CN110689402A - Method and device for recommending merchants, electronic equipment and readable storage medium - Google Patents
Method and device for recommending merchants, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN110689402A CN110689402A CN201910833752.9A CN201910833752A CN110689402A CN 110689402 A CN110689402 A CN 110689402A CN 201910833752 A CN201910833752 A CN 201910833752A CN 110689402 A CN110689402 A CN 110689402A
- Authority
- CN
- China
- Prior art keywords
- merchant
- user
- candidate
- target
- merchants
- 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 56
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims description 75
- 238000004590 computer program Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 11
- 230000003542 behavioural effect Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 16
- 230000007774 longterm Effects 0.000 description 15
- 238000013500 data storage Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012216 screening Methods 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]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a method and a device for recommending merchants, electronic equipment and a readable storage medium, aiming at enabling a server to recommend merchant information to a user more accurately and improving the operation efficiency of the user. The method comprises the following steps: obtaining user characteristics of a target user and merchant characteristics of a plurality of candidate merchants respectively; inputting the user characteristics and the merchant characteristics into a repurchase rate prediction model to obtain the repurchase rate of the target user for each candidate merchant in the candidate merchants; recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
Description
Technical Field
The embodiment of the application relates to the technical field of internet, in particular to a method and device for recommending merchants, electronic equipment and a readable storage medium.
Background
With the development of internet technology and the popularization of intelligent terminal devices, more and more terminal users are connected To a service end such as an e-commerce platform or an O2O (Online To Offline) platform through a browser or a client To realize Online trading activities such as Online shopping, Online ordering, Online ticket buying and the like. In the related technology, the server actively recommends merchant information to the user according to the historical browsing record of the user, so that the user can quickly enter the homepage of the target merchant without executing search operation, thereby promoting the target merchant to obtain income and improving the operation efficiency of the user.
When recommending merchant information to a user, the current service end generally determines a target merchant with a high historical click rate and/or a high historical conversion rate according to the historical click rate and/or the historical conversion rate of each merchant information, and recommends the information of the target merchant to the user. However, with the current recommendation method, the merchant information recommended to the user can only satisfy the maximization of the current profit of the server and the maximization of the current operation efficiency of the user, but cannot satisfy the maximization of the long-term profit of the server and the maximization of the long-term operation efficiency of the user.
Disclosure of Invention
The embodiment of the application provides a method and a device for recommending merchants, electronic equipment and a readable storage medium, aiming at enabling a server to recommend merchant information to a user more accurately so as to improve long-term income of the server and long-term operation efficiency of the user.
A first aspect of an embodiment of the present application provides a method for recommending a merchant, where the method includes:
obtaining user characteristics of a target user and merchant characteristics of a plurality of candidate merchants respectively;
inputting the user characteristics and the merchant characteristics into a repurchase rate prediction model to obtain the repurchase rate of the target user for each candidate merchant in the candidate merchants;
recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
Optionally, the method further comprises constructing a repurchase rate prediction model.
Optionally, the constructing a repurchase rate prediction model includes:
aiming at the historical users who have placed an order, acquiring a merchant browsing record sequence of the historical users in a preset time period from the order placing time;
aiming at each merchant browsing record in the merchant browsing record sequence, establishing a training sample corresponding to the merchant browsing record, wherein the training sample comprises: the merchant characteristics and the user characteristics corresponding to the merchant browsing records, the reward value corresponding to the user re-purchase condition and the merchant characteristics and the user characteristics corresponding to the next merchant browsing records are recorded;
constructing a training sample set according to training samples corresponding to multiple merchant browsing records;
and training a preset reinforcement learning model based on the training sample set to obtain the repurchase rate prediction model.
Optionally, the method further comprises:
for each merchant browsing record in the sequence of merchant browsing records:
under the condition that the historical user places an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value larger than zero;
and under the condition that the historical user does not place an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value which is not more than zero.
Optionally, in a case that the historical user places an order for a merchant corresponding to the merchant browsing record of this time, determining an incentive value corresponding to a user re-purchasing situation includes:
under the condition that the historical user places an order for a merchant corresponding to the merchant browsing record, determining an order placing time difference between the order placing time of the historical user at this time and the order placing time of the historical user at the last time;
and determining an incentive value corresponding to the user re-purchasing condition according to the order time difference and a preset incentive value function, wherein the incentive value is negatively related to the order time difference.
Optionally, determining an incentive value corresponding to a user re-purchase condition according to the order time difference and a preset incentive value function, including:
determining the reward value corresponding to the user re-purchase condition according to the following formula:
wherein r represents an award value corresponding to the user re-purchase condition, C represents a weight adjusting coefficient, and T represents the ordering time difference.
Optionally, the user characteristics include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic.
Optionally, the merchant characteristics include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price.
A second aspect of the embodiments of the present application provides an apparatus for recommending a merchant, where the apparatus includes:
the characteristic obtaining module is used for obtaining the user characteristic of the target user and the merchant characteristics of the candidate merchants;
the purchase-resuming rate obtaining module is used for inputting the user characteristics and the merchant characteristics into a purchase-resuming rate prediction model to obtain the purchase-resuming rate of the target user for each candidate merchant in the candidate merchants;
and the target merchant recommending module is used for recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
Optionally, the apparatus further comprises:
and the model construction module is used for constructing a repurchase rate prediction model.
Optionally, the model building module comprises:
the merchant browsing record sequence submodule is used for acquiring a merchant browsing record sequence of the historical user in a preset time period from the ordering time aiming at the ordered historical user;
a training sample establishing sub-module, configured to establish, for each merchant browsing record in the merchant browsing record sequence, a training sample corresponding to the merchant browsing record, where the training sample includes: the merchant characteristics and the user characteristics corresponding to the merchant browsing records, the reward value corresponding to the user re-purchase condition and the merchant characteristics and the user characteristics corresponding to the next merchant browsing records are recorded;
the training sample set constructing submodule is used for constructing a training sample set according to training samples corresponding to multiple merchant browsing records;
and the model training submodule is used for training a preset reinforcement learning model based on the training sample set to obtain the repurchase rate prediction model.
Optionally, the model building module further comprises:
the reward value determining submodule is used for determining that the reward value corresponding to the user re-purchasing condition is a value larger than zero under the condition that the historical user places an order for the merchant corresponding to the merchant browsing record for each merchant browsing record in the merchant browsing record sequence; and under the condition that the historical user does not place an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value which is not more than zero.
Optionally, the prize value determination sub-module comprises:
the ordering time difference determining unit is used for determining the ordering time difference between the ordering time of the historical user at this time and the ordering time of the historical user at the last time under the condition that the historical user orders the merchant corresponding to the browsing record of the merchant;
and the reward value determining unit is used for determining a reward value corresponding to the user re-purchasing condition according to the ordering time difference and a preset reward value function, and the reward value is negatively related to the ordering time difference.
Optionally, the bonus value determination unit includes:
the reward value determining subunit is used for determining a reward value corresponding to the user re-purchase condition according to the following formula:
wherein r represents an award value corresponding to the user re-purchase condition, C represents a weight adjusting coefficient, and T represents the ordering time difference.
Optionally, the user characteristics include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic.
Optionally, the merchant characteristics include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price.
A third aspect of embodiments of the present application provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the steps in the method according to the first aspect of the present application.
A fourth aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect of the present application when executed.
By adopting the method for recommending the merchants, provided by the embodiment of the application, the user characteristics of the target user and the merchant characteristics of the candidate merchants are obtained firstly, and then the characteristics are input into a pre-trained repurchase rate prediction model to obtain the repurchase rate of the target user for each candidate merchant in the candidate merchants. Wherein the repurchase rate of each candidate merchant characterizes the long-distance demand of the target user for the candidate merchant. The higher the rate of repurchase is, the greater the long-distance demand of the target user for the candidate merchant is, and the greater the probability that the target user places an order again for the candidate merchant is. And finally, recommending the target merchant to the target user according to the respective repurchase rates of the candidate merchants, thereby meeting the long-term demand of the user, improving the long-term income of the server and improving the long-term operation efficiency of the user on the homepage of the server.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flow chart illustrating the training of a repurchase rate prediction model according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a training sample proposed in an embodiment of the present application;
FIG. 3 is a schematic diagram of a method for determining a prize value according to an embodiment of the present application;
FIG. 4 is a flow chart of a method for recommending merchants according to an embodiment of the present application;
fig. 5 is a schematic interaction diagram of a server and a client according to an embodiment of the present application;
fig. 6 is a schematic diagram of an apparatus for recommending merchants, according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the technical field of internet, after a browser or a client user carries out a server homepage, the server can actively recommend merchant information to the user according to a historical browsing record of the user, so that the user can quickly enter the target merchant homepage without executing a search operation, and the operation efficiency of the user is improved. When recommending merchant information to a user, the current service end generally determines a target merchant with a high historical click rate and/or a high historical conversion rate according to the historical click rate and/or the historical conversion rate of each merchant information, and recommends the information of the target merchant to the user. However, with the current recommendation method, the merchant information recommended to the user can only satisfy the maximization of the current profit of the server and the maximization of the current operation efficiency of the user, but cannot satisfy the maximization of the long-term profit of the server and the maximization of the long-term operation efficiency of the user.
In view of this, the embodiments of the present application propose: the method comprises the steps of firstly obtaining user characteristics of a target user and merchant characteristics of a plurality of candidate merchants, and then determining the re-purchase rate of the target user for each candidate merchant of the candidate merchants according to the characteristics. And finally, recommending the target merchant to the target user according to the respective repurchase rates of the candidate merchants, thereby meeting the long-term demand of the user, improving the long-term income of the server and improving the long-term operation efficiency of the user on the homepage of the server.
In addition, in order to implement the method provided by the embodiment of the present application more intelligently, in the embodiment of the present application, a training sample is collected for a preset reinforcement learning model, a training sample set is constructed, and finally, the preset reinforcement learning model is trained based on the training sample set, so as to obtain a repurchase rate prediction model. The preset reinforcement learning model may be a model commonly used in the related art. The repurchase rate prediction model can be used for executing part or all of the steps in the method provided by the embodiment of the application.
Referring to fig. 1, fig. 1 is a flowchart illustrating a training process of a repurchase rate prediction model according to an embodiment of the present application. As shown in fig. 1, the training process includes the following steps:
step S11: and aiming at the historical users who have placed the order, obtaining a merchant browsing record sequence of the historical users in a preset time period from the order placing time.
In this embodiment, the merchant browsing record sequence of the historical user in the preset time period from the order placing time is as follows: and taking the one-time ordering behavior of the historical user as a starting point, and pushing merchant information to the historical user by the server after the historical user continuously enters the homepage of the server for multiple times in a preset time period, and/or a merchant information sequence consisting of the merchant information actively searched by the historical user.
Each merchant browsing record in the merchant browsing record sequence comprises merchant information and also comprises: the time stamp when the merchant information is browsed or pushed, and a mark whether the user places an order for the merchant corresponding to the merchant information.
By way of example, assuming that a certain historical user generates ordering behavior on day 4, 16, taking day 4, 16 as a starting point and taking day 15 as a preset time period, referring to table 1, table 1 schematically shows a sequence of merchant browsing records of the historical user.
TABLE 1 Merchant browsing records sequence Listing of historical users
| Serial number | Time of day | Merchant information | Whether to place an order |
| 1 | 11 o' clock 23 points on 17 th 4 th day | c Merchant | Do not make an order |
| 2 | 4 month, 17 days, 11 o' clock, 25 min | b Merchant | Order placing |
| 3 | 11 points 49 points on 21 days 4 months | c Merchant | Do not make an order |
| 4 | 18 o.33 points in 4 months, 22 days | d Merchant | Do not make an order |
| 5 | 4 month, 26 days 11 point and 19 points | e Merchant | Do not make an order |
| 6 | 11 o' clock 24 points on 26 days 4 months | d Merchant | Order placing |
| 7 | 12 o' clock 07 points on 29 days 4 months | b Merchant | Order placing |
| 8 | 18 o 51 points on 5.1.1 | f merchants | Do not make an order |
| 9 | 19 o' clock and 15 min on 5 months, 1 day | f merchants | Order placing |
Each line in table 1 represents a merchant browsing record, which indicates that the historical user browses or is pushed with the c merchant information at 11 points 23 on 17 days 4 months by the first behavior example in table 1, and the historical user does not place an order at the c merchant.
Step S12: aiming at each merchant browsing record in the merchant browsing record sequence, establishing a training sample corresponding to the merchant browsing record, wherein the training sample comprises: the merchant characteristics and the user characteristics corresponding to the merchant browsing records, the reward value corresponding to the user re-purchasing condition and the merchant characteristics and the user characteristics corresponding to the next merchant browsing records.
Referring to fig. 2, fig. 2 is a schematic diagram of a training sample according to an embodiment of the present application. As shown in fig. 2, where s represents a user characteristic, a represents a merchant characteristic, and r represents a prize value. The first training sample in fig. 2 is taken as an example for explanation: wherein s1 represents the user characteristic corresponding to the first merchant browsing record, a1 represents the merchant characteristic corresponding to the first merchant browsing record, r1 represents the reward value corresponding to the user re-purchase condition in the first merchant browsing record, s2 represents the user characteristic corresponding to the second merchant browsing record, and a2 represents the merchant characteristic corresponding to the second merchant browsing record.
Following table 1, the description will be made by taking the browsing record of the 2 nd merchant in table 1 as an example: the training sample corresponding to the merchant browsing record comprises: the characteristic of the merchant b is divided into time points of 11 points 25 on day 4 and 17, the user characteristic of the historical user is divided into time points 25 on day 11 on day 4 and 17, the reward value corresponding to the ordering behavior of the historical user, the merchant characteristic of the merchant c is divided into time points 49 on day 11 on day 4 and 21, and the user characteristic of the historical user is divided into time points 49 on day 11 on day 4 and 21.
In this embodiment, the merchant characteristics may include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price. In particular, the merchant characteristics may be vectorized representations of the several above, such as word vectors.
In this embodiment, the user characteristics may include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic. In particular, the user features may be vectorized representations of the above, such as word vectors.
The consumption preference of the user refers to the preference of the user on the commodity category, for example, the selling business is taken as an example, and the consumption preference of the user can be the taste preference of the user. The user representation refers to user attribute information extracted from massive user data, and the user attribute information may include one or more of the following information: basic attributes such as gender, occupation, age group, income level, marriage and childbearing condition and education level, behavior attributes such as APP use frequency and order taking probability, and interest attributes such as take-out preference, movie preference and commodity preference. The behavioral characteristics of the user may refer to a rate of orders placed when the user browses merchant information multiple times, a frequency with which the user uses the client, a probability with which the user uses the coupon, and so on.
In this embodiment, when the training sample corresponding to the merchant browsing record is established for each merchant browsing record, the merchant characteristics and the user characteristics at the time corresponding to the merchant browsing record can be obtained from the cached log, and the merchant characteristics and the user characteristics at the time corresponding to the next merchant browsing record can be obtained from the cached log.
Or, after the historical user produces ordering behavior in 16 days 4 months, when step S11 is executed, for each merchant browsing of the historical user, recording the merchant characteristics and the user characteristics at that time, and using the recorded merchant characteristics and user characteristics as part of the information in the record of the merchant browsing. Therefore, when the training sample corresponding to the merchant browsing record is established for each merchant browsing record, the merchant characteristics and the user characteristics are directly read from the merchant browsing record, and the merchant characteristics and the user characteristics are read from the next merchant browsing record.
In this embodiment, the reward value corresponding to the user re-purchase condition is used to represent whether the historical user places an order for the merchant in the merchant browsing record. During implementation of the method, if the historical user generates ordering behaviors aiming at the merchants in the merchant browsing records, the corresponding reward value is a larger value. If the historical user does not place an order for the merchant in the merchant browsing record, the corresponding reward value is a smaller value.
In this embodiment, when a training sample is established for each merchant browsing record in the merchant browsing record sequence, in order to determine an award value in the training sample, a feasible implementation manner is as follows: for each merchant browsing record in the sequence of merchant browsing records: under the condition that the historical user places an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value larger than zero; and under the condition that the historical user does not place an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value which is not more than zero.
Illustratively, table 1 above is followed, wherein the reward value in the training sample corresponding to the merchant browsing record with the serial number 1, 3, 4, 5 or 8 is not greater than 0, and the reward value in the training sample corresponding to the merchant browsing record with the serial number 2, 6, 7 or 9 is greater than 0.
Fig. 3 is a specific manner of determining an incentive value when a historical user places an order for a merchant corresponding to a certain merchant browsing record, where fig. 3 is a schematic diagram of a method for determining an incentive value according to an embodiment of the present application. As shown in fig. 3, the method of determining a prize value includes the steps of:
step S12-1: under the condition that the historical user places an order for a merchant corresponding to the merchant browsing record, determining an order placing time difference between the order placing time of the historical user at this time and the order placing time of the historical user at the last time;
step S12-2: and determining an incentive value corresponding to the user re-purchasing condition according to the order time difference and a preset incentive value function, wherein the incentive value is negatively related to the order time difference.
Illustratively, following the above table 1, the order placing behavior of the historical user is recorded in the merchant browsing record with the serial number 2, and the difference between the order placing time (4 months and 17 days) of the order placing behavior and the last order placing time (4 months and 16 days) is 1 day. The order placing behavior of the historical user is recorded in the merchant browsing record with the serial number of 6, and the difference between the order placing time (4 months and 26 days) of the order placing behavior and the last order placing time (4 months and 17 days) is 9 days. After the step S12-2, the reward value in the training sample corresponding to the merchant browsing record with the serial number 2 is greater than the reward value in the training sample corresponding to the merchant browsing record with the serial number 6.
Wherein the reward value function may be in the form of: and r is C/(T +1), wherein r represents an award value corresponding to the user re-purchase condition, C represents a weight adjusting coefficient, and T represents the ordering time difference. The weight adjusting coefficient C is a positive number which is larger than 0, and the weight adjusting coefficient can be manually changed according to the training requirement. The unit of the order time difference can be minutes, hours, days, etc., which is not limited in this application.
By determining the reward value in the manner of the above-described steps S12-1 and S12-2, the resulting reward value not only characterizes whether the historical user has made a repurchase (i.e., placed an order), but also characterizes the time between repurchasings. The reinforcement learning model is trained by using the training sample comprising the reward value, so that the repurchase rate prediction model obtained by training can recommend merchant information according to long-distance requirements of the user, the repurchase probability of the user is improved, and the time for actively searching and browsing is reduced for the user. The repurchase rate prediction model can also distinguish the repurchase interval length factor, can recommend merchants which enable the repurchase time of the user to be shorter, and improves the order-taking frequency of the user, so that the recommendation accuracy is further improved, and the operation efficiency of the user is further improved.
Step S13: and constructing a training sample set according to training samples corresponding to the multiple merchant browsing records.
In this embodiment, the training sample set includes training samples corresponding to the multiple merchant browsing records, and the training samples are sorted according to the merchant browsing record time corresponding to each training sample. As shown in fig. 2, the training samples 1 to 4 form a training sample set, and the training samples in the training sample set are ordered according to time sequence as follows: training sample 1, training sample 2, training sample 3, and training sample 4.
Step S14: and training a preset reinforcement learning model based on the training sample set to obtain the repurchase rate prediction model.
In this embodiment, based on the training sample set, the preset reinforcement learning model is trained to obtain the repurchase rate prediction model. The preset reinforcement learning model may be a DQN (Deep Q Network) model, a DDPG (Deep deterministic Policy Gradient) model, or a DDQN (Double DQN; Double Deep Q Network) model. The repurchase rate prediction model can be used as an optional means for executing part or all of the steps in the method provided by the embodiment of the application.
Referring to fig. 4, fig. 4 is a flowchart of a method for recommending merchants according to an embodiment of the present application. As shown in fig. 4, the method comprises the steps of:
step S41: user characteristics of the target user and merchant characteristics of each of the plurality of candidate merchants are obtained.
Wherein the user characteristics include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic. The user characteristic may be an abstract representation of at least one of the foregoing, such as a word vector. The merchant characteristics include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price. The merchant characteristic may be an abstract representation of at least one of the foregoing, such as a word vector.
Wherein, the target user may refer to: a user who is opening a client, or a user who is accessing a server homepage through a browser. Taking a takeout service end as an example, the service end simultaneously faces a large number of users, takeout clients are installed on terminal devices of some users, and browsers are installed on terminal devices of some users. Due to the fact that the user access concurrency of the takeout service side is large, at a certain moment, a plurality of target users may exist in the takeout service side at the same time, wherein one part of the target users are opening the takeout client side, and the other part of the target users are entering the homepage of the takeout service side through the browser. The takeout service side executes the above-described step S41, the following step S42, and the following step S43 for each target user.
The candidate merchants may refer to: aiming at the target user, a plurality of merchants are screened out by the existing screening mode. Such as a plurality of merchants screened by distribution distance, user taste, sales volume, historical ratings, or advertising auctions.
Step S42: inputting the user characteristics and the merchant characteristics into a repurchase rate prediction model to obtain the repurchase rate of the target user for each candidate merchant in the candidate merchants.
The repurchase rate prediction model may be obtained by training in the manner from step S11 to step S14, or may be obtained by training in another manner, and the source and the training manner of the repurchase rate prediction model in this step are not limited.
In this embodiment, the user feature and the plurality of merchant features may be combined in a one-to-one manner to form a plurality of feature combinations, where each feature combination includes the user feature and a merchant feature of a candidate merchant. And then, sequentially inputting the plurality of feature combinations into a repurchase rate prediction model to obtain the repurchase rate output by the repurchase rate prediction model aiming at each feature combination, wherein the repurchase rate indicates the long-distance demand of a target user aiming at the candidate merchants corresponding to the feature combinations. The higher the rate of repurchase is, the greater the long-distance demand of the target user for the candidate merchant is, and the greater the ordering probability of the target user for the candidate merchant is.
Step S43: recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
For example, the candidate merchant with the highest re-purchase rate in the multiple candidate merchants can be directly used as the target merchant and recommended to the target user.
Or, in order to increase the exploratory performance of the recommendation, the recommendation probability of each candidate merchant may be determined according to the repurchase rates of a plurality of candidate merchants, and then the candidate merchant is recommended to the target user according to the recommendation probability of each candidate merchant. For example, the respective repurchase rates of the candidate merchants A, B, C are: 0.2, 0.6, 0.4, the recommended probability of merchant a is equal to 0.2/(0.2+0.6+0.4) ═ 0.17, the recommended probability of merchant B is equal to 0.6/(0.2+0.6+0.4) ═ 0.50, and the recommended probability of merchant C is equal to 0.4/(0.2+0.6+0.4) ═ 0.33. In this way, when recommending candidate merchants to the target user, merchant a is recommended with a probability of 0.17, merchant B is recommended with a probability of 0.5, and merchant C is recommended with a probability of 0.33. In other words, each candidate merchant has a likelihood of being recommended, and the likelihoods of being recommended by the candidate merchants are ranked by size as: merchant B, merchant C, and merchant a.
Alternatively, after determining the repurchase rate of each candidate merchant, the target merchant may be determined comprehensively according to other considerations of each candidate merchant, such as delivery distance, user taste, sales volume, historical evaluation, advertisement bidding, Click Through Rate (CTR), or conversion rate (CVR).
By implementing the method for recommending merchants, which includes steps S41 to S43, the user characteristics of the target user and the merchant characteristics of each of the candidate merchants are obtained first, and then the characteristics are input into a pre-trained rate prediction model, so as to obtain the rate of repurchase of the target user for each of the candidate merchants. Wherein the repurchase rate of each candidate merchant characterizes the long-distance demand of the target user for the candidate merchant. The higher the rate of repurchase is, the greater the long-distance demand of the target user for the candidate merchant is, and the greater the ordering probability of the target user for the candidate merchant is. And finally, recommending the target merchant to the target user according to the respective repurchase rates of the candidate merchants, thereby meeting the long-term demand of the user, improving the long-term income of the server and improving the long-term operation efficiency of the user on the homepage of the server.
Referring to fig. 5, fig. 5 is a schematic diagram of interaction between a server and a client according to an embodiment of the present application. The server shown in fig. 5 is used for implementing the method for recommending merchants in any of the above method embodiments. As shown in fig. 5:
the server side mainly comprises a data storage module and a merchant recommending module. The data storage module stores a user ordering log, a user clicking log and a merchant exposure log, and also stores merchant characteristics and user characteristics. The merchant recommending module comprises a repurchase rate forecasting model and a releasing service interface. The repurchase rate prediction model is used for receiving the user characteristics of the target user and the merchant characteristics of the candidate merchant and outputting the repurchase rate of the target user for the candidate merchant. And the delivery service interface outputs the information of the target merchants in the candidate merchants to the client, and receives the behaviors of clicking, ordering and the like of the client aiming at the target merchants.
Specifically, as shown in fig. 5, the data storage module sends log information such as a user order placing log, a user click log, and a merchant exposure log to the KV (key-value) module sequentially through the distributed publish-subscribe message system Kafka and the stream processing framework Storm, and the data storage module sends user features and merchant features to the KV module sequentially through the data warehouse tool HIVE and the distributed computing model MapReduce. Thus, there are multiple key-value pairs in the KV module that consist of user characteristics and merchant characteristics. When the online shopping rate forecasting model is applied on line, the user characteristics of the target user and the merchant characteristics of the candidate merchants are read from the KV module, and therefore the shopping rate of the candidate merchants is output.
In addition, as shown in fig. 5, the client further sends information such as a click behavior and an order placing behavior of the user to the data storage module, so that the data storage module generates an order placing log of the user and a click log of the user according to the information such as the click behavior and the order placing behavior. The server side constructs a training sample set according to log information such as a user ordering log, a user clicking log, a merchant exposure log and the like, and is used for training and updating the purchase-resuming rate prediction model.
Based on the same inventive concept, an embodiment of the application provides a device for recommending merchants. Referring to fig. 6, fig. 6 is a schematic diagram of an apparatus for recommending merchants, according to an embodiment of the present application. As shown in fig. 6, the apparatus includes:
a feature obtaining module 61, configured to obtain a user feature of the target user and merchant features of each of the multiple candidate merchants;
a purchase recurrence rate obtaining module 62, configured to input the user characteristic and the merchant characteristics into a purchase recurrence rate prediction model, so as to obtain a purchase recurrence rate of the target user for each candidate merchant in the candidate merchants;
and a target merchant recommending module 63, configured to recommend a target merchant to the target user according to a repurchase rate of the target user for each candidate merchant in the multiple candidate merchants, where the target merchant is at least one of the multiple candidate merchants.
In a possible embodiment, the apparatus further comprises:
and the model construction module is used for constructing a repurchase rate prediction model.
In one possible embodiment, the model building module comprises:
the merchant browsing record sequence submodule is used for acquiring a merchant browsing record sequence of the historical user in a preset time period from the ordering time aiming at the ordered historical user;
a training sample establishing sub-module, configured to establish, for each merchant browsing record in the merchant browsing record sequence, a training sample corresponding to the merchant browsing record, where the training sample includes: the merchant characteristics and the user characteristics corresponding to the merchant browsing records, the reward value corresponding to the user re-purchase condition and the merchant characteristics and the user characteristics corresponding to the next merchant browsing records are recorded;
the training sample set constructing submodule is used for constructing a training sample set according to training samples corresponding to multiple merchant browsing records;
and the model training submodule is used for training a preset reinforcement learning model based on the training sample set to obtain the repurchase rate prediction model.
In one possible embodiment, the model building module further comprises:
the reward value determining submodule is used for determining that the reward value corresponding to the user re-purchasing condition is a value larger than zero under the condition that the historical user places an order for the merchant corresponding to the merchant browsing record for each merchant browsing record in the merchant browsing record sequence; and under the condition that the historical user does not place an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value which is not more than zero.
In one possible embodiment, the prize value determination sub-module comprises:
the ordering time difference determining unit is used for determining the ordering time difference between the ordering time of the historical user at this time and the ordering time of the historical user at the last time under the condition that the historical user orders the merchant corresponding to the browsing record of the merchant;
and the reward value determining unit is used for determining a reward value corresponding to the user re-purchasing condition according to the ordering time difference and a preset reward value function, and the reward value is negatively related to the ordering time difference.
In one possible embodiment, the prize value determination unit comprises:
the reward value determining subunit is used for determining a reward value corresponding to the user re-purchase condition according to the following formula:
wherein r represents an award value corresponding to the user re-purchase condition, C represents a weight adjusting coefficient, and T represents the ordering time difference.
In one possible embodiment, the user features include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic.
In one possible implementation, the merchant characteristics include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price.
Based on the same inventive concept, another embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method according to any of the above-mentioned embodiments of the present application.
Based on the same inventive concept, another embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the electronic device implements the steps of the method according to any of the above embodiments of the present application.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one of skill in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the true scope of the embodiments of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method, the device, the electronic device and the readable storage medium for recommending the merchant provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understand the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (11)
1. A method of recommending merchants, comprising:
obtaining user characteristics of a target user and merchant characteristics of a plurality of candidate merchants respectively;
inputting the user characteristics and the merchant characteristics into a repurchase rate prediction model to obtain the repurchase rate of the target user for each candidate merchant in the candidate merchants;
recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
2. The method of claim 1, further comprising constructing a repurchase rate prediction model.
3. The method of claim 2, wherein the constructing a repurchase rate prediction model comprises:
aiming at the historical users who have placed an order, acquiring a merchant browsing record sequence of the historical users in a preset time period from the order placing time;
aiming at each merchant browsing record in the merchant browsing record sequence, establishing a training sample corresponding to the merchant browsing record, wherein the training sample comprises: the merchant characteristics and the user characteristics corresponding to the merchant browsing records, the reward value corresponding to the user re-purchase condition and the merchant characteristics and the user characteristics corresponding to the next merchant browsing records are recorded;
constructing a training sample set according to training samples corresponding to multiple merchant browsing records;
and training a preset reinforcement learning model based on the training sample set to obtain the repurchase rate prediction model.
4. The method of claim 3, further comprising:
for each merchant browsing record in the sequence of merchant browsing records:
under the condition that the historical user places an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value larger than zero;
and under the condition that the historical user does not place an order for the merchant corresponding to the browsing record of the merchant, determining that the reward value corresponding to the user re-purchasing condition is a value which is not more than zero.
5. The method according to claim 4, wherein in the case that the historical user places an order for the merchant corresponding to the merchant browsing record, determining the reward value corresponding to the user who purchases again comprises:
under the condition that the historical user places an order for a merchant corresponding to the merchant browsing record, determining an order placing time difference between the order placing time of the historical user at this time and the order placing time of the historical user at the last time;
and determining an incentive value corresponding to the user re-purchasing condition according to the order time difference and a preset incentive value function, wherein the incentive value is negatively related to the order time difference.
6. The method according to claim 5, wherein determining the reward value corresponding to the user re-purchase condition according to the ordering time difference and a preset reward value function comprises:
determining the reward value corresponding to the user re-purchase condition according to the following formula:
wherein r represents an award value corresponding to the user re-purchase condition, C represents a weight adjusting coefficient, and T represents the ordering time difference.
7. The method of any of claims 1-6, wherein the user characteristics include at least one of: a consumption preference of the user, a geographic location of the user, a user representation, and a behavioral characteristic.
8. The method of any of claims 1-6, wherein the merchant characteristics include at least one of: merchant ID, item class ID, delivery duration, sales volume, full reduction, and customer unit price.
9. An apparatus for recommending merchants, the apparatus comprising:
the characteristic obtaining module is used for obtaining the user characteristic of the target user and the merchant characteristics of the candidate merchants;
the purchase-resuming rate obtaining module is used for inputting the user characteristics and the merchant characteristics into a purchase-resuming rate prediction model to obtain the purchase-resuming rate of the target user for each candidate merchant in the candidate merchants;
and the target merchant recommending module is used for recommending a target merchant to the target user according to the repurchase rate of the target user for each candidate merchant in the candidate merchants, wherein the target merchant is at least one of the candidate merchants.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executed implements the steps of the method according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833752.9A CN110689402A (en) | 2019-09-04 | 2019-09-04 | Method and device for recommending merchants, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910833752.9A CN110689402A (en) | 2019-09-04 | 2019-09-04 | Method and device for recommending merchants, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110689402A true CN110689402A (en) | 2020-01-14 |
Family
ID=69107833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910833752.9A Pending CN110689402A (en) | 2019-09-04 | 2019-09-04 | Method and device for recommending merchants, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689402A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275493A (en) * | 2020-02-10 | 2020-06-12 | 拉扎斯网络科技（上海）有限公司 | List data processing method and device, server and nonvolatile storage medium |
| CN111311332A (en) * | 2020-02-28 | 2020-06-19 | 北京互金新融科技有限公司 | User data processing method and device |
| CN111523922A (en) * | 2020-04-01 | 2020-08-11 | 北京三快在线科技有限公司 | Information pushing method and system, computer device and cloud server system |
| CN111582991A (en) * | 2020-05-13 | 2020-08-25 | 中国银行股份有限公司 | Product information recommendation method and device |
| CN112948693A (en) * | 2021-03-30 | 2021-06-11 | 北京三快在线科技有限公司 | Information pushing method and device, storage medium and electronic equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120296701A1 (en) * | 2008-07-14 | 2012-11-22 | Wahrheit, Llc | System and method for generating recommendations |
| CN106157650A (en) * | 2016-07-11 | 2016-11-23 | 东南大学 | A kind of through street traffic efficiency ameliorative way controlled based on intensified learning variable speed-limit |
| CN106802553A (en) * | 2017-01-13 | 2017-06-06 | 清华大学 | A kind of railway locomotive operation control system hybrid tasks scheduling method based on intensified learning |
| CN107194492A (en) * | 2017-04-13 | 2017-09-22 | 南京邮电大学 | The optimization method that a kind of businessman based on position social networks is recommended |
| CN107451840A (en) * | 2016-05-31 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | A kind of Transaction Information method for pushing and device |
| CN107742245A (en) * | 2017-10-31 | 2018-02-27 | 北京小度信息科技有限公司 | A kind of merchant information recommends method, apparatus and equipment |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| US20180374138A1 (en) * | 2017-06-23 | 2018-12-27 | Vufind Inc. | Leveraging delayed and partial reward in deep reinforcement learning artificial intelligence systems to provide purchase recommendations |
| CN109118337A (en) * | 2018-08-28 | 2019-01-01 | 深圳市烽焌信息科技有限公司 | Consume the recommended method and Related product of businessman |
| CN110135871A (en) * | 2018-02-02 | 2019-08-16 | 北京京东尚科信息技术有限公司 | Calculate the method and apparatus that user purchases the phase again |
| CN110197415A (en) * | 2019-04-23 | 2019-09-03 | 北京三快在线科技有限公司 | A kind of recommended method, device, electronic equipment and readable storage medium storing program for executing |
-
2019
- 2019-09-04 CN CN201910833752.9A patent/CN110689402A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120296701A1 (en) * | 2008-07-14 | 2012-11-22 | Wahrheit, Llc | System and method for generating recommendations |
| CN107451840A (en) * | 2016-05-31 | 2017-12-08 | 百度在线网络技术（北京）有限公司 | A kind of Transaction Information method for pushing and device |
| CN106157650A (en) * | 2016-07-11 | 2016-11-23 | 东南大学 | A kind of through street traffic efficiency ameliorative way controlled based on intensified learning variable speed-limit |
| CN106802553A (en) * | 2017-01-13 | 2017-06-06 | 清华大学 | A kind of railway locomotive operation control system hybrid tasks scheduling method based on intensified learning |
| CN107194492A (en) * | 2017-04-13 | 2017-09-22 | 南京邮电大学 | The optimization method that a kind of businessman based on position social networks is recommended |
| US20180374138A1 (en) * | 2017-06-23 | 2018-12-27 | Vufind Inc. | Leveraging delayed and partial reward in deep reinforcement learning artificial intelligence systems to provide purchase recommendations |
| CN107742245A (en) * | 2017-10-31 | 2018-02-27 | 北京小度信息科技有限公司 | A kind of merchant information recommends method, apparatus and equipment |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| CN110135871A (en) * | 2018-02-02 | 2019-08-16 | 北京京东尚科信息技术有限公司 | Calculate the method and apparatus that user purchases the phase again |
| CN109118337A (en) * | 2018-08-28 | 2019-01-01 | 深圳市烽焌信息科技有限公司 | Consume the recommended method and Related product of businessman |
| CN110197415A (en) * | 2019-04-23 | 2019-09-03 | 北京三快在线科技有限公司 | A kind of recommended method, device, electronic equipment and readable storage medium storing program for executing |
Non-Patent Citations (3)
| Title |
|---|
| YYMWATER: "强化学习系列一——基于深度强化学习的新闻推荐模型DRN", pages 1 - 5, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/58280384> * |
| 慕课网: "慕课网-个性化推荐系统实战入门", pages 1 - 7, Retrieved from the Internet <URL:https://www.kukuxiaai.com/blog/2019-07/%E6%85%95%E8%AF%BE%E7%BD%91-%E4%B8%AA%E6%80%A7%E5%8C%96%E6%8E%A8%E8%8D%90%E7%B3%BB%E7%BB%9F%E5%AE%9E%E6%88%98%E5%85%A5%E9%97%A8/> * |
| 段瑾: "强化学习在美团"猜你喜欢"的实践", pages 1 - 12, Retrieved from the Internet <URL:https://tech.meituan.com/2018/11/15/reinforcement-learning-in-mt-recommend-system.html> * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275493A (en) * | 2020-02-10 | 2020-06-12 | 拉扎斯网络科技（上海）有限公司 | List data processing method and device, server and nonvolatile storage medium |
| CN111275493B (en) * | 2020-02-10 | 2023-08-22 | 拉扎斯网络科技（上海）有限公司 | Processing method and device of list data, server and nonvolatile storage medium |
| CN111311332A (en) * | 2020-02-28 | 2020-06-19 | 北京互金新融科技有限公司 | User data processing method and device |
| CN111523922A (en) * | 2020-04-01 | 2020-08-11 | 北京三快在线科技有限公司 | Information pushing method and system, computer device and cloud server system |
| CN111523922B (en) * | 2020-04-01 | 2023-08-29 | 北京三快在线科技有限公司 | Information pushing method, system, computer device and cloud server system |
| CN111582991A (en) * | 2020-05-13 | 2020-08-25 | 中国银行股份有限公司 | Product information recommendation method and device |
| CN111582991B (en) * | 2020-05-13 | 2023-09-01 | 中国银行股份有限公司 | Product information recommendation method and device |
| CN112948693A (en) * | 2021-03-30 | 2021-06-11 | 北京三快在线科技有限公司 | Information pushing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108665329B (en) | Commodity recommendation method based on user browsing behavior | |
| US10409821B2 (en) | Search result ranking using machine learning | |
| Gunter et al. | Exploring the predictive ability of LIKES of posts on the Facebook pages of four major city DMOs in Austria | |
| CN110689402A (en) | Method and device for recommending merchants, electronic equipment and readable storage medium | |
| KR102297669B1 (en) | System for providing matching service for connecting between manufacturer and distributor | |
| CN102541971A (en) | Mapping advertiser intents to keywords | |
| CN106447463A (en) | Commodity recommendation method based on Markov decision-making process model | |
| US9965526B1 (en) | Data mining for multiple item comparisons | |
| EP3822902A1 (en) | Systems and methods for customization of reviews | |
| US20170186065A1 (en) | System and Method of Product Selection for Promotional Display | |
| KR102049777B1 (en) | Item recommendation method and apparatus based on user behavior | |
| Chen et al. | Common pitfalls in training and evaluating recommender systems | |
| CN110674391A (en) | Product data pushing method and system based on big data and computer equipment | |
| CN113424207B (en) | System and method for efficiently training understandable models | |
| KR20130038889A (en) | Object customization and management system | |
| US11494686B1 (en) | Artificial intelligence system for relevance analysis of data stream items using similarity groups and attributes | |
| CN111429214A (en) | Transaction data-based buyer and seller matching method and device | |
| JP6899805B2 (en) | Characteristic estimation device, characteristic estimation method, characteristic estimation program, etc. | |
| CN114595323A (en) | Portrait construction, recommendation, model training method, apparatus, device and storage medium | |
| CA3098792A1 (en) | Systems and methods for customization of reviews | |
| CN112784021A (en) | System and method for using keywords extracted from reviews | |
| US20140136280A1 (en) | Predictive Tool Utilizing Correlations With Unmeasured Factors Influencing Observed Marketing Activities | |
| KR20080087348A (en) | Method for recommending search word service using relation factor of business keyword and system thereof | |
| CN112015970A (en) | Product recommendation method, related equipment and computer storage medium | |
| CN110020118B (en) | Method and device for calculating similarity between users |
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 |