CN103617547B - A kind of business recommended method and system - Google Patents

Abstract

The invention discloses a service recommendation method and system, which includes obtaining basic information of users, original information of users using the Internet, and location situation information of users using mobile services; establishing a user interest model according to the obtained original information of users using the Internet; Establish a user scenario model based on the obtained location scenario information of the user using the mobile service; establish a user interest model, a correlation model between the user scenario model and business information, and calculate the recommendation degree of each business recommended to the user according to the correlation model, and Push highly recommended services to users. In the technical solution provided by the present invention, the user location scenario is introduced into the personalized service recommendation method, which improves the accuracy of personalized service recommendation and user experience; moreover, the present invention realizes resource elasticity based on the system framework of cloud computing resource pool , Dynamic expansion, shortening the system response time, while improving the user experience.

Description

A business recommendation method and system

technical field

The present invention relates to cloud computing technology, in particular to a location service (LBS)-based cloud service personalized service recommendation method and system.

Background technique

At present, focused services and refined operations have become an important means for operators to develop services and improve user experience. The existing precision marketing system is mainly based on the basic information of users, geographic location information, communication behavior and other data, from which business operation rules are discovered, and then business recommendations are carried out.

In the existing LBS-based business recommendation service system, only the geographical location information and the communication behavior information of the business category are considered, and the user's interest preference and location situation preference are not considered. In this way, the business recommended to the user is not the user's most desired service , resulting in poor user experience.

Contents of the invention

In order to solve the above technical problems, the present invention provides a service recommendation method and system, which can respond to user needs in real time and improve user experience.

In order to achieve the purpose of the present invention, the present invention provides a method for recommending services, including: acquiring basic user information, original information of the user using the Internet, and location context information of the user using mobile services;

Establish a user interest model based on the obtained original information of the user using the Internet; establish a user scenario model based on the obtained location context information of the user using the mobile service;

Establish the relationship model between user interest model, user scenario model and business information, calculate the recommendation degree of recommending new services to users according to the relationship model, and push the highly recommended services to users.

The basic user information includes at least: user identity information, order service information;

The original information of the user using the Internet is URL log information.

Described establishment user interest model comprises:

By analyzing the URL log information, the subject category of the web page document accessed by the user is obtained;

Establish the corresponding relationship between different interest categories and interest degrees;

Wherein, the degree of interest is directly proportional to the number of webpage-like documents included in the corresponding interest category, and inversely proportional to the time difference of the recently viewed webpage documents included in the interest category.

The method also includes: updating the user interest model according to a preset timing period.

The location context information of the user using the mobile service includes: location information, time information, terminal equipment information and service information.

The establishment of the user scenario model includes:

According to different types of location scenarios, a corresponding relationship among location, time, terminal, service, and interest degree of location scenarios is established.

The establishment of the relationship model between the user interest model, the user situation model and the business information includes:

Calculate the vector product of the user interest model of each user and the modularity of the user scenario to obtain an association relationship model.

The pushing of highly recommended services to users includes:

Calculating the degree of recommendation for recommending new services to users according to the relationship model;

The recommendation degree of the new business is sorted, and according to the business recommendation quantity threshold preset by the system, the business whose recommendation degree ranks first in the business recommendation quantity threshold item is pushed to the user.

The present invention also recommends a service recommendation system, which at least includes an acquisition unit, a first establishment unit, a second establishment unit, a third establishment unit, and a service recommendation unit; wherein,

The acquisition module is used for the basic information of the user, the original information of the user using the Internet, and the location context information of the user using the mobile service;

A first establishing unit, configured to establish a user interest model according to the obtained original information on the use of the Internet by the user;

The second establishing unit is used to establish a user scenario model according to the obtained location scenario information of the user using the mobile service;

The third establishment unit is used to establish a relationship model between the user interest model, the user situation model and the service information according to the established user interest model and user situation model;

The service recommendation unit is configured to calculate the recommendation degree of each service recommended to the user according to the association relationship model, and push the service with a high recommendation degree to the user according to the basic information of the user.

The service recommendation system is located in a cloud computing resource pool.

Compared with the prior art, the present invention includes obtaining basic information of users, original information of users using the Internet, and location context information of users using mobile services; establishing a user interest model according to the obtained original information of users using the Internet; Use the location context information of the mobile service to establish a user context model; establish a user interest model, a correlation model between the user context model and business information, and calculate the recommendation degree of each business recommended to the user according to the correlation model, and calculate the recommendation degree High-quality services are pushed to users. In the technical solution provided by the present invention, the user location scenario established according to the user's interests is introduced into the personalized service recommendation method, which improves the accuracy of personalized service recommendation and user experience; and the present invention is based on the system framework of the cloud computing resource pool, It realizes the elasticity and dynamic expansion of resources, shortens the system response time, and improves the user experience at the same time.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Description of drawings

The accompanying drawings are used to provide a further understanding of the technical solution of the present invention, and constitute a part of the description, and are used together with the embodiments of the application to explain the technical solution of the present invention, and do not constitute a limitation to the technical solution of the present invention.

Fig. 1 is a flow chart of the service recommendation method of the present invention;

FIG. 2 is a schematic diagram of the composition and structure of the service recommendation system of the present invention.

detailed description

In order to make the purpose, technical solution and advantages of the present invention more clear, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined arbitrarily with each other.

The steps shown in the flowcharts of the figures may be performed in a computer system, such as a set of computer-executable instructions. Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

Fig. 1 is a flowchart of the service recommendation method of the present invention, as shown in Fig. 1, comprising the following steps:

Step 100: Obtain the basic information of the user, the original information of the user using the Internet, and the location context information of the user using the mobile service.

In this step, basic user information such as user identity information, subscription service information, etc. can be collected from the Business Support System (BSS)/Operation Support System (OSS; Operation Support System);

Collect the original information of users using the Internet (log information of the Uniform Resource Locator (URL) accessed) from the broadband access server (BRAS, Broadband Remote Access Server) and remote user dial-up authentication system (RADIUS, Remote Authentication Dial In User Service), Such as( _URL1 ; _URL2 ;Λ);

Through the mobile base station positioning device installed in the mobile base station, the location situation information of the user using the mobile service is acquired. The location context information of the user using the mobile service includes the following four types of information: (1) location information, including location name L _Name , and its precise longitude information L _Longitude and latitude information L _Latitude ; (2) time information, including date L _Date and specific time L _Time ; (3) terminal equipment information, i.e. the type L _Terminal of the mobile terminal equipment; (4) business information L _Service , that is to say, the location context information of the user using the mobile service includes the following sets: (L _Name , L _Longitude , L _Latitude , L _Date , L _Time , L _Terminal , L _Service ).

The specific implementation of this step belongs to the usual technical means of those skilled in the art, and the specific implementation is not used to limit the protection scope of the present invention, and will not be repeated here.

Step 101: Establish a user interest model based on the obtained original information of the user using the Internet; establish a user scenario model based on the obtained location context information of the user using the mobile service.

In this step, the specific realization of establishing the user interest model according to the obtained original information of the user using the Internet includes:

First, through the analysis of the obtained original information of users using the Internet (accessed URL log information), that is, using the existing text mining technology, to obtain the subject category of the page corresponding to each URL, such as sports, and establish a user interest model As shown in formula (1),

In formula (1), m represents the number of interests of the current user, 0<m≤|C|; |C| is the total number of system topic categories, (c _i , w _i ) is the user's (i+1)th ( 0≤i<m) category of interest items, _{ci indicates the name of the category of interest, and w i indicates} the interest degree of the category of interest in _ci . That is, a corresponding relationship between different interest categories and interest degrees is established.

Since the user's interests and hobbies will change dynamically over time, some content that the user is originally interested in will gradually be forgotten over time, and new interests will gradually emerge. Therefore, in formula (1), the user's first (i +1) (0≤i<m) The degree of interest w _i of category interest is directly proportional to the number of webpage documents of category c _i that the user is interested in, and inversely proportional to the time difference of recently browsing the webpage documents of category c _i . Therefore, the interest degree w _i of the user's (i+1)th (0≤i<m) type of interest is shown in formula (2),

In formula (2), n _i represents the number of URL logs of type c _i in the URL log information of the current user, t _i represents the latest appearance time of URL logs of type c _i in the URL log information of the current user, T represents the current system time, α >0 is an adjustment coefficient, which is used to prevent the denominator of the f() function in formula (2) from being 0. At the same time, it can also adjust the decay speed of the interest degree w _i . The smaller the value of α, the decay speed of the interest degree _wi The faster, therefore, the value of α can be determined according to specific needs.

This step also includes: updating the user interest model periodically, that is, according to a preset timing period.

In this step, a user scenario model is established according to the obtained location scenario information of the user using the mobile service According to the location information (including the location name L _Name , and its precise longitude information L _Longitude and latitude information L _Latitude ), the location is classified, such as catering, entertainment, hotel, etc., and L _j is obtained; according to the time information (including the date L _Date and The specific time L _Time ) classifies the time, such as working days/holidays, morning/afternoon/evening, etc., to obtain T _j ; Terminal _j is the type of terminal equipment L _Terminal ; classify the business according to the business information L _Service , and obtain Service _j . As shown in formula (3):

In formula (3), p represents the number of the current user’s location scenario types, (L _j , T _j , Terminal _j , Service _j , ξ _j ) represents the current user’s (j+1)th (0≤j≤ p-1) type location scenario item, L _j represents the location category name, T _j represents the time category name, Terminal _j represents the terminal category name, Service _j represents the service category name, ξ _j is the (j+1)th type of location scenario interest.

It should be noted that, for each user u in the system, where 1 ≤ u ≤ |U|, |U| The acquired user uses the location context information of the mobile service to establish a user context model.

Step 102: Establish a relationship model among the user interest model, user scenario model and service information.

According to the user interest model of each user in the system User Scenario Model Relationship model with business information As shown in formula (4):

In formula (4), Represents individual users in the system, 1≤u≤|U|, where |U| is the total number of users.

Step 103: According to the relationship model, calculate the degree of recommendation for recommending new services to users, and push services with high degrees of recommendation to users.

In this step, according to the relationship model Calculate the recommendation degree R _k for recommending a new service Service _k to user A (assuming that user A has 1~a interests) as shown in formula (5):

In formula (5), l represents user A's a interests.

Then, the recommendation degree R _k of the new business Service _k is sorted in descending order, and the new business Service _k whose recommendation degree R _k ranks in the top Num items is pushed to user A according to the system preset business recommendation quantity threshold Num.

In the method of the present invention, the user location scenario established according to user interests is introduced into the LBS personalized service recommendation method, which improves the accuracy of personalized service recommendation and user experience; moreover, the method of the present invention is applied to a system based on cloud computing resource pools In the framework, the elasticity and dynamic expansion of resources are realized, the system response time is shortened, and the user experience is also improved.

Figure 2 is a schematic diagram of the composition and structure of the service recommendation system of the present invention, as shown in Figure 2, at least including an acquisition unit, a first establishment unit, a second establishment unit, a third establishment unit, and a service recommendation unit; wherein,

The acquisition module is used for the basic information of the user, the original information of the user using the Internet, and the location context information of the user using the mobile service;

A first establishing unit, configured to establish a user interest model according to the obtained original information on the use of the Internet by the user;

The second establishing unit is used to establish a user scenario model according to the obtained location scenario information of the user using the mobile service;

The third establishing unit is configured to establish a relationship model between the user interest model, the user situation model and the service information according to the established user interest model and user situation model.

The service recommendation unit is configured to calculate the recommendation degree of each service recommended to the user according to the association relationship model, and push the service with a high recommendation degree to the user according to the basic information of the user.

The service recommendation system of the present invention is located in the cloud computing resource pool, and the cloud computing resource pool itself contains computing and storage resources distributed in different geographical locations. In this way, under the cloud computing framework, through the scheduling strategy of the cloud computing resource management According to the different requirements of the related applications of the personalized service recommendation system, it dynamically and transparently provides the required computing and storage resources, and dynamically recycles the resources when the current application is not in use. That is to say, in the system framework based on the cloud computing resource pool, the present invention realizes elastic and dynamic expansion of resources, shortens system response time, and improves user experience at the same time.

Although the embodiments disclosed in the present invention are as above, the described content is only an embodiment adopted for understanding the present invention, and is not intended to limit the present invention. Anyone skilled in the field of the present invention can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed by the present invention, but the scope of patent protection of the present invention must still be The scope defined by the appended claims shall prevail.

Claims (6)

1. A business recommendation method, characterized in that it is applied in a system framework based on a cloud computing resource pool, comprising: Obtain the basic information of the user, the original information of the user using the Internet, and the location context information of the user using the mobile service; the location context information of the user using the mobile service includes: location information, time information, terminal equipment information, and business information; the user uses the Internet The original information of is Uniform Resource Locator URL log information; Establish a user interest model based on the obtained original information of the user using the Internet; establish a user scenario model based on the location scenario information of the user using the mobile service obtained from the mobile base station positioning device installed in the mobile base station, including: according to different location scenario types, establish Correspondence between location, time, terminal, service, and interest in location scenarios; Establish the relationship model between user interest model, user scenario model and business information, calculate the recommendation degree of recommending new services to users according to the relationship model, and push the highly recommended services to users; The establishment of the relationship model between the user interest model, the user situation model and the service information includes: calculating the vector product of the user interest model of each user and the modularity of the user situation to obtain the relationship model. 2. The service recommendation method according to claim 1, wherein the basic user information includes at least: user identity information and subscription service information. 3. The service recommendation method according to claim 2, wherein said setting up a user interest model comprises: By analyzing the URL log information, the subject category of the web page document accessed by the user is obtained; Establish the corresponding relationship between different interest categories and interest degrees; Wherein, the degree of interest is directly proportional to the number of webpage-like documents contained in the corresponding interest category, and inversely proportional to the time difference of the recently viewed webpage documents contained in the interest category. 4. The service recommendation method according to claim 2 or 3, further comprising: updating the user interest model according to a preset timing period. 5. The service recommendation method according to claim 1, wherein the pushing the highly recommended service to the user comprises: Calculating the degree of recommendation for recommending new services to users according to the relationship model; The recommendation degree of the new business is sorted, and according to the business recommendation quantity threshold preset by the system, the business whose recommendation degree ranks first in the business recommendation quantity threshold item is pushed to the user. 6. A service recommendation system, characterized in that it is located in a cloud computing resource pool and at least includes an acquisition unit, a first establishment unit, a second establishment unit, a third establishment unit, and a service recommendation unit; wherein, The acquisition module is used for basic user information, original information of users using the Internet, and location context information of users using mobile services; the location context information of users using mobile services includes: location information, time information, terminal equipment information, and service information ; The first building unit is used to establish a user interest model according to the obtained original information of the user using the Internet; the original information of the user using the Internet is Uniform Resource Locator URL log information; The second establishment unit is used to establish a user scenario model according to the location scenario information of the user using the mobile service obtained from the mobile base station positioning device provided with the mobile base station, including: according to different location scenario types, establish location, time, terminal, business, And the corresponding relationship between the interest degree of the location scene; The third establishment unit is used to establish the relationship model between the user interest model, the user situation model and the business information according to the established user interest model and user situation model; specifically, it is used to calculate the user interest model and user Vector product of situational modularity to get relational model; The service recommendation unit is configured to calculate the recommendation degree of each service recommended to the user according to the association relationship model, and push the service with a high recommendation degree to the user according to the basic information of the user.