CN111192108A

CN111192108A - Sorting method and device for product recommendation and electronic equipment

Info

Publication number: CN111192108A
Application number: CN201911290083.1A
Authority: CN
Inventors: 杨博闻; 王安滨; 常富洋
Original assignee: Beijing Qilu Information Technology Co Ltd
Current assignee: Beijing Qilu Information Technology Co Ltd
Priority date: 2019-12-16
Filing date: 2019-12-16
Publication date: 2020-05-22

Abstract

The invention provides a sorting method and device for product recommendation, electronic equipment and a computer readable medium. The method comprises the steps of obtaining training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of products recommended by the historical users and information of whether the recommended products are converted by the users; establishing a ranking model, and training the ranking model by using the training data; acquiring characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products respectively, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product; and sequencing the target products based on the conversion probability of the target products. The invention can provide more effective and optimized recommended product sequencing aiming at different users, and increases the conversion probability of each target product and the benefit of a display platform.

Description

Sorting method and device for product recommendation and electronic equipment

Technical Field

The invention relates to the field of computer information processing, in particular to a sorting method and device for product recommendation, electronic equipment and a computer readable medium.

Background

With the development of network technology, websites become more effective publicizing platforms, and many enterprises or companies utilize websites to publicize their own products for customers to browse, thereby achieving the desired publicizing effect. For example, in bid-ranked advertisements (PPCs), a landing page (a guide page) is a web page that is displayed to a potential user when the user clicks on an advertisement or searches with a search engine. Landing pages may weigh the effectiveness of different advertisements through different customizations.

Three key factors of website operation are capturing (enabling people to visit your website or landing page), converting (persuading them to perform operations that you expect, here, clicking, registering or directly purchasing), keeping (deepening the relationship with customers and improving their life value) and achieving high conversion rate, and landing pages are very important.

Currently, many sequencing algorithms include, for example, fitting and measuring various factors of commodity performance by logistic regression (logistic regression), adjusting factor weights by a machine learning method according to user feedback, selecting a preferred sequencing rule according to a business target by using a Multi-arm bandit (Multi-arm slot machine), and the like. Most of the traditional methods concern the characteristics of the commodity dimension or one-time interaction behavior of the user on the commodity.

In the related art, sorting is performed according to the sorting eigenvalue of each business object, and the sorting eigenvalue is obtained by the browsing amount and the conversion amount, and respective weight values are set for the browsing amount and the conversion amount. The method is used for calculating and sequencing so as to facilitate the user to locate the required products or improve the probability that the sequencing result can be accepted by the user. Although the above method produces some considerable effect in practical application by performing sorting through calculation, there is still much room for improvement in effective sorting and conversion yield.

Therefore, there is a need to provide a more efficient sorting method.

Disclosure of Invention

In order to solve the above problem, the present invention provides a ranking method for product recommendation, wherein the ranking method includes: acquiring training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of recommended products of the historical users and information of whether the recommended products are converted by the users; establishing a ranking model, and training the ranking model by using the training data; acquiring characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products respectively, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product; and sequencing the target products based on the conversion probability of the target products.

Preferably, the sorting the target products based on the conversion probability of each target product includes: calculating a ranking coefficient and ranking each target product according to the ranking coefficient, wherein the ranking coefficient comprises at least one ranking factor, and the ranking factor comprises the conversion probability.

Preferably, the ranking factor further comprises at least one of: the price of the target product, and the benefit of the target product being converted.

Preferably, the product characteristic information of the training data and the product characteristic information of the target product each include at least one of: the amount, duration, price, income of the product.

Preferably, the transformation comprises at least one of: the recommended product is converted into a registered, trusted and movable product.

Preferably, the feature information of the historical user and the feature information of the target user of the training data each include at least one of the following: long term preference profile, short term preference profile.

Preferably, the long term preference profile and the short term preference profile each include at least one of an average amount and an average interest rate of all products clicked by the user within the first predetermined time.

Preferably, the short-term preference feature data each include at least one of an average amount and an average interest rate of all products clicked by the user within the second predetermined time.

In addition, the invention also provides a sorting device for recommending products, which comprises: the data acquisition module is used for acquiring training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of products recommended by the historical users and information about whether the recommended products are converted by the users; a training module for establishing a ranking model and training the ranking model using the training data; the data processing module is used for acquiring the characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products respectively, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product; and the sequencing module is used for sequencing the target products based on the conversion probability of the target products.

Preferably, the sorting module further includes a calculating module, the calculating module is configured to calculate a sorting coefficient, and sort each target product according to the sorting coefficient, where the sorting coefficient includes at least one sorting factor, and the sorting factor includes the conversion probability.

Preferably, the long term preference profile and the short term preference profile each include at least one of an average amount and an average interest rate of all products clicked by the user within a predetermined time.

In addition, the present invention also provides an electronic device, wherein the electronic device includes: a processor; and a memory storing computer-executable instructions that, when executed, cause the processor to perform the ranking method for product recommendations according to the present invention.

Furthermore, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs which, when executed by a processor, implement the ranking method for product recommendation of the present invention.

Advantageous effects

Compared with the prior art, the sorting method can provide more effective and optimized recommended product sorting aiming at different users; the conversion probability of each target product and the income of a display platform are increased.

Drawings

In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects obtained more clear, the following will describe in detail the embodiments of the present invention with reference to the accompanying drawings. It should be noted, however, that the drawings described below are only illustrations of exemplary embodiments of the invention, from which other embodiments can be derived by those skilled in the art without inventive faculty.

FIG. 1 is a method flow diagram of one example of a ranking method for product recommendations of the present invention.

Fig. 2 is a schematic block diagram showing a loan supermarket to which the sorting method of the present invention is applied.

FIG. 3 is a method flow diagram of another example of a ranking method for product recommendations of the present invention.

Fig. 4 is a schematic block diagram of an example of the ranking device for product recommendation of the present invention.

Fig. 5 is a schematic block diagram of another example of the ranking device for product recommendation of the present invention.

Fig. 6 is a block diagram of an exemplary embodiment of an electronic device according to the present invention.

Fig. 7 is a block diagram of an exemplary embodiment of a computer-readable medium according to the present invention.

Detailed Description

Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.

Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.

In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, or sections, these terms should not be construed as limiting. These phrases are used to distinguish one from another. For example, a first device may also be referred to as a second device without departing from the spirit of the present invention.

The term "and/or" and/or "includes any and all combinations of one or more of the associated listed items.

Example 1

Hereinafter, a sorting method and apparatus for product recommendation of the present invention will be described with reference to fig. 1 to 3.

FIG. 1 illustrates a method flow diagram of one example of a ranking method for product recommendations of the present invention. As shown in fig. 1, the sorting method of the present invention includes:

step S101, obtaining training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of products recommended by the historical users and information of whether the recommended products are converted by the users.

Step S102, establishing a sequencing model, and training the sequencing model by using the training data.

Step S103, acquiring characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product.

And S104, sequencing the target products based on the conversion probability of the target products.

In order to more clearly illustrate the sorting method of the present invention, the sorting of loan products will be specifically described as an example.

Fig. 2 is a schematic block diagram showing a loan supermarket to which the sorting method of the present invention is applied. As shown in fig. 2, a supermarket for loan is used as a display platform for products, where the upstream side is a user side and the downstream side is a product side. Some products on the downstream side are shown on the landing page of the supermarket for loan and are arranged on the page in a certain order. However, product ordering on landing pages is crucial to website operations whether effective conversion (customer registration or movement, etc.) can be achieved. The inventors of the present invention improved the sorting method as follows.

First, step S101 is described. In step S101, training data is acquired, where the training data includes feature information of a plurality of historical users, product feature information of products recommended by the historical users, and information on whether the recommended products are converted by the users.

Specifically, the feature data of the historical user includes, for example, basic feature data and behavior feature data of the user.

In the present embodiment, the basic feature data includes, for example, age, sex, occupation, and the like.

Preferably, the behaviour signature comprises at least one of long term preference signature and short term preference signature.

In addition, the behavior feature data also includes monthly income/annual income, loan information, payment information, overdue information, the number of uses of the product, and the like.

Further, the long term preference profile includes at least one of an average amount and an average interest rate of all products clicked by the user within a first predetermined time, wherein the first predetermined time is, for example, three months, six months, nine months, and the like.

Likewise, the short term preference profile includes at least one of an average amount, an average interest rate of all products clicked on by the user within a second predetermined time, such as 3 days, 5 days, 7 days, 15 days, 20 days, 30 days, and the like.

In this embodiment, the product is a loan product. Further, the characteristic information of the product includes, for example, at least one of an amount, a term, and a price (loan rate) of the product. And, preferably, the product characteristic information of the present invention further includes the revenue obtained from the product by the ranking platform. For example, the benefit refers to a fee that the platform charges from the provider of the target product after the user is converted.

In addition, the training data also includes information whether the recommended product is converted by the user, wherein the conversion includes user registration information, credit information, dynamic information and the like. Specifically, the customer is recommended some products on the landing page of the loan supermarket, and for the recommended products, the user registers, gives credit or moves information.

Next, step S102 will be described. In step S102, a ranking model is established, and the ranking model is trained using the training data.

In the present embodiment, the ranking model is, for example, an FM algorithm model, a bilinear FFM, a DeepFFM model, a logistic regression, a gradient boosting tree (GBDT), or other algorithm models. The foregoing examples are provided for the purpose of illustration only and are not to be construed as limiting the present invention.

Regarding the sorting model of the loan supermarket, the input characteristics of the sorting model are the user characteristic information and the product characteristic information of the target user, namely one user and one product. The output characteristics are the conversion probability of the user for the target product (i.e., the probability that the target user registers, grants, moves, etc. after generating interest in each target product).

In this embodiment, the product characteristics mainly refer to characteristics derived from characteristics of the product and threshold requirements. It should be noted that a user may correspond to multiple target products, and therefore, there may be multiple inputs, i.e., one output value for each product.

It should be noted that the above conversion probability has different meanings for different settlement methods. For example, the probability of user registration is calculated for the channel of registration settlement, and the probability of credit granting is calculated for the channel of credit settlement. Therefore, the above description is only given as a preferred example, and is not to be construed as limiting the present invention.

In addition, training the ranking model using the training data further comprises defining good and bad samples. As a specific example, a "whether the recommended product is converted by the user" may be used to define a good-bad sample, i.e., a label value of "whether the recommended product is converted by the user" is specified as 0 or 1, where 1 indicates that the recommended product is converted by the user and 0 indicates that the recommended product is not converted by the user.

For each target user, the conversion probability of each target product output by the ranking model is typically a numerical value between 0 and 1. The closer to 1, the more likely the target user is to convert relative to the recommended product.

It is noted that the above transformation includes at least one of the following: the recommended product is converted into a registered, trusted and movable product.

Next, step S103 will be described. In step S103, feature information of the target user is acquired, and user feature data is extracted.

In this embodiment, the user characteristic information further includes a user behavior characteristic. The feature data can be extracted from different behaviors of the user by analyzing and deriving the clicking behaviors of the user in, for example, a loan supermarket and dividing the clicking behaviors into long-term preference features (long-term interest) and short-term preference features (short-term interest) according to time. For example, some users prefer to browse a product many times, some users prefer not to continue browsing if they encounter a suitable one, some users prefer a well-known organization, and so on, and feature data is extracted based on these user behaviors.

Thus, the feature data of the target user includes at least one of the base feature data and the behavior feature data.

Preferably, the behavioral characteristic data of the target user includes at least one of long-term preference characteristic data and short-term preference characteristic data.

If the training data includes the long-term preference feature data and the short-term preference feature data of the historical user, the ranking model obtained by the training supports the input of the long-term preference feature data and the short-term preference feature data of the target client. The specific meanings of the long-term preference profile and the short-term preference profile of the target user and the historical user are consistent, and thus the specific descriptions of the long-term preference profile and the short-term preference profile of the target user are omitted.

In other embodiments, the behavioral characteristic data further includes monthly income/annual income, loan information, payment information, overdue information, number of uses of the product, and the like. The foregoing is illustrative only and is not to be construed as limiting the invention.

Further, the characteristic information of the target user is respectively combined with the product characteristic information of each target product in a plurality of target products, and the product characteristic information is input into the sequencing model so as to calculate the conversion probability of each target product.

Next, step S104 will be described. Step S104 is a step of sorting based on the above-described conversion probability.

In order to further improve the sequencing accuracy and improve the probability of the profit brought by the product to the loan supermarket, the technical effect is realized by improving the calculation of the output value of the sequencing, which is specifically as follows.

In step S104, the target products are ranked based on the conversion probability of each target product. Specifically, a ranking coefficient is calculated and each target product is ranked according to the ranking coefficient, the ranking coefficient comprises at least one ranking factor, and the ranking factor comprises the conversion probability.

In this embodiment, the ranking factor further includes at least one of: the price of the target product, and the benefit of the target product being converted.

The ranking factor of the target product is the sum of the products of each ranking factor and the corresponding factor, and is specifically expressed as follows.

β a conversion probability of target product + b revenue of target product converted, wherein

β refers to the ranking coefficient of the target product, a refers to the weighting factor corresponding to the conversion rate of the target product, and b refers to the weighting factor corresponding to the benefit of the target product being converted.

Therefore, by the above calculation, the ranking coefficient of each target product can be calculated. And calculating the sorting coefficient of the target product of different customers, and sorting the products based on the sorting coefficient. Therefore, more effective product recommendation sequencing is provided, and product sequencing is optimized.

In this embodiment, the target product is a loan product. The converted benefit of the target product refers to the benefit which can be brought to the display platform by the target product on the display platform, in other words, the benefit obtained by the display platform due to diversion is not the benefit of the product. The price of the target product refers to the loan interest rate, the loan amount and the like.

Although in the present embodiment, the ranking factor and the ranking coefficient are both two, the number of ranking factors and ranking coefficients is not limited thereto, and may be increased. In other embodiments, these ranking factors and ranking coefficients described above may also be used in model training and to adjust parameters.

In addition, in other embodiments, the above steps may be further split into two steps, for example, step S102 may be split into step S102 and step S201, see fig. 3 specifically.

Compared with the prior art, the sorting method can provide more effective and optimized recommended product sorting aiming at different users. For example, for customers with short-term interests, products that match the short-term interests may be ranked ahead. In addition, the sequencing method increases the conversion probability of each target product and the income of a display platform.

Those skilled in the art will appreciate that all or part of the steps to implement the above-described embodiments are implemented as programs (computer programs) executed by a computer data processing apparatus. When the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium is not limited to centralized storage, but may be distributed storage, such as cloud storage based on cloud computing.

Embodiments of a data warehouse building apparatus of the present invention are described below, which may be used to perform method embodiments of the present invention. The details described in the device embodiments of the invention should be regarded as complementary to the above-described method embodiments; reference is made to the above-described method embodiments for details not disclosed in the apparatus embodiments of the invention.

Example 2

Referring to fig. 4 and 5, the present invention also provides a sorting apparatus 400 for product recommendation, comprising: the data acquisition module 401 is configured to acquire training data, where the training data includes feature information of a plurality of historical users, product feature information of products recommended by the historical users, and information of whether the recommended products are converted by the users; a training module 402 for establishing a ranking model, training the ranking model using the training data; the data processing module 403 is configured to obtain feature information of a target user, combine the feature information of the target user with product feature information of each of a plurality of target products, and input the combination result into the ranking model to calculate a conversion probability of each target product; and the sorting module 404 sorts the target products based on the conversion probability of the target products.

As shown in fig. 5, the sorting module further includes a calculating module 501, where the calculating module is configured to calculate a sorting coefficient, sort each target product according to the sorting coefficient, where the sorting coefficient includes at least one sorting factor, and the sorting factor includes the conversion probability.

In embodiment 2, the same portions as those in embodiment 1 are not described.

Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.

Example 3

In the following, embodiments of the electronic device of the present invention are described, which may be regarded as specific physical implementations for the above-described embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.

Fig. 6 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. An electronic apparatus 200 according to this embodiment of the present invention is described below with reference to fig. 6. The electronic device 200 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.

As shown in fig. 6, the electronic device 200 is embodied in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.

Wherein the storage unit stores program code executable by the processing unit 210 to cause the processing unit 210 to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 210 may perform the steps as shown in fig. 1.

The memory unit 220 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.

The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 230 may be one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to implement the above-described method of the invention, namely: and training the created user risk control model by using APP download sequence vector data and overdue information of the historical user as training data, and calculating the financial risk prediction value of the target user by using the created user risk control model.

As shown in fig. 7, the computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.

Claims

1. A ranking method for product recommendation, the ranking method comprising:

acquiring training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of recommended products of the historical users and information of whether the recommended products are converted by the users;

establishing a ranking model, and training the ranking model by using the training data;

acquiring characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products respectively, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product;

and sequencing the target products based on the conversion probability of the target products.

2. The ranking method according to claim 1, wherein the ranking of the target products based on the conversion probabilities of the target products comprises:

calculating a ranking coefficient and ranking each target product according to the ranking coefficient, wherein the ranking coefficient comprises at least one ranking factor, and the ranking factor comprises the conversion probability.

3. The ranking method according to claims 1-2, wherein the ranking factor further comprises at least one of: the price of the target product, and the benefit of the target product being converted.

4. The ranking method according to any one of claims 1-3, wherein the product characteristic information of the training data and the product characteristic information of the target product each comprise at least one of: the amount, duration, price, income of the product.

5. The sequencing method of any one of claims 1-4, wherein the conversion comprises at least one of: the recommended product is converted into a registered, trusted and movable product.

6. The ranking method according to any of claims 1-5, wherein the feature information of the historical users and the feature information of the target users of the training data each comprise at least one of:

long term preference profile, short term preference profile.

7. The method of claim 1-6, wherein the long term preference profile and the short term preference profile each include at least one of an average amount and an average interest rate of all products clicked by the user within the first predetermined time.

8. A ranking device for product recommendation, comprising:

the data acquisition module is used for acquiring training data, wherein the training data comprises characteristic information of a plurality of historical users, product characteristic information of products recommended by the historical users and information about whether the recommended products are converted by the users;

a training module for establishing a ranking model and training the ranking model using the training data;

the data processing module is used for acquiring the characteristic information of a target user, combining the characteristic information of the target user with the product characteristic information of each target product in a plurality of target products respectively, and inputting the characteristic information into the sequencing model to calculate the conversion probability of each target product;

and the sequencing module is used for sequencing the target products based on the conversion probability of the target products.

9. An electronic device, wherein the electronic device comprises:

a processor; and the number of the first and second groups,

memory storing computer-executable instructions that, when executed, cause the processor to perform the ranking method for product recommendation of any of claims 1-7.

10. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the ranking method for product recommendations of any of claims 1-7.