CN110163652B - Guest-obtaining conversion rate estimation method and device and computer readable storage medium - Google Patents
Guest-obtaining conversion rate estimation method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN110163652B CN110163652B CN201910295973.5A CN201910295973A CN110163652B CN 110163652 B CN110163652 B CN 110163652B CN 201910295973 A CN201910295973 A CN 201910295973A CN 110163652 B CN110163652 B CN 110163652B
- Authority
- CN
- China
- Prior art keywords
- link
- conversion rate
- information
- customer
- obtaining
- 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.)
- Active
Links
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method and a device for estimating customer-obtaining conversion rate and a computer-readable storage medium are provided, wherein the method for estimating the customer-obtaining conversion rate comprises the following steps: acquiring user information of a second link in the business links; inputting the user information of the second link into a customer acquisition conversion rate estimation model to obtain a customer acquisition conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link; and acquiring and outputting the estimated result of the customer-obtaining conversion rate. By adopting the scheme, the customer-obtaining conversion rate pre-estimation precision can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of data processing, in particular to a method and a device for estimating customer acquisition conversion rate and a computer readable storage medium.
Background
In a business scenario, the system generally includes a plurality of business links, such as short message reply, registration, ordering, card binding or purchase, and the like. And each business link has a corresponding customer acquisition conversion rate, the customer acquisition conversion rate is attenuated layer by layer, and the customer acquisition conversion rates of all the business links are funnel-shaped.
At present, the customer-obtaining conversion rate is usually estimated based on a specific link, however, the estimation precision of the customer-obtaining conversion rate obtained by the estimation method is low.
Disclosure of Invention
The technical problem solved by the embodiment of the invention is that the estimation precision of the customer-obtaining conversion rate is low.
In order to solve the above technical problem, an embodiment of the present invention provides a method for estimating a customer-obtaining conversion rate, including: acquiring user information of a second link in the business links; inputting the user information of the second link into a customer acquisition conversion rate estimation model to obtain a customer acquisition conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link; and acquiring and outputting the estimated result of the customer-obtaining conversion rate. By adopting the scheme, the customer-obtaining conversion rate pre-estimation precision can be improved.
Optionally, the customer-obtaining conversion rate estimation model is obtained by training in the following way: acquiring a training sample set; processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample; generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link; generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample; training by adopting a supervised training algorithm to obtain a first pre-estimation model corresponding to a first link based on the user characteristic vectors of all training samples in the training sample set and the guest obtaining conversion information of the first link; and continuously training the first estimation model based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
Optionally, the supervised training algorithm includes any one of: neural networks, deep neural networks, logistic regression.
Optionally, when the ith training sample is converted into a client in the nth link, the client obtaining conversion information of the ith training sample in the 1 st to N business links is 1; or when the ith training sample is not converted into the client in the Nth link, the client obtaining conversion information of the ith training sample in the Nth business link is 0.
Optionally, after obtaining the customer obtaining conversion rate estimation result, the method further includes: and when the estimated result of the passenger obtaining conversion rate meets a preset condition, executing corresponding operation.
The embodiment of the invention also provides a device for estimating the passenger obtaining conversion rate, which comprises: the first acquisition unit is suitable for acquiring user information of a second link in the business links; the estimation unit is suitable for inputting the user information of the second link into a customer obtaining conversion rate estimation model to obtain a customer obtaining conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link; the second acquisition unit is suitable for acquiring the estimated result of the passenger obtaining conversion rate; and the output unit is suitable for outputting the estimated result of the passenger obtaining conversion rate.
Optionally, the passenger obtaining conversion rate estimation device further includes: the model construction unit is suitable for obtaining the customer obtaining conversion rate estimation model through training in the following mode: acquiring a training sample set; processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample; generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link; generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample; training by adopting a supervised training algorithm to obtain a first pre-estimation model corresponding to a first link based on the user characteristic vectors of all training samples in the training sample set and the guest obtaining conversion information of the first link; and training the first estimation model based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
Optionally, the supervised training algorithm includes any one of: neural networks, deep neural networks, logistic regression.
Optionally, when the ith training sample is converted into a client in the nth link, the client obtaining conversion information of the ith training sample in the 1 st to N business links is 1; or when the ith training sample is not converted into the client in the Nth link, the client obtaining conversion information of the ith training sample in the Nth business link is 0.
Optionally, the passenger obtaining conversion rate estimation device further includes: and the execution unit is suitable for executing corresponding operation when the estimated result of the passenger obtaining conversion rate meets the preset condition.
The embodiment of the invention also provides another device for estimating the passenger getting conversion rate, which comprises a memory and a processor, wherein the memory is stored with a computer instruction capable of running on the processor, and the processor executes any step of the method for estimating the passenger getting conversion rate when running the computer instruction.
The embodiment of the invention also provides a computer-readable storage medium, which is a nonvolatile storage medium or a non-transitory storage medium, and on which a computer instruction is stored, and when the computer instruction runs, the method executes any one of the steps of the guest obtaining conversion rate estimation method.
Compared with the prior art, the technical scheme of the embodiment of the invention has the following beneficial effects:
the customer-obtaining conversion rate model used for carrying out customer-obtaining conversion rate estimation is generated by the following steps: the method comprises the steps of obtaining a first pre-estimation model based on link information training of a first link in business links, and obtaining the first pre-estimation model by adopting link information of a second link to continue training the first pre-estimation model, so that when the customer-obtaining conversion rate is pre-estimated, the influence of the first link on the customer-obtaining conversion rate of the second link can be considered due to the fact that the first link is a front link of the second link, and therefore the pre-estimation precision of the customer-obtaining conversion rate can be improved.
Drawings
FIG. 1 is a flow chart of a method for estimating customer-obtaining conversion rate in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a passenger-obtaining conversion rate estimation device in an embodiment of the present invention.
Detailed Description
As described above, currently, customer conversion rate is usually estimated based on a specific link. However, the accuracy of the estimated result of the conversion rate of getting guests obtained by adopting the existing scheme is lower.
In the embodiment of the invention, the customer-obtaining conversion rate model used for estimating the customer-obtaining conversion rate is generated by the following steps: the method comprises the steps of obtaining a first pre-estimation model based on link information training of a first link in business links, and obtaining the first pre-estimation model by adopting link information of a second link to continue training the first pre-estimation model, so that when the customer-obtaining conversion rate is pre-estimated, the influence of the first link on the customer-obtaining conversion rate of the second link can be considered due to the fact that the first link is a front link of the second link, and therefore the pre-estimation precision of the customer-obtaining conversion rate can be improved.
In order to make the aforementioned objects, features and advantages of the embodiments of the present invention more comprehensible, specific embodiments accompanied with figures are described in detail below.
Referring to fig. 1, a flowchart of a method for estimating a conversion rate of getting guests in an embodiment of the present invention is shown. The method specifically comprises the following steps:
and 11, acquiring user information of a second link in the business links.
In a specific implementation, the user information may include at least one of: the age of the user, the gender of the user, the occupation of the user, the operational record of the user, the historical purchase record of the user, and the like. It can be understood that the user information may also include other contents according to different actual service scenarios, which are not described herein again.
And step 12, inputting the user information of the second link into a customer obtaining conversion rate estimation model to obtain a customer obtaining conversion rate result.
In specific implementation, a first estimation model is obtained based on sample information training of a first link in the business links, and the first estimation model is continuously trained based on sample information of a second link to obtain the customer-obtaining conversion rate estimation model. The sample information may include user sample information and corresponding guest-obtaining conversion information, and the first link is a leading link of the second link.
In specific implementation, which link of the business links is selected as the first link according to the degree of influence of the first link on the second link.
In the embodiment of the present invention, the service link may sequentially include: short message reply, registration, information filling, ordering, card binding payment and successful purchase. For example, the first link is a short message reply, and the second link is a successful purchase. As another example, the first link is ordering, and the second link is successful purchase.
In the specific implementation, the corresponding business links are different according to different business scenes. For example, some service links corresponding to service scenarios include: and replying to the store by short messages. In practical application, a business link can be set according to actual needs, and the content included in the business link is not limited.
In a specific implementation, the user sample information may include: age of the user sample, gender of the user sample, occupation of the user sample, operational records of the user sample, historical purchase records of the user sample, and the like.
In a specific implementation, the guest conversion information may be a guest conversion condition. When the audience is converted into the client, the guest obtaining conversion information may be represented by 1, and when the audience is not converted into the client, the guest obtaining conversion information may be represented by 0.
For example, when the ith training sample is converted into a client in the nth link, the client obtaining conversion information of the ith training sample in the 1 st to the N service links is all 1.
For another example, when the ith training sample is not converted into a client in the nth link, the client obtaining conversion information of the ith training sample in the nth business link is 0.
In a specific implementation, the customer-obtaining conversion rate estimation model can be obtained by adopting the following steps 1) to 5) training:
1) acquiring a training sample set; the training sample set comprises a plurality of training samples; and processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample.
2) And generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link.
For example, the translation feature vector is Y ═ Y1, Y2, … …, Yn ], where n is the number of business links, and Y1, Y2, … …, and Yn are guest-obtaining translation information corresponding to each business link, respectively. When the customer acquisition conversion information Yn is 1, the nth link is successfully converted into the customer. When the customer acquisition conversion information Yn is 0, it indicates that the nth link is converted into a customer failure.
3) And generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample.
For example, the user feature vector corresponding to the user information of the ith training sample is X ═ X1, X2, … …, Xm.
4) And training by adopting a supervised training algorithm based on the user characteristic vectors of all the training samples in the training sample set and the conversion information of the first link to obtain a first pre-estimated model corresponding to the first link.
5) And continuously training the conversion rate estimation model corresponding to the first link based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
In a specific implementation, the supervised training algorithm may include a neural network, a deep neural network, or a logistic regression algorithm. It is understood that other algorithms may be adopted according to the actual application requirement, and are not described herein.
And step 13, obtaining and outputting the estimated result of the passenger obtaining conversion rate.
In a specific implementation, the estimated result of the customer-obtaining conversion rate may be a probability of converting into a customer, and may also be a scoring result. For example, the estimated customer conversion rate is 0.9, i.e., the probability of conversion to customers is 0.9. As another example, the estimated conversion was 85 points. And outputting the obtained estimated result of the passenger obtaining conversion rate.
According to the scheme, the customer-obtaining conversion rate model used for estimating the customer-obtaining conversion rate is generated through the following steps: the method comprises the steps of obtaining a first pre-estimation model based on link information training of a first link in business links, and obtaining the first pre-estimation model by adopting link information of a second link to continue training the first pre-estimation model, so that when the customer-obtaining conversion rate is pre-estimated, the influence of the first link on the customer-obtaining conversion rate of the second link can be considered due to the fact that the first link is a front link of the second link, and therefore the pre-estimation precision of the customer-obtaining conversion rate can be improved.
In specific implementation, after the customer-obtaining conversion rate estimation result is obtained, when the customer-obtaining conversion rate estimation result meets a preset condition, corresponding operation can be executed.
For example, when business marketing is performed, the first link selects the short message to reply, and can preferentially send the marketing short message to the user with the estimated result of the customer-obtaining conversion rate higher than 0.6, so that marketing can be performed more specifically, the marketing success rate is high, casual and non-purpose marketing can be avoided, and the marketing cost is reduced.
In order to facilitate better understanding and implementation of the present invention for those skilled in the art, the embodiment of the present invention further provides a device for estimating the conversion rate of the obtained customers.
Referring to fig. 2, a schematic structural diagram of a guest obtaining conversion rate estimation device in an embodiment of the present invention is shown. The customer-obtaining conversion rate estimation device 20 may include:
a first obtaining unit 21 adapted to obtain user information of a second link in the business links;
the estimation unit 22 is adapted to input the user information of the second link into a customer obtaining conversion rate estimation model to obtain a customer obtaining conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link;
a second obtaining unit 23, adapted to obtain the estimated result of the passenger obtaining conversion rate;
and the output unit 24 is suitable for outputting the estimated result of the passenger obtaining conversion rate.
In an implementation, the passenger conversion rate estimation device 20 may further include: a model construction unit (not shown in the figure) adapted to train to obtain the customer-obtaining conversion rate estimation model in the following manner: acquiring a training sample set; processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample; generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link; generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample; training by adopting a supervised training algorithm based on the user characteristic vectors of all the training samples in the training sample set and the conversion information of a first link to obtain a first pre-estimated model corresponding to the first link; and training the first estimation model based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
In a specific implementation, the supervised training algorithm comprises any one of: neural networks, deep neural networks, logistic regression.
In specific implementation, when the ith training sample is converted into a client in the nth link, the conversion rate of acquiring the client of the ith training sample in the 1 st to the N service links is all 1.
In specific implementation, when the ith training sample is not converted into a customer in the nth link, the customer obtaining conversion rate of the ith training sample in the nth business link is 0.
In an implementation, the passenger conversion rate estimation device 20 may further include: and the execution unit (not shown in fig. 2) is adapted to execute a corresponding operation when the passenger obtaining conversion rate estimation result meets a preset condition.
In a specific implementation, the working principle and the working process of the guest obtaining conversion rate estimation device may refer to any description of the guest obtaining conversion rate estimation method provided in the embodiment of the present invention, and are not described herein again.
The embodiment of the invention further provides a device for estimating the passenger getting conversion rate, which comprises a memory and a processor, wherein the memory stores a computer instruction capable of running on the processor, and the processor executes any step of the method for estimating the passenger getting conversion rate provided by the embodiment of the invention when running the computer instruction.
The embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium is a non-volatile storage medium or a non-transitory storage medium, and has a computer instruction stored thereon, and when the computer instruction runs, the method performs any of the steps of the estimation method of the guest obtaining conversion rate provided by the embodiment of the present invention.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in any computer readable storage medium, and the storage medium may include: ROM, RAM, magnetic or optical disks, and the like.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A method for estimating customer-obtaining conversion rate is characterized by comprising the following steps:
acquiring user information of a second link in the business links;
inputting the user information of the second link into a customer acquisition conversion rate estimation model to obtain a customer acquisition conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link;
obtaining and outputting the estimated result of the customer obtaining conversion rate;
the customer obtaining conversion rate estimation model is obtained by training in the following way:
acquiring a training sample set;
processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample;
generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link;
generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample;
training by adopting a supervised training algorithm to obtain a first pre-estimation model corresponding to a first link based on the user characteristic vectors of all training samples in the training sample set and the guest obtaining conversion information of the first link;
and continuously training the first estimation model based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
2. The method of claim 1, wherein the supervised training algorithm comprises any one of:
neural networks, deep neural networks, logistic regression.
3. The method for predicting the customer acquisition conversion rate according to claim 1, wherein when the ith training sample is converted into a customer in the nth link, the customer acquisition conversion information of the ith training sample in the 1 st to the N service links is 1; or when the ith training sample is not converted into the client in the Nth link, the client obtaining conversion information of the ith training sample in the Nth business link is 0.
4. The method according to any one of claims 1 to 3, further comprising, after obtaining the guest-obtaining conversion rate estimation result:
and when the estimated result of the passenger obtaining conversion rate meets a preset condition, executing corresponding operation.
5. An acquisition conversion rate estimation device, comprising:
the first acquisition unit is suitable for acquiring user information of a second link in the business links;
the estimation unit is suitable for inputting the user information of the second link into a customer obtaining conversion rate estimation model to obtain a customer obtaining conversion rate result; the customer obtaining conversion rate estimation model is generated by the following steps: training based on sample information of a first link in the business links to obtain a first pre-estimation model, and training the first pre-estimation model based on sample information of a second link to obtain the customer-obtaining conversion rate pre-estimation model; the sample information comprises user sample information and corresponding customer acquisition conversion information, and the first link is a front link of the second link;
the second acquisition unit is suitable for acquiring the estimated result of the passenger obtaining conversion rate;
the output unit is suitable for outputting the estimated result of the passenger obtaining conversion rate;
wherein, still include: the model construction unit is suitable for obtaining the customer obtaining conversion rate estimation model through training in the following mode: acquiring a training sample set; processing link information corresponding to all business links corresponding to the ith training sample in the training sample set to obtain user sample information and corresponding customer obtaining conversion information of each business link in the ith training sample; generating a conversion feature vector corresponding to the ith training sample according to the guest obtaining conversion information of each business link in the ith training sample, wherein the conversion feature vector comprises guest obtaining conversion information of the second link and guest obtaining conversion information of the first link; generating a user feature vector corresponding to the ith training sample according to the user data of each business link in the ith training sample; training by adopting a supervised training algorithm to obtain a first pre-estimation model corresponding to a first link based on the user characteristic vectors of all training samples in the training sample set and the guest obtaining conversion information of the first link; and training the first estimation model based on the user characteristic vectors of all the training samples in the training sample set and the corresponding guest obtaining conversion information of the second link to obtain the guest obtaining conversion rate estimation model.
6. The acquisition conversion rate estimation device according to claim 5, wherein the supervised training algorithm comprises any one of: neural networks, deep neural networks, logistic regression.
7. The device for predicting customer acquisition conversion rate according to claim 5, wherein when the ith training sample is converted into a customer in the Nth link, the customer acquisition conversion information of the ith training sample in the 1 st to Nth business links is 1; or when the ith training sample is not converted into the client in the Nth link, the client obtaining conversion information of the ith training sample in the Nth business link is 0.
8. The device for estimating the passenger obtaining conversion rate according to any one of claims 5 to 7, further comprising: and the execution unit is suitable for executing corresponding operation when the estimated result of the passenger obtaining conversion rate meets the preset condition.
9. A passenger conversion rate estimation device, comprising a memory and a processor, wherein the memory stores computer instructions capable of running on the processor, and the processor executes the computer instructions to execute the steps of the passenger conversion rate estimation method according to any one of claims 1 to 4.
10. A computer readable storage medium, which is a non-volatile storage medium or a non-transitory storage medium, and on which computer instructions are stored, wherein the computer instructions are executed to perform the steps of the passenger obtaining conversion rate estimation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295973.5A CN110163652B (en) | 2019-04-12 | 2019-04-12 | Guest-obtaining conversion rate estimation method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910295973.5A CN110163652B (en) | 2019-04-12 | 2019-04-12 | Guest-obtaining conversion rate estimation method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110163652A CN110163652A (en) | 2019-08-23 |
| CN110163652B true CN110163652B (en) | 2021-07-13 |
Family
ID=67639373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910295973.5A Active CN110163652B (en) | 2019-04-12 | 2019-04-12 | Guest-obtaining conversion rate estimation method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110163652B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131227B (en) * | 2019-12-20 | 2023-04-18 | 深圳前海微众银行股份有限公司 | Data processing method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
| CN107133628A (en) * | 2016-02-26 | 2017-09-05 | 阿里巴巴集团控股有限公司 | A kind of method and device for setting up data identification model |
| CN108090788A (en) * | 2017-12-22 | 2018-05-29 | 苏州大学 | Ad conversion rates predictor method based on temporal information integrated model |
| CN108154288A (en) * | 2017-12-07 | 2018-06-12 | 北京三快在线科技有限公司 | New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy |
| CN108230009A (en) * | 2017-11-30 | 2018-06-29 | 北京三快在线科技有限公司 | The Forecasting Methodology and device of a kind of user preference, electronic equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11182804B2 (en) * | 2016-11-17 | 2021-11-23 | Adobe Inc. | Segment valuation in a digital medium environment |
| CN108205766A (en) * | 2016-12-19 | 2018-06-26 | 阿里巴巴集团控股有限公司 | Information-pushing method, apparatus and system |
| CN108171545A (en) * | 2017-12-27 | 2018-06-15 | 银橙(上海)信息技术有限公司 | A kind of conversion ratio predictor method based on level of hierarchy data |
| CN109491740B (en) * | 2018-10-30 | 2021-09-10 | 北京云测信息技术有限公司 | Automatic multi-version funnel page optimization method based on context background information |
-
2019
- 2019-04-12 CN CN201910295973.5A patent/CN110163652B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133628A (en) * | 2016-02-26 | 2017-09-05 | 阿里巴巴集团控股有限公司 | A kind of method and device for setting up data identification model |
| CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
| CN108230009A (en) * | 2017-11-30 | 2018-06-29 | 北京三快在线科技有限公司 | The Forecasting Methodology and device of a kind of user preference, electronic equipment |
| CN108154288A (en) * | 2017-12-07 | 2018-06-12 | 北京三快在线科技有限公司 | New user subsidizes computational methods, device, electronic equipment and the storage medium of strategy |
| CN108090788A (en) * | 2017-12-22 | 2018-05-29 | 苏州大学 | Ad conversion rates predictor method based on temporal information integrated model |
Non-Patent Citations (2)
| Title |
|---|
| "Applying Data Mining Techniques to Direct Marketing Challenges and Solutions";Ying li,Pavankumar Murali,Nan shao,Anshul Sheopuri;《2015IEEE International Conference on Data Mining Workshop (ICDMW)》;20160204;第1-9页 * |
| "基于用户大数据的海尔集团线上精准营销研究";王文璐;《中国优秀硕士学术论文全文数据库 经济与管理科学辑》;20160515(第5期);第152-888页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110163652A (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11521221B2 (en) | Predictive modeling with entity representations computed from neural network models simultaneously trained on multiple tasks | |
| CN110555469B (en) | Method and device for processing interactive sequence data | |
| WO2021027260A1 (en) | Method and device for processing interaction sequence data | |
| US9355067B1 (en) | Distribution of parameter calculation for iterative optimization methods | |
| US20180268318A1 (en) | Training classification algorithms to predict end-user behavior based on historical conversation data | |
| CN111210008B (en) | Method and device for processing interactive data by using LSTM neural network model | |
| CN109344295B (en) | Distributed graph embedding method, device, equipment and system | |
| US10395646B2 (en) | Two-stage training of a spoken dialogue system | |
| CN109035028B (en) | Intelligent consultation strategy generation method and device, electronic equipment and storage medium | |
| CN110689110B (en) | Method and device for processing interaction event | |
| CN110543935A (en) | Method and device for processing interactive sequence data | |
| CN112085293B (en) | Method and device for training interactive prediction model and predicting interactive object | |
| US11651383B2 (en) | Actionable KPI-driven segmentation | |
| US11556848B2 (en) | Resolving conflicts between experts' intuition and data-driven artificial intelligence models | |
| CN111160638B (en) | Conversion estimation method and device | |
| CN111736940A (en) | Business interface display method and device for intelligent counter | |
| CN110163652B (en) | Guest-obtaining conversion rate estimation method and device and computer readable storage medium | |
| KR102152081B1 (en) | Valuation method based on deep-learning and apparatus thereof | |
| CN110390041B (en) | Online learning method and device and computer readable storage medium | |
| CN111258469A (en) | Method and device for processing interactive sequence data | |
| CN108090785B (en) | Method and device for determining user behavior decline tendency and electronic equipment | |
| CN109493186A (en) | The method and apparatus for determining pushed information | |
| CN112328769A (en) | Automatic customer service response method, device and computer readable storage medium | |
| US8126765B2 (en) | Market demand estimation method, system, and apparatus | |
| US20230214757A1 (en) | Optimization processing apparatus, optimization processing method, and computer readable recording medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |