CN112288569A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN112288569A CN112288569A CN202011320803.7A CN202011320803A CN112288569A CN 112288569 A CN112288569 A CN 112288569A CN 202011320803 A CN202011320803 A CN 202011320803A CN 112288569 A CN112288569 A CN 112288569A
- Authority
- CN
- China
- Prior art keywords
- model
- user
- products
- time
- product
- 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
- 238000003672 processing method Methods 0.000 title abstract description 9
- 238000000034 method Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 description 5
- 230000003542 behavioural effect Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001737 promoting effect Effects 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q30/0282—Rating or review of business operators or products
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a data processing method and device.A server firstly determines a first product set matched with user information after receiving the user information of a first user from a channel device, and then determines a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel device. And after determining the products meeting the current channel equipment, calculating the recommendation score of each product in the second product set by using the first model and the second model. The first model is obtained according to historical behavior data of the first user, and the second model is obtained according to real-time behavior data of the first user. When the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model, and the products recommended to the first user are determined according to the recommendation scores of the products.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a data processing method and apparatus.
Background
Currently, when a bank marketing system actively recommends products for a user, a recommendation list is generally formed according to two models: models based on historical behavioral data of the user, and models based on real-time behavioral data of the user. However, when recommendation is performed, since the models used are different, the recommended products may be different, and therefore, the best recommended product cannot be accurately obtained, and the recommendation effect is not good.
For this reason, a solution is urgently needed to solve this problem.
Disclosure of Invention
The technical problem to be solved by the application is to provide a data processing method to solve the problem that when a current bank marketing system actively recommends products for a user, the recommended optimal products cannot be accurately obtained due to different recommendation models, and the recommendation effect is poor.
In a first aspect, an embodiment of the present application provides a data processing method, where the method includes:
receiving user information of a first user from a channel device;
determining a first set of products matching the user information;
determining a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel equipment;
calculating a recommendation score for each product in the second set of products using the first model and the second model;
determining a product recommended to the first user according to the recommendation score of each product;
wherein:
the first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data are used for representing products which are concerned by the first user in a historical mode, the real-time behavior data are used for representing products which are concerned by the first user in a first time period including the current time, and when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model.
Optionally, the determining, according to the recommendation score of each product, a product recommended to the first user includes:
ranking the recommendation scores of the products from high to low;
and determining the preset number of products ranked at the top in the products as the products recommended to the first user.
Optionally, the first time is any time after the current time, the weight of the second model at the first time is smaller than the initial weight of the second model, and the larger the difference between the first time and the current time, the larger the difference between the initial weight of the second model and the weight of the second model at the first time.
Optionally, the first time is any time after the current time, and the weight of the first model at the first time is equal to the initial weight of the first model.
Optionally, the method further includes:
and sending the determined information of the products recommended to the first user to the channel equipment.
Optionally, the initial weights of the first model and the initial weights of the second model are configured by a user.
In a second aspect, an embodiment of the present application provides an apparatus for data processing, where the apparatus includes:
a receiving module to: receiving user information of a first user from a channel device;
a first determination module to: determining a first set of products matching the user information;
a second determination module to: determining a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel equipment;
a calculation module to: calculating a recommendation score for each product in the second set of products using the first model and the second model;
a third determination module to: determining a product recommended to the first user according to the recommendation score of each product;
wherein:
the first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data are used for representing products which are concerned by the first user in a historical mode, the real-time behavior data are used for representing products which are concerned by the first user in a first time period including the current time, and when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model.
Optionally, the third determining module is configured to:
ranking the recommendation scores of the products from high to low;
and determining the preset number of products ranked at the top in the products as the products recommended to the first user.
Optionally, the first time is any time after the current time, the weight of the second model at the first time is smaller than the initial weight of the second model, and the larger the difference between the first time and the current time, the larger the difference between the initial weight of the second model and the weight of the second model at the first time.
Optionally, the first time is any time after the current time, and the weight of the first model at the first time is equal to the initial weight of the first model.
Optionally, the apparatus further includes a sending module, configured to: and sending the determined information of the products recommended to the first user to the channel equipment.
Optionally, the initial weights of the first model and the initial weights of the second model are configured by a user.
Compared with the prior art, the embodiment of the application has the following advantages:
the embodiment of the application provides a data processing method, and a server firstly determines a first product set matched with user information after receiving the user information of a first user from a channel device. After the first product set is determined, in order to determine products meeting current channel equipment in the first product set, a second product set is determined from the first product set, wherein the second product set comprises products which are marketed in channels corresponding to the channel equipment. After the products meeting the current channel equipment are determined, in order to comprehensively utilize a model based on the historical behavior data of the user and a model based on the real-time behavior data of the user, the optimal product recommended for the current user is accurately obtained, and the recommendation score of each product in the second product set is calculated by utilizing the first model and the second model. The first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data is used for representing products which are concerned by the first user in a historical mode, and the real-time behavior data is used for representing products which are concerned by the first user in a first time period including the current time. Considering that the products concerned by the user in real time can influence the purchase selection of the current user more than the products concerned by the user in history, when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model, so that the contribution degree of the second model to the recommendation scores is larger, and the products concerned by the user currently are more accurate. And after the recommendation score of each product in the second product set is calculated, determining the product recommended to the first user according to the recommendation score of each product. By adopting the scheme, when the bank marketing system actively recommends products for the user, the model based on the historical behavior data of the user and the model based on the real-time behavior data of the user can be comprehensively utilized, the optimal product recommended for the current user can be accurately obtained, and the recommendation success rate is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart illustrating a data processing method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, 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 only a part of the embodiments of the present application, and not all of the embodiments. 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.
The inventor of the present application finds, through research, that currently, when a bank marketing system actively recommends a product for a user, a recommendation list is generally formed according to two models: models based on historical behavioral data of the user, and models based on real-time behavioral data of the user. However, when recommendation is performed, since the models used are different, the recommended products may be different, and therefore, the best recommended product cannot be accurately obtained, and the recommendation effect is not good.
In order to solve the above problem, in the embodiment of the present application, after receiving user information of a first user from a channel device, a server first determines a first product set matching the user information. After the first product set is determined, in order to determine products meeting the current channel equipment in the first product set, a second product set is determined from the first product set, wherein the second product set comprises products which are marketed in a channel corresponding to the channel equipment. In order to comprehensively utilize a model based on user historical behavior data and a model based on user real-time behavior data to accurately obtain the optimal product recommended for the current user, after determining the products meeting the current channel equipment, the recommendation scores of all products in the second product set are calculated by utilizing the first model and the second model. The first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data is used for representing products which are concerned by the first user in a historical mode, and the real-time behavior data is used for representing products which are concerned by the first user in a first time period including the current time. Considering that the products concerned by the user in real time can influence the purchase selection of the current user more than the products concerned by the user in history, when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model, so that the contribution degree of the second model to the recommendation scores is larger, and the products concerned by the user currently are more accurate. And after the recommendation score of each product in the second product set is calculated, determining the product recommended to the first user according to the recommendation score of each product. By adopting the scheme, when the bank marketing system actively recommends products for the user, the model based on the historical behavior data of the user and the model based on the real-time behavior data of the user can be comprehensively utilized, the optimal product recommended for the current user can be accurately obtained, and the recommendation success rate is improved.
Various non-limiting embodiments of the present application are described in detail below with reference to the accompanying drawings.
Exemplary method
Referring to fig. 1, a schematic flow chart of a data processing method in an embodiment of the present application is shown. The method illustrated in FIG. 1, in one implementation, may be performed by a device, such as a server, running an intelligent product marketing system.
In the present embodiment, the method shown in FIG. 1 can be implemented, for example, by the following steps S101-S105.
S101: user information of a first user is received from a channel device.
In this embodiment, the channel device may be, for example, a device for handling various banking services, such as an internet bank, a mobile banking machine, an automatic teller machine, a queuing machine, a self-service terminal, a super counter, and the like. When the user transacts business on the channel equipment, the channel equipment can actively recommend products to the user. The first user refers to a user currently transacting business on the channel equipment, and the user information may be, for example, a user number or a user mobile phone number of the user in a bank system.
S102: a first set of products that match the user information is determined.
In this embodiment, after receiving the user information of the first user from the channel device, in order to recommend a bank product to the first user, a first product set matching the user information may be determined first. When matching is carried out, firstly, a user information list of each product stored in a bank system is inquired, then, user information in the user information list of each product is compared with user information of the first user, if the user information of the first user exists in the user information list of the product, the product is matched with the user information of the first user, and the first product set comprises products matched with the first user. The user information list of the product includes user information indicating the purchase intention of the product. After a user purchases, collects or browses a certain type of product, for example, user information of the current user is recorded in a user information list of the type of product. For example, when a user collects a financial product, the user information of the user is recorded in the user information list of the financial product. After comparing the user information in the user information list of each product with the user information of the first user, the obtained first product set comprises the product information of which the first user expresses the purchasing intention. The first product set comprises products marketed in channels corresponding to the channel devices.
S103: and determining a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel equipment.
It is understood that the first product set contains product information that the first user has shown an intention to purchase, but these products may not be products that are supported for sale by the channel device in which the current user is located. For example, the first product set includes financial products, but when the channel device, that is, a device currently transacting business by the first user, is an automatic teller machine, for example, because the financial products cannot be purchased at the automatic teller machine, the recommendation of the financial products to the first user cannot realize user purchase. Therefore, in order to obtain the best product recommended for the current user and improve the recommendation success rate, a set of products which can be marketed in the channel corresponding to the channel equipment in the first product set, that is, a second product set, may be determined.
S104: and calculating the recommendation score of each product in the second product set by using the first model and the second model.
After determining products which can be marketed in a channel corresponding to the channel equipment from the first product set, in order to comprehensively utilize historical behavior data and real-time behavior data of a user to recommend the products to the customer, recommendation scores of each product in the second product set can be calculated by utilizing a first model and a second model. The first model is obtained according to historical behavior data of the first user, and the second model is obtained according to real-time behavior data of the first user. The historical behavior data can be used for representing products which are concerned by the first user in history, and the products which are concerned by the first user in history can be products purchased, collected and browsed by the first user; the historical products may be predicted based on customer information, for example, where the customer information may include one or more of basic information such as age, occupation, academic history, marital status, financial asset information such as deposits and loans, and transaction information. The real-time behavior data is used for representing products concerned by the first user in a first time period including a current time, the current time is the time when the channel device sends the user information to the server, and the first time period is a period of time including the current time, and may be 10 seconds, for example.
When calculating the recommendation score of each product in the second product set by using a first model and a second model, in a possible implementation manner, first, an initial weight of the first model and an initial weight of the second model are configured, where the initial weight of the first model is used to represent a degree of contribution of the first model, which is obtained based on historical behavior data analysis, to the recommendation score at the current time; the initial weight of the second model is used for representing the contribution degree of the second model to the recommendation score at the current moment based on real-time behavior data analysis. The greater the weight of the model, the greater the degree of contribution of the model to the recommendation score.
The initial weight may be configured by a user before the current time, and the configured user may be a bank worker, for example, and the configuration may be performed at the channel device or the marketer device. In a possible implementation manner, bank staff may pre-configure the initial weight of the first model and the initial weight of the second model for each product at each channel device or marketer device end, and when the first user handles corresponding business at the channel device, the bank staff may also adjust the initial weights in real time.
It can be understood that, although both the products of the user's historical interest and the products of the user's real-time interest affect the purchasing behavior of the user at the current moment, the products of the user's real-time interest are more likely to affect the purchasing choices of the current user than the products of the user's historical interest, and the user is more likely to purchase the products recommended by the server on the channel device according to the real-time behavior, so that the initial weight of the first model is lower than the initial weight of the second model when calculating the recommended score of each product.
For example, the second product set includes product A and product B, wherein the first model has an initial weight of 1/3 and the second model has an initial weight of 2/3. Assuming that the calculation score of the first model of the product A to the product A at the current moment is 50 minutes, and the calculation score of the second model of the product A to the product A at the current moment is 0 minute; and the calculation score of the first model of the product B to the product B at the current moment is 0 score, and the calculation score of the second model of the product B to the product A at the current moment is 50 scores. The overall score of product a is 50 × 1/3+0 × 2/3 ═ 50/3; product B scored 0 × 1/3+50 × 2/3 ═ 100/3 overall.
S105: and determining the products recommended to the first user according to the recommendation scores of the products.
In a possible implementation manner, after obtaining the recommendation score of each product, the recommendation scores of the products are ranked from high to low, and after the ranking, a preset number of products ranked in the front of the products are determined as the products recommended to the first user. The preset number is the number of the recommended products of the channel equipment, which is preset by bank staff.
And after determining the product recommended to the first user, sending the determined information of the product recommended to the first user to the channel equipment. The information of the product may be, for example, one or more of a name of the product, a purchase link, a promotional picture, a saleable date, and a predicted profitability.
In one embodiment, in order to accurately reflect the attention degree of the user to the recommended product and obtain a better recommendation effect, when the product is accurately recommended by using the first model and the second model, the weights of the first model and the second model may be changed at a time after the current time, so that the purchase intention of the user can be accurately reflected by the recommendation scores obtained by using the first model and the second model. It can be understood that, since the first model is obtained according to the historical behavior data of the first user, the historical behavior data that the user shows which product is interested in does not change greatly within a certain time, so that the contribution degree of the first model to the recommendation score does not change, the attention condition of the first user to the product can be accurately reflected, and the server can perform accurate recommendation according to the recommendation score. In view of this, in the embodiments of the present application, the weight of the first model may remain unchanged. Defining any time after the current time as a first time, wherein the weight of the first model at the first time is equal to the initial weight of the first model;
since the second model is obtained according to the real-time behavior data of the first user, the attention of the user to the current product is likely to be gradually reduced along with the lapse of time, the product which the user is interested in at the current moment may lose interest of the user after a certain time, and if the product is still recommended to the user at the moment, the recommendation effect may not be good. Therefore, when the recommendation score is calculated, the contribution degree of the second model to the recommendation score is gradually reduced along with time, the attention condition of the first user to the product can be accurately reflected, and the server can be facilitated to accurately recommend according to the recommendation score. In view of this, in the embodiment of the present application, the weight of the second model may gradually decrease with time. The weight of the second model at the first time is smaller than the initial weight of the second model, and the larger the difference between the first time and the current time is, the larger the difference between the initial weight of the second model and the weight of the second model at the first time is.
And calculating the recommendation score of each product in the second product set by using the weight of the first model and the weight of the second model after obtaining the weight of the first model and the weight of the second model at any time after the current time. When calculating the recommendation score of each product in the second product set at any time after the current time, the method is the same as the method for calculating the recommendation score at the current time except that the weight of the second model is gradually reduced along with the time, and details are not repeated here.
It can be understood that, since the weight of the second model is gradually reduced with the passage of time, the recommendation score calculated by using the first model and the second model of the same product is changed at different time, and the server can recommend the product to the user according to the score of the product at different time. For example, according to the analysis of the historical behavior data of the user, the user is interested in insurance products, when the user browses financial products, the server collects the user information of the user into a financial product set after acquiring the behavior data, when the user transacts business in a certain channel device, if the recommendation score of a financial product is high, the server recommends the product to the client, if the client does not browse, purchase or collect the financial products within a later period of time, the server does not recommend the financial products to the client, but recommends the insurance products to the user according to the historical behavior data.
Exemplary device
Based on the method provided by the above embodiment, the embodiment of the present application further provides an apparatus, which is described below with reference to the accompanying drawings.
Referring to fig. 2, a schematic structural diagram of a data processing apparatus in an embodiment of the present application is shown. The apparatus may specifically include, for example:
the receiving module 201: the channel equipment is used for receiving user information of a first user from the channel equipment;
the first determination module 202: a first set of products for determining matches to the user information;
the second determination module 203: the system comprises a channel device, a first product set and a second product set, wherein the channel device is used for receiving a first product set and a second product set;
the calculation module 204: a recommendation score for each product in the second set of products is calculated using the first model and the second model;
the third determination module 205: the system comprises a first user, a second user and a server, wherein the first user is used for recommending products to the first user;
wherein:
the first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data are used for representing products which are concerned by the first user in a historical mode, the real-time behavior data are used for representing products which are concerned by the first user in a first time period including the current time, and when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model.
By the aid of the device, when a bank marketing system actively recommends products for users, the model based on historical behavior data of the users and the model based on real-time behavior data of the users can be comprehensively utilized, the best products recommended for the current users can be accurately obtained, and the recommendation success rate is improved.
In one implementation, the third module is configured to:
ranking the recommendation scores of the products from high to low;
and determining the preset number of products ranked at the top in the products as the products recommended to the first user.
In one implementation, the first time is any time after the current time, the weight of the second model at the first time is smaller than the initial weight of the second model, and the larger the difference between the first time and the current time, the larger the difference between the initial weight of the second model and the weight of the second model at the first time.
In one implementation, the first time is any time after the current time, and the weight of the first model at the first time is equal to the initial weight of the first model.
In one implementation, the apparatus further includes a sending module configured to: and sending the determined information of the products recommended to the first user to the channel equipment.
In one implementation, the initial weights of the first model and the initial weights of the second model are configured by a user.
Since the apparatus 200 is an apparatus corresponding to the method provided in the above method embodiment, and the specific implementation of each unit of the apparatus 200 is the same as that of the above method embodiment, for the specific implementation of each unit of the apparatus 200, reference may be made to the description part of the above method embodiment, and details are not repeated here.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice in the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the attached claims
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (12)
1. A method of data processing, the method comprising:
receiving user information of a first user from a channel device;
determining a first set of products matching the user information;
determining a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel equipment;
calculating a recommendation score for each product in the second set of products using the first model and the second model;
determining a product recommended to the first user according to the recommendation score of each product;
wherein:
the first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data are used for representing products which are concerned by the first user in a historical mode, the real-time behavior data are used for representing products which are concerned by the first user in a first time period including the current time, and when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model.
2. The method of claim 1, wherein determining the products recommended to the first user based on the recommendation scores for the respective products comprises:
ranking the recommendation scores of the products from high to low;
and determining the preset number of products ranked at the top in the products as the products recommended to the first user.
3. The method of claim 1, wherein a first time is any time after the current time, the weight of the second model at the first time is less than the initial weight of the second model, and the larger the difference between the first time and the current time, the larger the difference between the initial weight of the second model and the weight of the second model at the first time.
4. The method of claim 1, wherein a first time is any time after the current time, and wherein the weight of the first model at the first time is equal to the initial weight of the first model.
5. The method of claim 1, further comprising:
and sending the determined information of the products recommended to the first user to the channel equipment.
6. The method of claim 1, wherein the initial weights of the first model and the initial weights of the second model are configured by a user.
7. A data processing apparatus, characterized in that the apparatus comprises:
a receiving module to: receiving user information of a first user from a channel device;
a first determination module to: determining a first set of products matching the user information;
a second determination module to: determining a second product set from the first product set, wherein the second product set comprises products marketed in a channel corresponding to the channel equipment;
a calculation module to: calculating a recommendation score for each product in the second set of products using the first model and the second model;
a third determination module to: determining a product recommended to the first user according to the recommendation score of each product;
wherein:
the first model is obtained according to historical behavior data of the first user, the second model is obtained according to real-time behavior data of the first user, the historical behavior data are used for representing products which are concerned by the first user in a historical mode, the real-time behavior data are used for representing products which are concerned by the first user in a first time period including the current time, and when the recommendation scores of the products are calculated, the initial weight of the first model is lower than that of the second model.
8. The apparatus of claim 7, wherein the third determining module is configured to:
ranking the recommendation scores of the products from high to low;
and determining the preset number of products ranked at the top in the products as the products recommended to the first user.
9. The apparatus of claim 7, wherein a first time is any time after the current time, the weight of the second model at the first time is less than the initial weight of the second model, and the larger the difference between the first time and the current time, the larger the difference between the initial weight of the second model and the weight of the second model at the first time.
10. The apparatus of claim 7, wherein a first time is any time after the current time, and wherein the weight of the first model at the first time is equal to the initial weight of the first model.
11. The apparatus of claim 7, further comprising a sending module configured to: and sending the determined information of the products recommended to the first user to the channel equipment.
12. The apparatus of claim 7, wherein the initial weights of the first model and the initial weights of the second model are configured by a user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011320803.7A CN112288569A (en) | 2020-11-23 | 2020-11-23 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011320803.7A CN112288569A (en) | 2020-11-23 | 2020-11-23 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112288569A true CN112288569A (en) | 2021-01-29 |
Family
ID=74425792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011320803.7A Pending CN112288569A (en) | 2020-11-23 | 2020-11-23 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288569A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113946752A (en) * | 2021-10-28 | 2022-01-18 | 平安银行股份有限公司 | Financial product recommendation method, device, equipment and storage medium based on big data |
| CN115374370A (en) * | 2022-10-26 | 2022-11-22 | 小米汽车科技有限公司 | Content pushing method and device based on multiple models and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060212359A1 (en) * | 2002-05-23 | 2006-09-21 | Hudgeon Douglas R | System and method for selecting a service provider |
| CN104835066A (en) * | 2015-05-25 | 2015-08-12 | 北京京东尚科信息技术有限公司 | Embarking channel selection method and system |
| CN109413461A (en) * | 2018-09-30 | 2019-03-01 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
| CN110490683A (en) * | 2018-05-15 | 2019-11-22 | 中国移动通信集团浙江有限公司 | A kind of method and system of the offline upper collaboration multi-model mixed recommendation of line |
| CN110766497A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Trading method, platform, system and computer readable storage medium |
-
2020
- 2020-11-23 CN CN202011320803.7A patent/CN112288569A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060212359A1 (en) * | 2002-05-23 | 2006-09-21 | Hudgeon Douglas R | System and method for selecting a service provider |
| CN104835066A (en) * | 2015-05-25 | 2015-08-12 | 北京京东尚科信息技术有限公司 | Embarking channel selection method and system |
| CN110490683A (en) * | 2018-05-15 | 2019-11-22 | 中国移动通信集团浙江有限公司 | A kind of method and system of the offline upper collaboration multi-model mixed recommendation of line |
| CN110766497A (en) * | 2018-07-27 | 2020-02-07 | 北京京东尚科信息技术有限公司 | Trading method, platform, system and computer readable storage medium |
| CN109413461A (en) * | 2018-09-30 | 2019-03-01 | 武汉斗鱼网络科技有限公司 | A kind of recommended method and relevant device of direct broadcasting room |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113946752A (en) * | 2021-10-28 | 2022-01-18 | 平安银行股份有限公司 | Financial product recommendation method, device, equipment and storage medium based on big data |
| CN115374370A (en) * | 2022-10-26 | 2022-11-22 | 小米汽车科技有限公司 | Content pushing method and device based on multiple models and electronic equipment |
| CN115374370B (en) * | 2022-10-26 | 2023-04-07 | 小米汽车科技有限公司 | Content pushing method and device based on multiple models and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11395026B2 (en) | Systems and methods for web spike attribution | |
| US11195191B2 (en) | Method of generating a prioritized listing of customers using a purchase behavior prediction score | |
| US20180101852A1 (en) | Risk assessment rule set application for fraud prevention | |
| US8620746B2 (en) | Scoring quality of traffic to network sites | |
| US20170124628A1 (en) | Hybrid recommendation system | |
| US9846884B2 (en) | Click conversion score | |
| KR101794221B1 (en) | System and method for providing calculation of online sellers | |
| US20110035273A1 (en) | Profile recommendations for advertisement campaign performance improvement | |
| US20110082718A1 (en) | Analyzing Patterns within Transaction Data | |
| US20090307028A1 (en) | A method and a system for identifying potentially fraudulent customers in relation to electronic customer action based systems, and a computer program for performing said method | |
| US20070143172A1 (en) | System and method for predicting card member spending using collaborative filtering | |
| US20090106081A1 (en) | Internet advertising using product conversion data | |
| CN107798607A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
| CN112288569A (en) | Data processing method and device | |
| KR102334404B1 (en) | Merchandise recommendation server and control method thereof | |
| US20110191166A1 (en) | Leveraging of Financial Transaction Data | |
| JP6679648B2 (en) | Information processing device, information processing method, information processing program, determination device, determination method, and determination program | |
| US20090192878A1 (en) | Method and apparatus for utilizing shopping survey data | |
| KR101801761B1 (en) | System and method for offering vehicle purchase information | |
| JP6962839B2 (en) | Information processing equipment, information processing methods, and programs | |
| KR102576123B1 (en) | Product marketing linkage system and method | |
| KR20010111913A (en) | Complex filtering apparatus and method for database marketing in electronic commerce | |
| CN113657894A (en) | Foreign exchange quotation processing method and device and electronic equipment | |
| US12033171B2 (en) | System for improving distributed network data flow efficiency by generating interaction leads | |
| KR20020012748A (en) | Apparatus For Analysis Of Information And Method For Analysis Of Information Using It in electronic commerce |
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 |