CN111814032B

CN111814032B - Cold start recommendation method and device and electronic equipment

Info

Publication number: CN111814032B
Application number: CN201910289260.8A
Authority: CN
Inventors: 苏云琳
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-04-11
Filing date: 2019-04-11
Publication date: 2024-05-28
Anticipated expiration: 2039-04-11
Also published as: CN111814032A

Abstract

The invention discloses a cold start recommending method, a cold start recommending device and electronic equipment, wherein the cold start recommending method comprises the following steps: obtaining a user characteristic value of a new user for setting user characteristics according to user data generated by the new user by using a third party application; obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics; obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product; and obtaining a product recommendation list of the new user at least according to the matching degree between the new user and each product.

Description

Cold start recommendation method and device and electronic equipment

Technical Field

The present invention relates to the field of information processing technologies, and in particular, to a cold start recommendation method, a cold start recommendation device, an electronic device, and a computer readable storage medium.

Background

With the development of science and technology, more and more people tend to read or purchase products, such as reading books, or purchasing goods, etc., through terminals.

Currently, when a user uses a terminal for reading or purchasing a product for the first time, the user is required to input a large amount of registration information into the terminal, and the terminal recommends a related product to the user according to the large amount of registration information and self equipment information. Taking the example that the user uses the terminal for reading the book for the first time, after the user starts the terminal for the first time, a corresponding table is displayed on a display interface of the terminal so as to prompt the user to input a large amount of registration information such as the gender of the user, the type of the book of interest and the like. Meanwhile, the terminal actively acquires the ip address of the self equipment, and inquires the region information of the user according to the ip address. And finally, the terminal displays books recommended to the user on a display interface according to the registration information and the region information of the user.

However, on the one hand, a user is required to input a large amount of registration information into the terminal, which results in complicated operation of the user. On the other hand, the terminal cannot obtain the characteristics of accurately reflecting the relevant information of the user according to the equipment information of the terminal, for example, the region information of the user cannot be accurately inquired according to the ip address of the terminal, and meanwhile, the user cannot necessarily input all registration information due to complicated operation, so that the terminal recommends products to the user and cannot be close to the actual demands of the user.

Disclosure of Invention

The embodiment of the invention aims to provide a new cold start recommending method for recommending products for new registered users.

According to a first aspect of the present invention, there is provided a cold start recommendation method, comprising:

Obtaining a user characteristic value of a new user for setting user characteristics according to user data generated by the new user by using a third party application;

obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics;

Obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product;

And obtaining a product recommendation list of the new user at least according to the matching degree between the new user and each product.

Optionally, the user characteristic includes at least one of a gender characteristic, an age characteristic, a region characteristic, and an academic characteristic.

Optionally, the obtaining the matching degree between the new user and each product according to the user feature value and the classification feature value of each product includes:

acquiring the preference degree of the corresponding product for each user characteristic value according to the classification characteristic value of each product;

And obtaining the matching degree between the new user and each product according to the preference degree corresponding to each product and the influence weight of each user characteristic.

Optionally, the method further includes:

And acquiring the searching heat degree of each product in a search engine so as to acquire a product recommendation list of the new user at least according to the searching heat degree.

Optionally, the method further includes:

And acquiring transaction heat degree formed by transaction payment of each product, so as to acquire a product recommendation list of the new user at least according to the transaction heat degree.

Optionally, the method further includes:

Comparing the user characteristic value of the new user with the user characteristic value of the historical new user to obtain a comparison result;

And obtaining the synergy of each product according to the comparison result and the products converted by the historical new user in the set time after registration, so as to obtain a product recommendation list of the new user at least according to the synergy, wherein the converted products belong to the product set.

Optionally, the obtaining the synergy of each product according to the comparison result and the product converted by the historical new user in the set time after registration includes:

Obtaining a product converted by the history new user in a set time after registration;

Obtaining classification characteristic values obtained by classifying each converted product in the historical new user according to the user characteristics;

And obtaining the synergy of each product according to the comparison result and the classification characteristic value of each converted product.

Optionally, after obtaining the product recommendation list of the new user, the method further includes:

Acquiring a product list actually converted by the new user;

And comparing the actually converted product list with the product recommendation list, and updating the book recommendation list according to a comparison result.

Optionally, the method further includes:

screening out products to be recommended from all the products according to set conditions to form the product set;

wherein the set condition includes at least one of a search heat in the search engine exceeding a set search heat, a transaction heat formed by transaction payment exceeding a set transaction heat, a conversion rate in a history of new users exceeding a set conversion rate.

According to a second aspect of the present invention, there is provided a cold start recommendation method, comprising:

Acquiring a classification characteristic value obtained by classifying each book in the book set according to the user characteristics;

obtaining the matching degree between the new user and each book according to the user characteristic value and the classification characteristic value of each book;

And obtaining a book recommendation list of the new user at least according to the matching degree between the new user and each book.

Optionally, the method further includes:

acquiring the searching heat of each product in a search engine;

acquiring transaction heat generated by transaction payment of each product;

Obtaining the synergy of each product according to the comparison result and the products converted by the historical new user in the set time after registration, wherein the converted products belong to the product set;

The method further obtains a product recommendation list of the new user according to the search heat, the transaction heat and the synergy of each product.

According to a third aspect of the present invention, there is provided a cold start recommendation device comprising:

the user characteristic acquisition module is used for acquiring a user characteristic value of a new user for setting user characteristics according to user data generated by the new user by using a third-party application;

The product characteristic acquisition module is used for acquiring a classification characteristic value obtained by classifying each product in the product set according to the user characteristics;

the matching module is used for obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product; and

And the recommending module is used for obtaining a product recommending list of the new user at least according to the matching degree between the new user and each product.

According to a fourth aspect of the present invention, there is provided an electronic device comprising a cold start recommendation apparatus according to the third aspect of the present invention; or the electronic device comprises a memory for storing computer instructions and a processor for calling the computer instructions from the memory and executing the cold start recommendation method according to the first or second aspect under the control of the computer instructions.

According to a fifth aspect of the present invention there is provided a computer storage medium having stored thereon computer instructions which, when executed by a processor, implement the cold start recommendation method according to the first or second aspect.

The embodiment of the invention provides a cold start recommendation method, on one hand, a product recommendation list can be obtained without inputting a large amount of registration information by a new user, and thus, related operations of inputting the registration information by the user can be avoided. On the other hand, the matching degree between the new user and each product can be obtained according to the characteristic value which is obtained by the new user through using the user data generated by the third-party application and the classifying characteristic value of the product according to the user characteristic classification, and the product recommendation list which is close to the actual requirement of the new user is obtained at least according to the matching degree between the new user and each product.

Other features of the present invention and its advantages will become apparent from the following detailed description of exemplary embodiments of the invention, which proceeds with reference to the accompanying drawings.

Drawings

In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described. It is appreciated that the following drawings depict only certain embodiments of the invention and are therefore not to be considered limiting of its scope. Other relevant drawings may be made by those of ordinary skill in the art without undue burden from these drawings.

FIG. 1 is a schematic diagram of a product providing system to which a cold start recommendation method of an embodiment of the present invention may be applied;

FIG. 2 is a schematic flow chart of a cold start recommendation method according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of a product recommendation list according to an embodiment of the present invention;

FIG. 4 is a schematic diagram showing another product recommendation list according to an embodiment of the present invention;

FIG. 5 is a flowchart illustrating another cold start recommendation method according to an embodiment of the present invention;

FIG. 6 is a flowchart illustrating another cold start recommendation method according to an embodiment of the present invention;

FIG. 7 is a flowchart of another cold start recommendation method according to an embodiment of the present invention;

fig. 8 is a schematic structural diagram of a cold start recommendation device according to an embodiment of the present invention.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.

The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of exemplary embodiments may have different values.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

< Hardware configuration >

The cold start recommendation method provided by the embodiment of the invention can be applied to a product providing system, and the product providing system can recommend products for new users according to the cold start recommendation method provided by the embodiment of the invention, so that the conversion rate of the users on the recommended products is improved, and the user experience is further improved. Fig. 1 is a schematic diagram showing a structure of a product providing system to which a cold start recommendation method according to an embodiment of the present invention can be applied.

As shown in fig. 1, such a product providing system 1000 may include a server 1100, a terminal device 1200, and a network 1300.

The server 1100 may be, for example, a blade server, a rack server, etc., and is not limited herein.

As shown in fig. 1, the server 1100 may include a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, a display device 1150, and an input device 1160.

The processor 1110 may be, for example, a central processing unit CPU or the like. The memory 1120 includes, for example, ROM (read only memory), RAM (random access memory), nonvolatile memory such as a hard disk, and the like. The interface device 1130 includes, for example, a USB interface, a serial interface, and the like. The communication device 1140 can perform wired or wireless communication, for example. The display device 1150 is, for example, a liquid crystal display. The input device 1160 may include, for example, a touch screen, a keyboard, and the like.

Although a number of devices of the server 1100 are shown in fig. 1, the server may also include only the processor 1110, the memory 1120, and the communication device 1140.

In one embodiment, the servers may be implemented as a cloud architecture, for example, by a cluster of servers deployed at the cloud.

Terminal device 1200 may be a smart phone, portable computer, desktop computer, tablet computer, wearable device, PDA, electronic reader, etc. The terminal device 1200 may be any device capable of loading a product providing application, such as a device capable of providing a service for online or offline reading of literary works, and the like, and is not limited herein.

As shown in fig. 1, the terminal apparatus 1200 may include a processor 1210, a memory 1220, an interface device 1230, a communication device 1240, a display device 1250, an input device 1260, a speaker 1270, a microphone 1280, and so forth. The processor 1210 may be a central processing unit CPU, a microprocessor MCU, or the like. The memory 1220 includes, for example, ROM (read only memory), RAM (random access memory), nonvolatile memory such as a hard disk, and the like. The interface device 1230 includes, for example, a USB interface, a headphone interface, and the like. The communication device 1240 can perform wired or wireless communication, for example. The display device 1250 is, for example, a liquid crystal display, a touch display, or the like. The input device 1260 may include, for example, a touch screen, a keyboard, and the like. A user may output/input voice information through the speaker 1270 and the microphone 1280.

The communication network 1300 may be a wireless network or a wired network, or may be a local area network or a wide area network. The terminal device 1200 may communicate with the server 1100 through the communication network 1300.

The product providing system 1000 shown in fig. 1 is merely illustrative and is in no way intended to limit the invention, its application or uses. For example, although fig. 1 shows only one server 1100 and one terminal device 1200, it is not meant to limit the respective numbers, and the product providing system 1000 to which the cold start recommendation method of the embodiment of the present invention is applied may include a plurality of servers 1100 and/or a plurality of terminal devices 1200.

The cold start recommendation method according to any embodiment of the present invention may be implemented by the server 1100 of the product providing system 1000, may be implemented by the terminal device 1200 of the product providing system 1000, or may be implemented by both the server 1100 and the terminal device 1200, which is not limited herein.

Example 1

The cold start recommendation method provided in this embodiment, as shown in fig. 2, includes the following steps S101 to S104:

s101, obtaining a user characteristic value of the new user for setting the user characteristic according to user data generated by the new user through using a third party application.

In this embodiment, the new user may be a user whose current date is within a set time period from the registered date, for example, the set time period is one month, and all users whose current date is within one month from the registered date are referred to as new users.

In this embodiment, the third party application may include: at least one of a video playing platform, a search engine, a payment platform, a navigation positioning platform and an online shopping platform.

The new user may be exemplified by user data generated by using a third party application:

When the third party application is a video playback platform, the corresponding data may include: registration information of the user, the type of video watched by the user history (e.g., comedy, love, family, city, even-young, news, documentary, etc.), the duration of video watched by the user history, the corresponding region of video watched by the user history (e.g., inland, hong Kong region, european and American country, japanese and Korean country, etc.), and the like.

When the third party application is a search engine, the corresponding data may include: registration information of the user, user history search records, and the like.

When the third party application is for a payment platform, the corresponding data may include: registration information for the user, user history bill payment, type of goods paid (e.g., restaurant, clothing, daily use chemicals, etc.), etc.

When the third party application is for a navigational positioning platform, the corresponding data may include: registration information of the user, origin of the user's history travel, destination of the user's history travel, user's history travel mode (e.g., walking, taxi, riding, driving, etc.), origin of the user's history travel, and surrounding building types of destination (office building, mall, menu, etc.), and the like.

When the third party application is an online shopping platform, the corresponding data may include: registration information of the user, historical order information of the user (order information comprises a receiving address, a commodity type, a commodity price and the like), commodity information historically browsed by the user and the like.

Illustratively, the user characteristics may include: at least one of gender, age, region, and academic features.

The characteristic values of the sex characteristics are: either male or female. The feature values of the age feature may be classified according to age groups, for example, as: under 20 years old, 20 to 35 years old, 35 to 50 years old, over 50 years old, etc. The feature values of the regional features can be divided into provinces, cities, etc., for example, the regional features are divided into: beijing, shanghai, guangzhou, shaanxi province, jiangsu province, ningxia, taiwan province, and the like. The feature values of the academic features can be divided into: the junior middle school and the following, the senior middle school, the university and the research student, etc.

The feature values of the user features may be further quantized. For example, the feature values of the gender feature are quantized to 0 and 1, where 0 represents a male and 1 represents a female.

In addition, the user features may further include type features of the type of interest, and feature values of the type features of the type of interest may be: comedy, love, family, metropolitan, idol, news, documentary, etc., without limitation.

In this embodiment, when implementing the step S101, the product providing system 1000 applying the cold start recommendation method according to the embodiment of the present invention may first obtain information about a device of a new user, for example, obtain an identification number of the device of the new user, and registration information provided by the new user when the product providing system 1000 registers, so as to search for the new user in a third party application according to the information, and further obtain user data generated by the new user by using the third party application. For example, the product providing system 1000 may communicate data interactions with a third party platform through the international mobile equipment identity (International Mobile Equipment Identity, IMEI) and UTD-ID of the handset used by the new user.

In one example, the implementation of step S101 may include: and determining the characteristic value of the regional characteristic of the new user according to the origin of the historical trip, the destination of the historical trip of the user, the origin of the historical trip of the user and the surrounding building types of the destination and/or the receiving address of the order in the network management platform. For example, determining the origin of the market with the highest frequency of occurrence in the historical trip and the surrounding buildings and/or the receiving address with the highest frequency of use, wherein the province is used as the characteristic value of the regional characteristic of the new user.

In one example, the implementation of step S101 may include: and determining the characteristic value of the academic characteristic of the new user according to the historical search record of the user provided by the search engine. For example, search content of a history search record of a user is determined, the duty ratio of related teaching materials and/or related knowledge in different learning stages included in the search content is determined, the learning corresponding to the teaching materials and/or knowledge with the highest duty ratio is determined, and the feature value of the learning feature of the new user is determined.

In one example, the implementation of step S101 may include: and determining the age characteristic of the new user according to the video type watched by the user history provided by the video playing platform. For example, an optimum viewing age range corresponding to the video type viewed in the history is determined, and the optimum viewing age range is taken as a feature value of the age feature of the new user.

In one example, the implementation of step S101 may include: and determining the characteristic value of the sex characteristic of the new user according to the type of the paid commodity provided by the payment platform. For example, when the type of commodity paid is determined to be a garment, the ratio of male and female garments in the garment is determined, and the sex corresponding to the garment with the ratio is used as the characteristic value of the sex characteristic.

S102, obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics.

By way of example, the above-mentioned products may be books, electronic products, cosmetics, clothing, etc., without limitation.

In one example, the product collection described above may include a collection of all products that can be provided by the product providing system 1000.

In another example, the product set may be a set composed of products selected from all products according to a set condition, so that the information processing amount can be reduced and the recommendation efficiency can be improved. Based on this, the cold start recommendation method provided in this embodiment may further include: and screening the products to be recommended from all the products according to the set conditions to form the product set.

In this example, the above-described setting condition may include at least one of searching for a heat exceeding a set search heat in the search engine, a transaction heat formed by transaction payment exceeding a set transaction heat, and a conversion rate exceeding a set conversion rate in the history of the new user.

The search heat may be quantified, for example, based on the number of times a product is searched for within a predetermined period of time.

The transaction heat may be quantified, for example, according to the number of times the product is successfully transacted within a predetermined period of time. Taking books as an example, the transaction payment may include at least one of a reading payment and a purchasing payment.

Taking the product as the product a as an example, the conversion rate in the history new user for the product a may be: the ratio between the number of people of the product A and the total number of the historical new users containing the product A in the recommended product is converted for all the historical new users containing the product A in the recommended product. The meaning of the above conversion may be determined according to the need and the type of the provided product, for example, the product providing system 1000 provides an electronic book reading service, and the conversion may refer to a book whose reading progress reaches a set condition, and the reading progress may include at least one of a reading amount and a reading duration; as another example, where the product providing system 1000 provides a service that sells a certain type of product, conversion may refer to successful sales, etc.

Taking the example that the user features include age features, gender features, academic features and region features, the classification feature value obtained by classifying each product in the product set according to the user features in the step S102 may be expressed as a1-a4 as follows:

a1, obtaining a classification characteristic value of each product in the product set, wherein the classification characteristic value is obtained by classifying each product according to the sex characteristics.

For example, for each product in a product set, a number X1 of female users that converted the product, a number X2 of male users that converted the product, a number Y1 of female users in all users, and a number Y2 of male users in all users are obtained.

This may be that X1 and Y1, and X2 and Y2 are directly taken as classification characteristic values obtained by classifying according to gender.

In this case, X1 and X2 may be directly used as classification feature values obtained by classifying according to gender.

The preference degree of the product for females and the preference degree of the product for males can be used as classification characteristic values obtained by classifying according to sexes.

The preference prifile _pre _{j_i} of each product for any classification feature j_i of any user feature j can be calculated according to the following formula (1):

In formula (1), j_i represents the serial number of the classification feature obtained by classifying the provided product according to the user feature j, where j is the serial number of the user feature, for example, j=1 represents the gender feature, j=2 represents the age feature, j=3 represents the academic feature, j=4 represents the regional feature, taking the user feature as the gender feature as an example, it has two classification features, for example, i=1 represents a female, i=2 represents a male, prifile _pre _{1_1} represents the preference of a certain product for a female, and prifile _pre _{1_2} represents the preference of the product for a male. n represents the number of classification features of the provided product classified according to a user feature j, for example, the number of classification features obtained for classification according to gender features includes females and males, and thus the number of classification features obtained for classification according to gender features is 2, n is 2, and the number of classification features obtained for classification according to age features is four, and thus the number of classification features obtained for classification according to age features is 4, n is 4.Read_uv _{j_i} represents the number of people who converted the classification feature of a product that corresponds to the sequence number j_i. Read_uv_all _{j_i} represents the number of people in all users of the product providing system 1000 who fit the classification feature of sequence number j_i.

In this example, for the user feature being a gender feature, the classification feature includes a female (denoted by number 1) and a male (denoted by number 2), and the preference of a product for the female and the preference of the product for the male can be calculated according to the formula (1), namely:

male preference= (X2/X1)/(Y2/Y1);

Female preference = (X1/X2)/(Y1/Y2).

A2, acquiring characteristic values of age characteristics obtained by classifying each product in the product set according to the age characteristics.

For example, for each product in a product collection, a number Z1 of users under 20 years old who converted the product, a number Z2 of users under 20 years old to 35 years old who converted the product, a number Z3 of users under 35 years old to 50 years old who converted the product, a number Z4 of users over 50 years old who converted the product, a number W1 of users under 20 years old among all users, a number W2 of users under 20 years old to 35 years old among all users, a number W3 of users under 35 years old to 50 years old among all users, and a number W4 of users over 50 years old among all users is obtained.

This may be that Z1 and W1, Z2 and W2, Z3 and W3, and Z4 and W4 are directly taken as classification characteristic values obtained by age classification.

In this case, Z1, Z2, Z3, and Z4 may be directly used as classification characteristic values obtained by classifying according to age.

Similarly, the preference of the product for different age classifications may be used as the classification characteristic value obtained by classifying according to gender.

Still referring to the above formula (1), for the user feature being an age feature, the classification feature may include under 20 years old (denoted by number 1), 20 years old to 35 years old (denoted by number 2), 35 years old to 50 years old (denoted by number 3), and over 50 years old (denoted by number 4), that is, the age feature has 4 classification features, corresponding to n=4 in the formula (1), according to the formula (1), preference degrees of a product for the above 4 classification features included in the age feature may be calculated respectively:

and a3, acquiring classification characteristic values of the academic characteristics obtained by classifying each product in the product set according to the academic characteristics.

For example, for each product in a product set, a number P1 of users that converts the product's history to junior middle school and below, a number P2 of users that converts the product's history to junior middle school, a number P3 of users that converts the product's history to university's history, a number P4 of users that converts the product's history to research student's history, a number Q1 of users that all users are junior middle school and below, a number Q2 of users that all users are junior middle school, a number Q3 of users that all users are junior middle school's history, and a number Q4 of users that all users are junior research student's history are obtained.

This may be that P1 and Q1, P2 and Q2, P3 and Q3, and P4 and Q4 are directly taken as classification characteristic values obtained by the academic classification.

In this case, P1, P2, P3, and P4 may be directly used as classification characteristic values obtained by the academic classification.

Similarly, the preference degree of the product for different calendar classifications can be used as the classification characteristic value obtained according to the calendar classifications.

Still referring to the above formula (1), for the user feature to be a learning feature, the classification feature may include a junior middle school and following (denoted by number 1), a senior middle school (denoted by number 2), a university (denoted by number 3), a research student (denoted by number 4), etc., that is, the learning feature has 4 classification features, n=4 in the corresponding formula (1), and according to the formula (1), the preference of a product for the above 4 classification features included in the learning feature can be calculated respectively.

And a4, acquiring a classification characteristic value of the regional characteristics obtained by classifying each product in the product set according to the regional characteristics.

Likewise, for the regional features, the classification feature values obtained by classifying a product according to the academic may be obtained by referring to the examples of a1 to a3 above, which are not described herein again.

And S103, obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product.

Continuing taking the user features as gender feature, age feature, region feature and academic feature, respectively as examples, in one example, obtaining the matching degree between the new user and each product according to the user feature value and the classification feature value of each product in S103 may be achieved by the following steps S1031 and S1032:

s1031, obtaining the preference degree of the corresponding product for each user characteristic value according to the classification characteristic value of each product.

Taking the user characteristic as the sex characteristic as an example, the characteristic value of the sex characteristic of the new user is female, and according to different forms of the classification characteristic value, the preference of each product for female can be directly obtained from the classification characteristic value of the product, or according to the classification characteristic value of the product and the formula (1) above, the preference of each product for female can be obtained.

Taking the user characteristic as the age characteristic as an example, the characteristic value of the age characteristic of the new user is less than 20 years old, according to different forms of the classification characteristic value, the preference degree of each product for the age range of less than 20 years old can be directly obtained from the classification characteristic value of the product, or the preference degree of each product for the age range of less than 20 years old can be obtained according to the classification characteristic value of the product and the formula (1) above.

S1032, obtaining the matching degree between the new user and each product according to the preference degree corresponding to each product and the influence weight of each user characteristic.

For example, the expression for calculating the matching degree M described above may be the following expression (2):

In the formula (2), M refers to the degree of matching. j represents the serial number of the user feature, for example, four user features are selected in the embodiment of the invention, namely, sex feature, age feature, learning feature and region feature, and the serial number of the sex feature is 1, the serial number of the age feature is 2, the serial number of the learning feature is 3, and the serial number of the region feature is 4.w _j refers to the influence weight of the user feature with the sequence number j, where w _j may be a preset fixed value, and the influence weights of different user features may be the same or different, and is not limited herein, for example, w ₁ represents the influence weight of the gender feature. m is the number of user features, for example, in the embodiment of the present invention, where m=4, the four user features are selected. In the formula (2), j_i is determined according to the user characteristic value of the new user for the user characteristic j, for example, the characteristic value of the new user for the gender characteristic is female, j_i is 1_1, for example, the characteristic value of the new user for the age characteristic is less than 20 years old, j_i is 2_1, for example, the characteristic value of the new user for the academic characteristic is research calendar, j_i is 3_4, and so on, and will not be described again.

The user feature values for each user feature of the new user include: for example, in women, under 20 years old, in the research academic, in northeast areas, according to the above formula (2), the matching degree between the new user and each product can be obtained according to the preference degree of each product for each user characteristic value and the influence weight of the corresponding user characteristic.

S104, obtaining a product recommendation list of the new user at least according to the matching degree between the new user and each product.

The implementation manner of the step S104 may be: based on the matching degree between the new user and each product obtained in the step S103, N products with the highest matching degree are extracted to be recommended products, and a product recommendation list is generated based on the related information of the recommended products. The product recommendation list may further be presented to the new user.

Taking a product as an example, the related information of the recommended product may be: book name, author, press, book cover image, etc.

For example, the above-mentioned product recommendation list may be displayed in the form of fig. 3 and fig. 4.

< Example two >

The cold start recommendation method provided in this embodiment, as shown in fig. 5, may include the following steps S501 to S505:

s501, obtaining a user characteristic value of the new user for setting the user characteristic according to user data generated by the new user through using a third party application.

S502, obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics.

S503, according to the user characteristic value and the classification characteristic value of each product, obtaining the matching degree between the new user and each product.

It should be noted that the specific implementation of S501-S503 is the same as the specific implementation of S101-S103, and will not be repeated here.

S504, acquiring the search heat of each product in the search engine.

In this embodiment, the search heat may be quantified, for example, according to the number of times a product is searched for within a preset period of time.

S505, obtaining a product recommendation list of the new user at least according to the matching degree and the searching heat degree between the new user and each product.

In this embodiment, since the search heat of the product in the search engine is also a factor that affects the conversion of the product by the new user, the recommendation list of the product may be further determined according to the search heat of the product in the search engine.

Based on the above, when the search heat is quantitatively represented by H, a product recommendation list of a new user can also be obtained based on the output value f1 of the following formula (3):

Wherein, K1 and K2 respectively represent the weight of the matching degree and the searching heat, and K1 and K2 are both larger than 0 and the sum is 1. In addition, the description of the other parameters in the above formula (3) is the same as the description of the parameters in the above formula (2), and will not be repeated here.

In this embodiment, based on f1 obtained in the above formula (3), the highest N products corresponding to f1 are extracted as recommended products, and a product recommendation list is generated based on the related information of the recommended products. The product recommendation list may further be presented to the new user.

The above-mentioned product recommendation list may also be displayed in the form of fig. 3 and fig. 4, for example.

Based on the above embodiment, when obtaining the product recommendation list of the new user, the factor of searching heat which can affect the conversion product of the new user is considered, so that the finally obtained recommendation list is closer to the actual requirement of the user.

Example III

The cold start recommendation method provided in this embodiment, as shown in fig. 6, may include the following steps S601 to S605:

S601, obtaining a user characteristic value of the new user for setting the user characteristic according to user data generated by the new user through using a third party application.

S602, obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics.

And S603, obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product.

It should be noted that the specific implementation of S601-S603 is the same as the specific implementation of S101-S103, and will not be repeated here.

S604, acquiring transaction heat formed by transaction payment of each product.

In this embodiment, the transaction heat may be quantified, for example, according to the number of times the product is successfully transacted within a preset time period.

S605, obtaining a product recommendation list of the new user at least according to the matching degree and the transaction heat degree between the new user and each product.

In this embodiment, since the transaction heat of the product in the transaction is also a factor affecting the conversion of the product by the new user, the recommendation list of the product can be further determined according to the transaction heat of the product in the transaction payment.

Based on the above, when the transaction heat is represented by P, the product recommendation list of the new user can also be obtained based on the output value f2 of the following formula (4):

Wherein, K3 and K4 respectively represent the weight of the matching degree and the transaction heat, and K3 and K4 are both more than 0 and the sum is 1. In addition, the description of the other parameters in the above formula (4) is the same as the description of the parameters in the above formula (2), and will not be repeated here.

In one embodiment, when transaction heat is represented by P, a product recommendation list for the new user may also be obtained based on the output value f2 of the following equation (5):

Wherein K5, K6, K7 represent the weights of the matching degree, the search heat degree, and the transaction heat degree, respectively, and K5, K6, and K7 are all greater than 0 and the sum is 1. In addition, the description of the other parameters in the above formula (5) is the same as the description of the parameters in the above formula (2) and the above formula (3), and will not be repeated here.

Based on the above, in the cold start recommendation method provided in the present embodiment, S605 may be replaced with: and obtaining a product recommendation list of the new user at least according to the matching degree, the transaction heat degree and the search heat degree between the new user and each product.

In this embodiment, based on f2 obtained in the above formula (4) or formula (5), the highest N products corresponding to f2 are extracted as recommended products, and a product recommendation list is generated based on the related information of the recommended products. The product recommendation list may further be presented to the new user.

Based on the above embodiment, when obtaining the product recommendation list of the new user, the factor of transaction heat which can affect the conversion product of the new user is considered, so that the finally obtained recommendation list is closer to the actual requirement of the user.

Example IV

The cold start recommendation method provided in this embodiment, as shown in fig. 7, may include the following steps S701-S706:

S701, obtaining a user characteristic value of the new user for setting the user characteristic according to the user data generated by the new user through using the third-party application.

S702, obtaining a classification characteristic value obtained by classifying each product in the product set according to the user characteristics.

S703, obtaining the matching degree between the new user and each product according to the user characteristic value and the classification characteristic value of each product.

It should be noted that the specific implementation of S701-S703 is the same as the specific implementation of S101-S103, and will not be described here again.

S704, comparing the user characteristic value of the new user with the user characteristic value of the historical new user to obtain a comparison result.

In this embodiment, the specific implementation manner of S704 is as follows: and according to the user characteristic value of the new user, based on a collaborative filtering algorithm, finding the user characteristic value of the historical new user which is most similar to the user characteristic value of the new user from the user characteristic values of the historical new user. And the user characteristic value of the most similar historical new user is used as a comparison result.

And S705, obtaining the synergy of each product according to the comparison result and the product converted by the historical new user in the set time after registration.

In one embodiment, the step S705 may be implemented by the following steps S7051-S7053:

S7051, obtaining a product converted by the new user in the set time after registration.

In this embodiment, the history new user refers to a user whose current date is longer than a preset time period from the registered date.

S7052, obtaining classification characteristic values obtained by classifying each converted product in a history new user according to the product characteristics.

In the present embodiment, the specific implementation of S7052 described above is similar to the specific implementation of S102 described above, except that when S7052 described above is executed, it is determined based on a history of new users.

For example, when the product features are used as gender features, the classification feature values obtained by classifying the converted product according to the gender features in the historical new user may be: the method comprises the steps of obtaining the number of female users in the history fresh users of the product, and converting the number of male users in the history fresh users of the product, the number of female users in all the history fresh users, and the number of male users in all the history fresh users.

S7053, obtaining the synergy of each product according to the comparison result and the classification characteristic value of each converted product.

In this embodiment, for one converted product, the classification characteristic value of the one converted product is compared with the comparison result obtained in S704: the user characteristic value of the most similar historical new user is brought into the calculation formula of the matching degree in the formula (2), and the finally obtained matching degree is used as the synergy degree of the converted product. The step is repeated, and the synergy of each conversion product can be obtained.

In another embodiment, the step of S705 may be implemented as follows: based on the comparison result obtained in S704: the user characteristic value of the most similar historical new user is determined, and the product converted by the corresponding historical new user is obtained;

For each of the products converted by the historic new user, classifying feature values of the one converted product, and comparing results based on the above S704: the user characteristic value of the most similar historical new user is brought into the calculation formula of the matching degree in the formula (2), and the finally obtained matching degree is used as the synergy degree of the converted product. The step is repeated, and the synergy of each conversion product can be obtained.

S706, obtaining a product recommendation list of the new user at least according to the matching degree and the cooperation degree between the new user and each product, wherein the converted products belong to the product set.

In this embodiment, since the product pair converted by the historical new user has the degree of synergy of the user feature value of the historical new user most similar to the user feature value of the new user, which is also a factor affecting the product conversion of the new user, the recommendation list of the product can be further determined according to the degree of synergy.

Based on the above, when the degree of synergy is represented by C, the product recommendation list of the new user can also be obtained based on the output value f3 of the following formula (6):

Wherein, K8 and K9 respectively represent the weight of the matching degree and the synergy degree, and K8 and K9 are both more than 0 and the sum is 1. In addition, the description of the other parameters in the above formula (6) is the same as the description of the parameters in the above formula (2), and will not be repeated here.

In one embodiment, when the degree of synergy is denoted by C, the product recommendation list of the new user may also be obtained based on the output value f3 of the following formula (7):

Wherein, K10, K11, K12 respectively represent the weight of matching degree, transaction heat and cooperation degree, K10, K11, K12 are all more than 0, and the sum is 1. The description of the other parameters in the above formula (7) is the same as the description of the parameters in the above formulas (2) and (4), and will not be repeated here.

Based on the above, in the cold start recommendation method provided in the present embodiment, S706 may be replaced by: and obtaining a product recommendation list of the new user at least according to the matching degree, the coordination degree and the transaction heat degree between the new user and each product, wherein the converted products belong to a product set.

In one embodiment, when the degree of synergy is denoted by C, the product recommendation list of the new user may also be obtained based on the output value f3 of the following formula (8):

Wherein, K13, K14, K15 respectively represent the weight of matching degree, searching heat and cooperation degree, K13, K14, K15 are all more than 0, and the sum is 1. The description of the other parameters in the above formula (8) is the same as the description of the parameters in the above formulas (2) and (3), and will not be repeated here.

Based on the above, in the cold start recommendation method provided in the present embodiment, S706 may be replaced by: and obtaining a product recommendation list of the new user at least according to the matching degree, the coordination degree and the search heat degree between the new user and each product, wherein the converted product belongs to a product set.

In one embodiment, when the degree of synergy is denoted by C, the product recommendation list of the new user may also be obtained based on the output value f3 of the following formula (9):

Wherein K16, K17, K18, K19 respectively represent the weights of the matching degree, the search heat degree, the synergy degree and the transaction heat degree, and K16, K17, K18, K19 are all larger than 0 and the sum is 1. The description of the other parameters in the above formula (9) is the same as the description of the parameters in the above formulas (2), (3) and (4), and will not be repeated here.

Based on the above, in the cold start recommendation method provided in the present embodiment, S706 may be replaced by: and obtaining a product recommendation list of the new user at least according to the matching degree, the cooperation degree, the searching heat degree and the transaction heat degree between the new user and each product, wherein the converted product belongs to a product set.

It should be noted that, when the converted product corresponding to the synergy degree C is different from the product corresponding to the matching degree M, the synergy degree C may be exemplarily set to 0.

In this embodiment, based on f3 obtained in the above formulas (6) to (8), the highest N products corresponding to f3 are extracted as recommended products, and a product recommendation list is generated based on the related information of the recommended products. The product recommendation list may further be presented to the new user.

Based on the above embodiment, when obtaining the product recommendation list of the new user, the factor of the degree of synergy that can affect the conversion product of the historical new user is considered, so that the finally obtained recommendation list is closer to the actual requirement of the user.

< Example five >

The cold start recommending method provided by the embodiment further includes the following steps S105 and S106 on the basis of any one of the above embodiments:

S105, acquiring a product list actually converted by the new user.

Specifically, the product list actually converted by the new user is a list formed by products actually converted by the new user in a preset time period. Here, the preset period of time may be 10 days or the like.

S106, comparing the actually converted product list with the product recommendation list, and updating the book recommendation list according to the comparison result.

In this embodiment, when S106 is performed, the number of products included in each of the product list and the product recommendation list actually converted by the new user may be first determined. And then determining whether w _j in the matching degree formula is needed to be adjusted and calculated according to the ratio of the number to the total number of products in the product recommendation list.

If the ratio is greater than the preset ratio, the w _i in the matching degree formula is not adjusted. Otherwise, w _j in the matching degree formula in S1032 is adjusted.

For example, the adjustment manner for adjusting w _j in the above matching degree formula may be: and determining the preference degree with large overall numerical value in the preference degrees corresponding to the products contained in the product list and the product recommendation list actually converted by the new user, and increasing the value of w _j corresponding to the preference degree. And then based on the adjusted w _j, obtaining a subsequent product recommendation list.

Based on the above embodiments, in the cold start recommendation method provided by the embodiment of the present invention, the obtained book recommendation list may be updated, so that the book recommendation list obtained by the subsequent new user is more closely attached to the actual requirement of the subsequent new user.

< Example six >

The embodiment of the invention provides a cold start recommending method for books, which comprises the following steps of S201 to S204:

s201, obtaining a user characteristic value of the new user for setting the user characteristic according to user data generated by the new user through using a third party application.

S202, obtaining a classification characteristic value obtained by classifying each book in the book set according to the user characteristics.

S203, according to the user characteristic values and the classification characteristic values of each book, the matching degree between the new user and each book is obtained.

S204, obtaining a book recommendation list of the new user at least according to the matching degree between the new user and each book.

In one embodiment, the embodiment of the present invention provides a cold start recommendation method, which further includes the following steps S205 to S204:

S205, acquiring the search heat of each product in the search engine.

S206, acquiring transaction heat generated by transaction payment of each product.

S207, comparing the user characteristic value of the new user with the user characteristic value of the historical new user to obtain a comparison result.

S208, obtaining the synergy of each product according to the comparison result and the products converted by the historical new user in the set time after registration, wherein the converted products belong to the product set.

S209, the method further obtains a product recommendation list of the new user according to the search heat, the transaction heat and the cooperation degree of each product.

It should be noted that the book provided in the embodiment of the present invention may be used as a product involved in any one of the cold start recommendation methods in the first to fifth embodiments.

The above method embodiments are described in a progressive manner, and the same and similar parts of each embodiment are referred to each other, and each embodiment is mainly described as different from other embodiments, and each embodiment may be used alone or in combination with each other as needed, for example, a person skilled in the art may combine any two or more method embodiments to implement the information processing method of the present invention as needed, which is not limited herein.

< Example seven >

The cold start recommendation device provided in this embodiment includes: the system comprises a user characteristic acquisition module, a product characteristic acquisition module, a matching module and a recommendation module. Wherein:

the user characteristic acquisition module is used for acquiring a user characteristic value of the new user for setting the user characteristic according to the user data generated by the new user by using the third-party application;

And the recommending module is used for acquiring a product recommending list of the new user at least according to the matching degree between the new user and each product.

In one embodiment, the user characteristics include at least one of gender characteristics, age characteristics, geographic characteristics, and academic characteristics.

In one embodiment, the matching module is specifically configured to:

and obtaining the matching degree between the new user and each product according to the corresponding preference degree of each product and the influence weight of each user characteristic.

In one embodiment, the recommendation module is further to:

and acquiring the search heat of each product in the search engine so as to acquire a product recommendation list of the new user at least according to the search heat.

In one embodiment, the recommendation module is further to:

In one embodiment, the recommendation module further comprises: a comparing unit and a recommending unit, wherein:

the comparison unit is used for comparing the user characteristic value of the new user with the user characteristic value of the historical new user to obtain a comparison result;

and the recommending unit is used for obtaining the degree of synergy of each product according to the comparison result and the products converted by the historical new user in the set time after registration so as to obtain a product recommending list of the new user at least according to the degree of synergy, wherein the converted products belong to a product set.

In one embodiment, the recommending unit is further configured to obtain a product converted by the new user within a set time after registration;

obtaining a classification characteristic value obtained by classifying each converted product in a history new user according to user characteristics;

In an embodiment, the cold start recommending apparatus provided in this embodiment further includes a conversion list obtaining module and an updating module, where:

The conversion list acquisition module is used for acquiring a product list actually converted by the new user;

And the updating module is used for comparing the actually converted product list with the product recommendation list and updating the book recommendation list according to the comparison result.

In an embodiment, the cold start recommendation device provided in this embodiment further includes a product set forming module, where: the product set forming module is used for screening out products to be recommended from all the products according to set conditions to form a product set; the set condition includes at least one of a search heat in the search engine exceeding a set search heat, a transaction heat formed by a transaction payment exceeding a set transaction heat, a conversion rate in a history of new users exceeding a set conversion rate.

It should be noted that the above products may be products such as books.

< Electronic device >

The electronic device provided in this embodiment includes any one of the cold start recommending apparatuses in the foregoing embodiments.

Or an electronic device 80 provided in this embodiment, as shown in fig. 8, includes: a memory 81 and a processor 82. Wherein,

A memory 81 for storing computer instructions.

A processor 82 for calling computer instructions from the memory 81 and executing the cold start recommendation method according to any one of the above embodiments one to five under the control of the computer instructions.

The electronic device may be, for example, the terminal device 1200 in fig. 1, or the server 1100 in fig. 1, or may include the terminal device 1200 and the server 1100 in fig. 1, which is not limited herein.

< Storage Medium >

In this embodiment, there is also provided a computer-readable storage medium storing computer instructions that, when executed by a processor in the storage medium, implement any of the cold start recommendation methods provided in the above embodiments.

The present invention may be a computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present invention.

The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium (a non-exhaustive list includes a portable computer diskette, a hard disk, a random access memory (RAM, read-only memory (ROM, erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disc read-only memory (CD-ROM, digital versatile disks (DVD, memory sticks, floppy disks, mechanical coding devices, punch cards or bump structures within a groove such as those having instructions stored thereon, and any suitable combination thereof).

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present invention can be assembler instructions, instruction set architectures (ISA instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as SMALLTALK, C ++ or the like and conventional procedural programming languages, such as the "C" language or similar programming languages.

Various aspects of the invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems and computer program products) according to embodiments of the invention, it being understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

The foregoing description of embodiments of the invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvements in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. A cold start recommendation method, comprising:

obtaining a product converted by the history new user in a set time after registration; wherein the converted product belongs to the product collection;

Obtaining the degree of synergy of each product according to the comparison result and the classification characteristic value of each converted product;

And obtaining a product recommendation list of the new user at least according to the matching degree between the new user and each product and the synergy degree.

2. The method of claim 1, wherein the user characteristics include at least one of gender characteristics, age characteristics, territory characteristics, and academic characteristics.

3. The method of claim 1, wherein the obtaining a degree of matching between the new user and each product according to the user feature value and the classification feature value of each product comprises:

4. The method of claim 1, wherein the method further comprises:

5. The method of claim 1, wherein the method further comprises:

6. The method of any of claims 1 to 5, wherein the method further comprises, after obtaining the new user's product recommendation list:

Acquiring a product list actually converted by the new user;

And comparing the actually converted product list with the product recommendation list, and updating the product recommendation list according to a comparison result.

7. The method of any one of claims 1 to 5, wherein the method further comprises:

8. A cold start recommendation method, comprising:

obtaining a book recommendation list of the new user at least according to the matching degree between the new user and each book;

wherein the method further comprises:

Obtaining the synergy of each book according to the comparison result and books converted by the historical new user in the set time after registration, so as to obtain a book recommendation list of the new user at least according to the synergy, wherein the converted books belong to the book set;

The obtaining the synergy of each book according to the comparison result and books converted by the historical new user in the set time after registration comprises the following steps:

acquiring books converted by the historical new user in a set time after registration;

Obtaining classification characteristic values obtained by classifying each converted book in the historical new user according to the user characteristics;

And obtaining the synergy of each book according to the comparison result and the classification characteristic value of each converted book.

9. The method of claim 8, wherein the method further comprises:

Acquiring the searching heat of each book in a search engine;

Acquiring transaction heat generated by transaction payment of each book;

the method further comprises the step of obtaining a book recommendation list of the new user according to the search heat, the transaction heat and the synergy of each book.

10. A cold start recommendation device, comprising:

The recommending module is used for obtaining a product recommending list of the new user at least according to the matching degree between the new user and each product;

wherein, the recommendation module further comprises: a comparing unit and a recommending unit, wherein:

The recommendation unit is used for obtaining the degree of synergy of each product according to the comparison result and the products converted by the historical new user in the set time after registration so as to obtain a product recommendation list of the new user at least according to the degree of synergy, wherein the converted products belong to a product set;

the recommending unit is specifically used for acquiring products converted by the historical new user within a set time after registration;

11. An electronic device comprising the cold start recommendation apparatus of claim 10; or the electronic device comprises: a memory for storing computer instructions, and a processor for calling the computer instructions from the memory and executing the cold start recommendation method according to any of claims 1-9 under control of the computer instructions.

12. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the cold start recommendation method of any one of claims 1-9.