account.
The following examples are further developed based on the disclosure of CN112419016A, and the following examples, where not described in detail, are consistent with the disclosure of CN112419016A and other prior art in this field.
Example 1 setting of Merge probability and Change Compensation logic in Commodity transaction Process
The commodity sharing probability is set in the commodity transaction disclosed in CN112419016A, the sharing probability can be automatically adjusted according to the sharing group bargaining data, the sharing persons can obtain low-price commodities, the non-sharing persons refund money in full amount, the platform compensates change or high-value prizes from preset marketing cost to give the non-sharing users, the expectation of the commodity transaction is improved, and the setting of the probability and the small amount compensation can effectively leverage the ordering conversion rate of the users to general commodities.
As shown in fig. 1, in this embodiment, under the condition that a third-party merchant is introduced or other demands are made on the overall profit of the commodity, the centering probability is manually set, and is a fixed value and is unchanged in the whole transaction period, so as to meet the use demands of the commodities of various merchants. Meanwhile, in the actual operation process, change is the optimal choice in the un-pieced compensation.
Real usage scenarios: when a user A purchases a low-price commodity B with a middle sharing probability of 50%, the platform is preset with the small change compensation of 0.5 yuan per capita, after the user normally pays, if the user shares the middle, the user normally enters into transaction performance, if the user does not share the middle, the platform returns the transaction payment amount, meanwhile, the small change of 0.5 yuan per capita of the user is compensated, and the specific numerical value can be revised according to the actual execution condition.
As a preferable scheme, as shown in fig. 2, commodity sharing probability and full refund of non-sharing persons are set in commodity transaction, and the platform compensates change from preset cost and gives to the non-sharing users, and meanwhile, the change can be rewarded to the sharing users, so that ordering conversion of the users is promoted. The bottom logic of the scheme is the change of value delivery, the past commodity transaction and the core delivery are commodities, in the Internet era, each conversion behavior of a user can be used as a value delivery object, as long as the input-output ratio is met, the thin profit and the multiple sales can be realized, the expectation of the user transaction is further improved, and the incremental consumption is created.
Example 2 taged matching management in personalized goods recommendation algorithm
In the commodity transaction disclosed in CN112419016A, the system monitors the piecing together transaction data in real time, automatically adjusts the weight of the piecing together product according to the transaction data, the piecing together person can obtain low-price commodities, the un-pieced together person refunds in full amount, the platform compensates change or high-value prizes from preset marketing fees to give to the un-pieced together user, the expectation of commodity transaction is improved, and setting probability and small amount compensation can effectively leverage the user's ordering conversion rate for general commodities.
As shown in fig. 3, the tag matching management in the personalized product recommendation algorithm is performed in this embodiment, specifically:
1) the system automatically divides words for each commodity of the platform, disassembles and/or self-establishes and manages keywords during shelving;
2) the automatic word segmentation can use common word segmentation services, and the labeling management is to perform keyword management on the commodities in a manual or automatic mode.
For example: the small fresh shower cream is divided into small fresh, shower and shower cream for commodity labeling management.
3) The system carries out keyword labeling management on the user;
4) the system records commodity click browsing and ordering records of the user;
5) the system superposes the commodity label clicked by the user to browse or order the user requests to the keyword labeling management of the user.
For example: the user browses for "fresher shower gel" the user will get the label attributes of "fresher", "shower gel".
6) And a new keyword label is superposed once every time a new commodity is clicked to browse or placed.
For example: the user browses the 'fresh shower cream' and continues to browse the 'fresh facial cleanser', and the label weight of the 'fresh' is increased from 1 time to 2 times. The user gets a label of "fresh" (2 times), bath, shower, face wash, etc.
7) The system carries out updating and updating on the keyword labels superposed by clicking, browsing and ordering of the user;
8) the user labels recorded by the system need to set a certain saturation number, and a saturation upper limit is generally established by using the number of the browsed commodities, namely after the browsed commodities of the user exceed the saturation upper limit, the commodity key words superposed by latest clicking browsing and ordering of the user replace the commodity key words obtained by earliest clicking browsing and ordering.
9) The commodity number interval can be set to be 1-N commodities according to the actual requirement of the platform;
for example: if the value is set to 1, the user completely replaces the commodity keyword added to the attribute of the user every time the user browses and clicks and places a new commodity, and this situation may cause that the recommended commodity completely refers to the last commodity keyword and the long tail effect is lost.
For example: and setting the value to be 2, after the user clicks to browse and order a new product, keeping the previous product label on the attribute of the user, replacing the previous product label with the keyword of the new product, and so on.
10) When the system displays the commodity for the user, the label key words of the commodity and the label key words of the user are matched, and the more the label key words of the commodity are matched with the label key words of the user, the more easily the commodity is displayed.
The most important thing on the E-commerce transaction link is to match the transaction, the matching of the commodity and the user most suitable for the commodity is a key point for improving transaction conversion, and the matching of the suitable commodity and the suitable user can be efficiently realized through the matching of the keyword label, so that the value of the platform is increased. The weight of all keywords matched in a labeling mode is generally set to be 60% -90%, and the keywords can be adjusted according to the accuracy of actual requirements, the set percentage is higher, the accuracy of the current matched commodities is higher, and an 'information cocoon room' is easier to form at the same time, so that external commodities cannot enter a display area of a user. The lower the weight is set, the less delicate the recommended goods are, resulting in a decrease in the efficiency of the transaction, which can be specifically analyzed according to the specific scenario in the practical application.
Claims (7)
1. A high-efficiency clustering method based on a middle-piecing probability is characterized in that: the system monitors user browsing data in real time, automatically adjusts the weight of the grouping products according to the browsing data, and preferentially recommends commodities with high coefficient weight; the commodity spelling probability is set in the system, and the spelling probability is a fixed value and is not changed in the process of grouping; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account.
2. The efficient clustering method based on the split probability as claimed in claim 1, wherein: the compensation module issues compensation to the participating users no matter whether the users are sharing the commodities or not.
3. The efficient clustering method based on the split probability as claimed in claim 1, wherein: the system monitors browsing data of a user in real time, automatically adjusts the weight of the grouping product according to the browsing data, and comprises the following specific processes:
1) the system automatically divides words for each commodity of the platform, disassembles and/or self-establishes and manages keywords during shelving;
2) the automatic word segmentation can use common word segmentation service, and the labeling management is to perform keyword management on the commodities in a manual or automatic mode;
3) the system carries out keyword labeling management on the user;
4) the system records commodity click browsing and ordering records of the user;
5) the system superposes the commodity label clicked by the user to browse or order the user requests to the keyword labeling management of the user;
6) each time a new commodity is clicked to browse or placed, a new keyword label is superposed once;
7) the system carries out updating and updating on the keyword labels superposed by clicking, browsing and ordering of the user;
8) the user tags recorded by the system are set to a certain saturation number, and after the commodities browsed by the user exceed the saturation upper limit, the commodity key words superposed by latest click browsing and ordering of the user replace the commodity key words obtained by earliest click browsing and ordering;
9) the commodity number interval is set to be 1-N commodities according to the actual requirement of the platform;
10) when the system displays the commodity for the user, the label key words of the commodity and the label key words of the user are matched, and the more the label key words of the commodity are matched with the label key words of the user, the more easily the commodity is displayed.
4. A clustering method based on a split probability is characterized in that: setting commodity spelling probability in the system, wherein the spelling probability is a fixed value and is not changed in the process of grouping; in addition, a compensation module is preset in the system, and if the user does not collect the commodity, the system automatically refunds the user and automatically issues compensation to the user account.
5. The clustering method based on the split probabilities according to claim 4, characterized by: the compensation module issues compensation to the participating users no matter whether the users are sharing the commodities or not.
6. A method for automatically adjusting the weight of a conglomerate product by monitoring user browsing data in real time is characterized by comprising the following specific processes:
1) the system automatically divides words for each commodity of the platform, disassembles and/or self-establishes and manages keywords during shelving;
2) the automatic word segmentation can use common word segmentation service, and the labeling management is to perform keyword management on the commodities in a manual or automatic mode;
3) the system carries out keyword labeling management on the user;
4) the system records commodity click browsing and ordering records of the user;
5) the system superposes the commodity label clicked by the user to browse or order the user requests to the keyword labeling management of the user;
6) each time a new commodity is clicked to browse or placed, a new keyword label is superposed once;
7) the system carries out updating and updating on the keyword labels superposed by clicking, browsing and ordering of the user;
8) the user labels recorded by the system need to set a certain saturation number, and after the commodities browsed by the user exceed the saturation upper limit, the commodity key words superposed by latest click browsing and ordering of the user replace the commodity key words obtained by earliest click browsing and ordering;
9) the commodity number interval is set to be 1-N commodities according to the actual requirement of the platform;
10) when the system displays the commodity for the user, the label key words of the commodity and the label key words of the user are matched, and the more the label key words of the commodity are matched with the label key words of the user, the more easily the commodity is displayed.
7. A system for implementing the efficient clustering method based on split probabilities of claim 1, characterized in that: the system comprises a data server and an equipment server, wherein the equipment server is provided with a client, and a user acquires transaction link information of the data server through the client and initiates a group-combining request; the data server creates transaction link information of the pieced products, realizes monitoring, calculation, analysis and storage of pieced data information, and realizes pieced probability adjustment, weight adjustment and grouping information feedback; the data server adopts an entity server or a cloud server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110328287.0A CN113129096A (en) | 2021-03-26 | 2021-03-26 | High-efficiency clustering method and system based on piecing probability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110328287.0A CN113129096A (en) | 2021-03-26 | 2021-03-26 | High-efficiency clustering method and system based on piecing probability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113129096A true CN113129096A (en) | 2021-07-16 |
Family
ID=76773902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110328287.0A Pending CN113129096A (en) | 2021-03-26 | 2021-03-26 | High-efficiency clustering method and system based on piecing probability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129096A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111933A (en) * | 2013-04-17 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and device for acquiring business object label and building training model |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN112001754A (en) * | 2020-08-21 | 2020-11-27 | 上海风秩科技有限公司 | User portrait generation method, device, equipment and computer readable medium |
| CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
| CN112419016A (en) * | 2021-01-25 | 2021-02-26 | 南京石匠网络科技有限公司 | Big data-based grouping method and system |
-
2021
- 2021-03-26 CN CN202110328287.0A patent/CN113129096A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104111933A (en) * | 2013-04-17 | 2014-10-22 | 阿里巴巴集团控股有限公司 | Method and device for acquiring business object label and building training model |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN112001754A (en) * | 2020-08-21 | 2020-11-27 | 上海风秩科技有限公司 | User portrait generation method, device, equipment and computer readable medium |
| CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
| CN112419016A (en) * | 2021-01-25 | 2021-02-26 | 南京石匠网络科技有限公司 | Big data-based grouping method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11259072B2 (en) | Online live video sales management system | |
| US20190114686A1 (en) | Real-time internet capable device information interchange for coordinated queuing at locations | |
| CN111177563B (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN112150243A (en) | Digital mall system based on business middling platform | |
| US20170262926A1 (en) | Predictive shopping | |
| US20020128910A1 (en) | Business supporting system and business supporting method | |
| WO2020243894A1 (en) | Advertisement recommending method and apparatus, and electronic device | |
| CA2973706A1 (en) | Item classification method and selection system for electronic solicitation | |
| CN111340600A (en) | Intelligent marketing management system and method based on VR/AR mobile mall | |
| US10127605B2 (en) | Method and server for processing item identifiers, and computer readable storage medium | |
| CN102722836A (en) | Automatic bid inviting and bid competing system and method applied to internet | |
| CN112215448A (en) | Method and device for distributing customer service | |
| CN107992500A (en) | A kind of information processing method and server | |
| Cahyo et al. | Analysis and design of sales information system on web-based e-commerce in yoga farm catfish breeding business using uml | |
| CN113298568B (en) | Method and device for advertising | |
| JP2004239950A (en) | Sales promoting and control method, and device and program for realizing this method | |
| US20020087412A1 (en) | Method for post-sales customer retention | |
| CN113129096A (en) | High-efficiency clustering method and system based on piecing probability | |
| CN111914202B (en) | Multi-platform intelligent automatic publishing method, device, system and terminal | |
| WO2019047630A1 (en) | Marketing system, advertising gift recommendation method and sales sharing system | |
| US20220270142A1 (en) | Intermediary technology for online marketing | |
| EP1929437A1 (en) | Methods and systems for offering and selling advertising | |
| CN114971767A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN114493748A (en) | E-commerce marketing system and method based on Internet of things | |
| CN112991021A (en) | Service system for information interchange of electronic commerce platform |
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 |