CN118822075A - Business recommendation method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a service recommendation method, a device, equipment and a storage medium, and relates to the technical field of intelligent recommendation, wherein the method comprises the following steps: acquiring order data and behavior data of cloud family members initially configured by a target service; analyzing the required data of the target user predicted from each cloud family member based on the order data and the behavior data; carrying out cluster analysis on each cloud family member based on a preset cluster model and required data to obtain a cluster result, wherein the preset cluster model comprises a cluster algorithm taking month consumption data, a relation set value, product information and concerned data as parameters; and predicting target users of the target service from the cloud family members according to the clustering result, and recommending the target service to the target users. According to the method and the system, the cloud family members are clustered by using the preset clustering model based on the data required by the target users, and the target users suitable for the target service are predicted according to the clustering result, so that the target users are accurately positioned, and the conversion rate of target service recommendation is improved.

Description

Business recommendation method, device, equipment and storage medium

Technical Field

The present application relates to the field of intelligent recommendation technology, and in particular to a business recommendation method, device, equipment and storage medium.

Background Art

Cloud home business is a family-centric service model that relies on cloud computing, big data, the Internet of Things and other technologies to provide a variety of intelligent, convenient and secure services to make the family more intelligent, convenient and secure, and improve the quality and efficiency of family life.

In order to better enable the public to experience cloud home services, the target user groups of cloud home services are often screened based on IOP, service recommendation strategies are bound, target user groups are locked, participation channels and activity rules are set, and personalized recommendations are made to the user groups of designated target services through intelligent matching of cloud home services. However, the current positioning of target users is not accurate enough, resulting in a low conversion rate of target services.

Summary of the invention

The main purpose of this application is to provide a business recommendation method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that the positioning of target users is not accurate enough, resulting in a low conversion rate of target business.

To achieve the above object, the present application provides a service recommendation method, the service recommendation method comprising:

Collect order data and behavior data of the cloud family members initially configured for the target business;

Predicting required data of the target user from each member of the cloud family based on the order data and the behavior data analysis, wherein the required data at least includes monthly consumption data, relationship set value, product information and attention data of the cloud family members to the target business;

Performing cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the concerned data as parameters;

The target users of the target service are predicted from the members of the cloud family according to the clustering result, and the target service is recommended to the target users.

Optionally, before the step of collecting order data and behavior data of cloud family members initially configured for the target business, the step further includes:

Acquire historical cloud members participating in the target business and determine the initial point of the target business;

Clustering the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point;

Based on the cluster center point, the FGCP model of the target business is constructed to obtain a preset clustering model.

Optionally, the step of clustering the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point includes:

Determine the clustering distance of each of the historical cloud members to the initial point based on the clustering algorithm;

Clustering the historical cloud members based on the clustering distance to determine a clustering cluster of each historical cloud member;

Obtaining historical monthly consumption data, historical relationship set values, historical product information, and historical attention data for the target business of each of the historical cloud members;

The cluster center point of each cluster cluster is determined based on the historical monthly consumption data, the historical relationship set value, the historical product information and the historical attention data.

Optionally, the product information includes at least product attributes and package quotas used by the cloud family members, the attention data includes at least browsing data and click data of the cloud family members on the target service, and the step of predicting required data of the target user from each of the cloud family members based on the order data and the behavior data analysis includes:

Analyzing the reference monthly consumption data of each member of the cloud family, the product attributes and the package amount from the order data;

The reference relationship set value of each member of the cloud family, the browsing data and the click data are analyzed from the behavior data.

Optionally, after the step of predicting target users of the target service from the members of the cloud family according to the clustering result and recommending the target service to the target users, the step further includes:

Obtain historical recommendation data and current recommendation data of the target business;

Analyzing the changes between the current recommendation data and the historical recommendation data based on the preset clustering model;

Determine a service recommendation strategy for recommending the target service again based on the change.

Optionally, the step of analyzing the change between the current recommendation data and the historical recommendation data based on the preset clustering model includes:

The current recommendation data is analyzed based on the historical recommendation data and the preset clustering model to determine changes in user participation, conversion rate, and order volume in the current recommendation data.

Optionally, after the step of obtaining the current recommendation data of the target service, the step further includes:

Review the recommended data to determine the current cloud users participating in the target business, as well as the target monthly consumption data, target relationship set value, target product information, and target attention data of each current cloud user;

The preset clustering model is updated and iterated based on the target monthly consumption data, the target relationship set value, the target product information, and the target attention data to obtain an optimized FGCP model;

The influence of the monthly consumption data, the relationship set value, the product information and the attention data on the recommendation effect is analyzed based on the current recommendation data.

In addition, to achieve the above-mentioned purpose, the present application also provides a business recommendation device, which includes:

A collection module, used to collect order data and behavior data of cloud family members initially configured for the target business;

An analysis module, configured to predict required data of a target user from each member of the cloud family based on the order data and the behavior data analysis, wherein the required data at least includes monthly consumption data, relationship set values, product information, and attention data for the target business of the member of the cloud family;

A clustering module, used to perform cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the concerned data as parameters;

A prediction module is used to predict target users of the target service from among the members of the cloud family according to the clustering result, and recommend the target service to the target users.

In addition, to achieve the above objectives, the present application also proposes a business recommendation device, which includes: a memory, a processor, and a business recommendation program stored in the memory and executable on the processor, wherein the business recommendation program is configured to implement the steps of the business recommendation method described above.

In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a service recommendation program is stored, and when the service recommendation program is executed by a processor, the steps of the service recommendation method described above are implemented.

The present application provides a service recommendation method, apparatus, device and storage medium. Compared with the prior art in which the positioning of target users is not accurate enough, resulting in a low conversion rate of target services, in the present application, order data and behavior data of cloud family members initially configured for the target service are collected; based on the order data and the behavior data analysis, the required data of the target user is predicted from each member of the cloud family, and the required data at least includes the monthly consumption data, relationship set values, product information and attention data of the cloud family members, and the target service; based on a preset clustering model and the required data, a clustering analysis is performed on each member of the cloud family to obtain a clustering result, and the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the attention data as parameters; according to the clustering result, the target user of the target service is predicted from the members of the cloud family, and the target service is recommended to the target user. That is, in the present application, the monthly consumption data, relationship set values, product information and attention data of the cloud family members are analyzed and summarized through the collected order data and behavior data, and then the preset clustering model is used to cluster the cloud family members based on the monthly consumption data, relationship set values, product information and attention data to obtain the clustering results, that is, the consumption level of the cloud family members is determined through the monthly consumption data, the potential user group that can be expanded through the cloud family members is determined through the relationship set value, the needs of the cloud family members are accurately determined through the product information, and the willingness of the users to participate in the target business is determined through the attention data, and then the business activities suitable for the cloud family members are accurately determined through the consumption level and needs of the cloud family members, and the conversion rate of recommending the business activities to the cloud family members is determined through the willingness degree and the potential user group, and the target users suitable for the target business and with high conversion rate are accurately predicted from the cloud family members according to the clustering results, and the target business activities are recommended to the target users, so as to achieve accurate positioning of the target users and improve the conversion rate of the target business recommendation.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a schematic diagram of a business recommendation device structure of a hardware operating environment involved in an embodiment of the present application;

FIG2 is a flow chart of a first embodiment of a service recommendation method of the present application;

FIG3 is a flow chart of a specific method of the service recommendation method of the present application;

FIG4 is a flow chart of a second embodiment of the service recommendation method of the present application;

FIG5 is a flow chart of a third embodiment of the service recommendation method of the present application;

FIG. 6 is a schematic diagram of the structural configuration of the service recommendation device of the present application.

The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings.

DETAILED DESCRIPTION

It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

Refer to Figure 1, which is a schematic diagram of the business recommendation device structure of the hardware operating environment involved in the embodiment of the present application.

As shown in FIG1 , the service recommendation device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

Those skilled in the art will appreciate that the structure shown in FIG. 1 does not constitute a limitation on the business recommendation device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a service recommendation program.

In the business recommendation device shown in Figure 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the business recommendation device of the present application can be set in the business recommendation device, and the business recommendation device calls the business recommendation program stored in the memory 1005 through the processor 1001, and executes the business recommendation method provided in the embodiment of the present application.

An embodiment of the present application provides a service recommendation method. Referring to FIG. 2 , FIG. 2 is a flow chart of a first embodiment of a service recommendation method of the present application.

It should be noted that the executor of this embodiment may be the business recommendation device, and the business recommendation device may be an electronic device such as a personal computer, a smart phone, a tablet computer, or other other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the business recommendation method of this application is explained by taking the business recommendation device as an example.

In this embodiment, the service recommendation method includes:

Step S10, collecting order data and behavior data of cloud family members initially configured for the target business.

Among them, the order data may include the service packages that the cloud family members have activated, the business activities they have participated in, and the monthly consumption records; the behavioral data may include the service packages and/or business activities that the cloud family members have clicked or browsed, as well as the data of service packages and/or business activities that have been inquired by phone or text message.

It should be noted that the initial configuration may be a cloud family member pre-configured for the target business. The cloud family member may be pre-configured through a big data mining and analysis engine with cloud family members who have participated in the target business, have participated in the target business, and have browsed the target business. By initially configuring cloud family members for the target business, a preliminary screening of cloud family members who may participate in the target business is performed, and the number of cloud family members that need to be predicted is reduced, thereby narrowing the prediction range and improving the prediction efficiency.

It should be noted that the order data and behavior data of the cloud family members can be collected by using a big data mining and analysis engine to mine the order data and behavior data of the cloud family members.

In a specific implementation, the order data and behavior data of the cloud family members may be collected by using a big data mining and analysis engine to mine the order data and behavior data of the cloud family members, wherein the big data mining and analysis engine may be created or debugged for the target business.

Step S20, predicting the required data of the target user from each member of the cloud family based on the order data and the behavior data analysis, wherein the required data at least includes the monthly consumption data, relationship set value, product information and attention data of the cloud family members to the target business.

Among them, the relationship set value can be the number of members who have established cloud family relationships with cloud family members. For example, cloud family member A has joined 3 cloud families, 3 people in cloud family a have cloud family relationships with cloud family member A, 4 people in cloud family b have cloud family relationships with cloud family member A, and 10 people in cloud family c have cloud family relationships with cloud family member A, then the relationship set value of cloud family member A is 17.

It should be noted that the monthly consumption data, relationship set values, product information and attention data of cloud family members are analyzed from the order data and behavior data. The consumption level of cloud family members can be analyzed through the monthly consumption data, the expandable potential user group can be analyzed through the relationship set value, the needs of cloud family members can be accurately analyzed through the product information, and the willingness of users to participate in the target business can be analyzed through the attention data. Then, the business activities suitable for each cloud family member can be accurately analyzed through the consumption level and needs of cloud family members, and the conversion rate of recommending the business activity to cloud family members can be analyzed through the willingness level and potential user group analysis.

In the specific implementation, the order data and behavior data are sent to the message queue of the analysis module. After in-depth analysis by the analysis module, the monthly consumption data of the cloud family members, the attribute information and quota information of the purchased services, the data of clicking or browsing the target business, and the relationship set value and other required data are obtained, so as to cluster the cloud family members through the required data and the clustering model.

Furthermore, the product information at least includes product attributes and package quotas used by the cloud family members, the attention data at least includes browsing data and click data of the cloud family members on the target service, and the step of predicting the required data of the target user from each of the cloud family members based on the order data and the behavior data analysis includes:

Step S21, analyzing the reference monthly consumption data, the product attributes and the package amount of each cloud family member from the order data;

Step S22, analyzing the reference relationship set value of each cloud family member, the browsing data and the click data from the behavior data.

The reference monthly consumption data can be understood as the consumption data of the cloud family members that need to be referenced for predicting the current target business; the reference relationship set value can be understood as the relationship set value of each cloud family member that needs to be referenced for predicting the current target business.

It should be noted that by analyzing the reference monthly consumption data, product attributes and package amount of business activities of the cloud family members from the order data, the basic business needs of the cloud family members can be determined based on the product attributes, and the proportion of the package amount for business activities in the monthly consumption that the cloud family members can accept can be determined based on the reference monthly consumption data and the package amount. Based on the basic needs and the proportion of the package amount in the monthly consumption, the business activities that are suitable to be recommended to the cloud family members can be accurately determined.

It should be noted that by analyzing the reference relationship set values, browsing data and click data of cloud family members from the behavioral data, the business activities that cloud family members are willing to participate in can be determined based on the browsing data and click data, and the relevant data of the cloud family circle related to the cloud family members can be obtained based on the reference relationship set value, which makes it convenient to select businesses that are suitable for cloud family members and the cloud family circle, and that cloud family members are more willing to participate in, from business activities that are suitable for recommending to cloud family members.

Step S30, performing cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the attention data as parameters.

Among them, the preset clustering model can be an FGCP model, and the specific composition of the FGCP model can be F: cloud family member relationship group, a user group formed based on the analysis of consumption behavior and consumption data of cloud family members; G: a pan-family relationship group established based on the association between multiple cloud family circles; C: a user group established based on the family business attributes and user characteristic preferences handled by cloud family member users; P: a user group established based on the browsing and clicking behavior of cloud family member users.

It should be noted that the clustering algorithm includes an algorithm formula with monthly consumption data, relationship set value, product information and attention data as parameters. Since the result obtained by the formula has the characteristic of accuracy, the algorithm formula can accurately determine the target user. Among them, the algorithm formula may include:

Among them, Y _r is the final value of the distance from each cloud family member to the center point after multiple iterative calculations; r is the number of the target business; fn is an iterative calculation function, which iteratively executes the distance from the FGCP data of each cloud family member to the center point until there is no change; F _n is the monthly consumption data of each cloud family member; G _n is the relationship set value of each cloud family circle; C _n is the product attributes and package quota of the cloud family member users; P _n is the browsing and click data of the cloud family member users; is the distance from each cloud family member to the initial center point, and the initial center point is the FGCP model point of each target business.

in, It is calculated using the distance calculation formula from the cloud family members to the initial center point. The distance calculation formula is:

Among them, FLr(Fr, Gr, Cr, Pr) (1<=r<=m) is the initial point of each FGCP model.

It should be noted that by using the preset clustering model to perform cluster analysis on each cloud family member based on monthly consumption data, relationship set value, product information and attention data, the accuracy of data-driven business recommendations can be improved, the enthusiasm of cloud family members to participate in the target business can be fully mobilized, the scope of business recommendations can be expanded in a more precise way of reaching, the target users who may participate in the target business can be accurately located, the conversion rate of the target business can be improved, and the development of cloud family business can be promoted.

In the specific implementation, an FGCP model is established, and the FGCP model is used as a model tool for refined operations of target users. Each FGCP model point FLr (Fr, Gr, Cr, Pr) is used as the initial center point; the distance from each cloud family member to the initial center point is calculated, and each cloud family member is assigned to the nearest center point as a cluster; the above two steps are iterated until the calculated distance value from the FGCP data of the cloud family member to the center point no longer changes; the minimum value calculated for each cloud family member is then clustered and grouped, and the center point of each cluster is calculated; the distance between the initial center point and the center point of the cluster cluster that no longer changes is calculated to obtain the clustering result, so as to predict the target user through the clustering result.

Step S40: predicting target users of the target service from among the cloud family members according to the clustering result, and recommending the target service to the target users.

It should be noted that the cluster grouping with the minimum distance between the initial center point and the center point of the cluster cluster that no longer changes is selected from the clustering results to determine the business activities suitable for each cloud family member, avoid blind recommendations to cloud family members, and take all users in the cluster grouping corresponding to the target business as target users to accurately capture high-quality target user groups and improve the conversion rate of target business recommendations.

In the specific implementation, the cluster grouping with the minimum distance between the initial center point and the center point of the cluster cluster that no longer changes is selected from the clustering results, and the target cluster grouping corresponding to the target business activity is selected from the cluster grouping, all users in the target cluster grouping are taken as target users, and the target business is recommended to all target users corresponding to the target business.

In a specific implementation, refer to FIG3 , which is a flowchart of a specific method of the service recommendation method of the present application.

1. Mining of cloud family member order data;

Create a big data mining and analysis engine, collect order data and behavior data of cloud family members through data mining operations, send them to the message queue for in-depth analysis, obtain relevant data such as browsing, consumption, clicks, cloud family circles, etc. of cloud family members, and save them in ElasticSearch (open source full-text search engine), and summarize them into key data items.

2. FGCP model update;

Based on the FGCP model algorithm, an accurate recommendation model for cloud family members is built to screen out target user groups with high value and high conversion rates. The target user group data can be updated in real time through model operations.

3. Implement accurate recommendations based on the FGCP model;

Based on the FGCP model configuration, a precise recommendation algorithm is used. When members of the cloud family participate in business activities, the platform selects the most matching target user group through algorithm analysis based on the Golden Flower model, which greatly improves the utilization rate of marketing resources. At the same time, it also effectively improves the enthusiasm and satisfaction of members of the cloud family in participating in business activities.

4.Analysis of marketing recommendation effect;

Further compare the historical data of business activities with the performance data of current activities, and use the FGCP model to analyze and calculate the changes in key indicators, such as the increase in user participation, the improvement in conversion rate, the increase in order volume, etc., and use the key indicator data related to the marketing activities as the main basis for subsequent marketing strategy decisions.

The present embodiment provides a service recommendation method. Compared with the prior art in which the positioning of the target user is not accurate enough, resulting in a low conversion rate of the target service, in the present application, the order data and behavior data of the cloud family members initially configured for the target service are collected; based on the analysis of the order data and the behavior data, the required data of the target user is predicted from each member of the cloud family, and the required data at least includes the monthly consumption data, relationship set value, product information and attention data of the cloud family members, and the target service; based on a preset clustering model and the required data, a clustering analysis is performed on each member of the cloud family to obtain a clustering result, and the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the attention data as parameters; according to the clustering result, the target user of the target service is predicted from the cloud family members, and the target service is recommended to the target user. That is, in the present application, the monthly consumption data, relationship set values, product information and attention data of the cloud family members are analyzed and summarized through the collected order data and behavior data, and then the preset clustering model is used to cluster the cloud family members based on the monthly consumption data, relationship set values, product information and attention data to obtain the clustering results, that is, the consumption level of the cloud family members is determined through the monthly consumption data, the potential user group that can be expanded through the cloud family members is determined through the relationship set value, the needs of the cloud family members are accurately determined through the product information, and the willingness of the users to participate in the target business is determined through the attention data, and then the business activities suitable for the cloud family members are accurately determined through the consumption level and needs of the cloud family members, and the conversion rate of recommending the business activities to the cloud family members is determined through the willingness degree and the potential user group, and the target users suitable for the target business and with high conversion rate are accurately predicted from the cloud family members according to the clustering results, and the target business activities are recommended to the target users, so as to achieve accurate positioning of the target users and improve the conversion rate of the target business recommendation.

Refer to FIG4 , which is a flow chart of a second embodiment of the service recommendation method of the present application.

Based on the above embodiment, in this embodiment, in order to effectively expand the coverage of the cloud family service and improve the activity and satisfaction of the members of the cloud family, before step S10, the following is also included:

Step S01, obtaining historical cloud members participating in the target business and determining the initial point of the target business;

Step S02, clustering the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point;

Step S03: constructing the FGCP model of the target business based on the cluster center point to obtain a preset cluster model.

The initial point of the target service may be the center point of each historical cloud member after the first clustering; the historical cloud member may be a member of a cloud family that has participated in or has participated in the target service.

It should be noted that the clustering algorithm and the initial point are used to cluster the historical cloud members until the monthly consumption data, relationship set values, product information and attention data of the cloud family members no longer change from the distance value to the initial point, and then the cluster center point is determined to improve the accuracy of clustering analysis of cloud family members using the FGCP model. According to the cluster center point, the FGCP model of the target business is constructed, where the FGCP model is a preset clustering model created by a clustering algorithm with monthly consumption data, relationship set values, product information and attention data as parameters. The FGCP model can be used to screen out high-value, high-conversion target user groups to cover a richer range of activity types, and to improve the convenience of clustering cloud family members.

In a specific implementation, historical cloud members who participated in the target business within a certain period of time can be obtained from historical monthly summary files or historical business logs, and historical order data and historical behavior data of historical cloud members can be obtained. The historical cloud members are clustered for the first time through the historical order data and historical behavior data, and the initial center point of the historical cloud members is determined. The initial center point is used as the initial point of the target business, and the clustering algorithm and the initial point are used to iterate the clustering of the historical cloud members until the distance from the FGCP data of the cloud family members to the initial point no longer changes. The cluster center point of the target business is determined, and a clustering model containing the relationship between monthly consumption data, relationship set values, product information, and attention data is constructed using the cluster center point and the clustering algorithm.

Optionally, in order to enable the preset clustering model to accurately predict the target user according to the monthly consumption data, the relationship set value, the product information and the attention data, step S02 includes:

Step S021, determining the clustering distance from each of the historical cloud members to the initial point based on the clustering algorithm;

Step S022, clustering the historical cloud members based on the clustering distance to determine a clustering cluster of each historical cloud member;

Step S023, obtaining historical monthly consumption data, historical relationship set values, historical product information, and historical attention data for the target business of each of the historical cloud members;

Step S024: determining the cluster center point of each cluster based on the historical monthly consumption data, the historical relationship set value, the historical product information and the historical attention data.

It should be noted that based on historical monthly consumption data, historical relationship set values, historical product information, and historical attention data, the cluster center points of each cluster cluster are determined from multiple angles related to cloud family members to build a preset clustering model that predicts target users from multiple angles. The angles are interrelated, so that the created preset clustering model can more accurately predict target users.

In the specific implementation, according to the clustering algorithm, The clustering distance from each historical cloud member to the initial point is calculated using the formula, and the historical cloud members are clustered according to the clustering distance to determine the clustering clusters of each historical cloud member. The clustering of the historical cloud members is iterated until the clustering distance is stable, and then the clustering center point of each cluster is determined.

Refer to FIG5 , which is a flowchart of a third embodiment of the service recommendation method of the present application.

Based on the above embodiment, in this embodiment, in order to make the conversion rate of this time exceed when recommending the target business again, and realize the full life cycle management of "attracting new members-active-retention-conversion" of cloud family cloud members, after step S40, it also includes:

Step S1, obtaining historical recommendation data and current recommendation data of the target business;

Step S2, analyzing the changes between the current recommendation data and the historical recommendation data based on the preset clustering model;

Step S3: Determine a service recommendation strategy for recommending the target service again based on the change.

The recommendation data may be data related to the result of recommending the target business to the members of the cloud family, such as user participation, conversion rate, order volume, user feedback, and user needs.

It should be noted that the changes between the current recommendation data and the historical recommendation data are analyzed through the preset clustering model, so as to adjust the business recommendation strategy in a targeted manner according to the changes, so as to improve the conversion rate of the target business recommended next time. The preset clustering model analysis can make the changes obtained more accurate, and thus adjust the business recommendation strategy more accurately.

It should be noted that the business recommendation strategy will be adjusted according to the changes between the current recommendation data and the historical recommendation data, so as to track the target business recommendation effect analysis and perform automatic intervention throughout the process. The key indicators will flow into the Family Circle FGCP model again for operational decision-making, thereby realizing a closed loop of marketing private domain traffic, continuously promoting personalized and precise marketing for the cloud home user group, fully improving the utilization rate of marketing resources, and ultimately achieving improved customer satisfaction and effectively improving user perception.

In the specific implementation, the historical recommendation data and the current recommendation data of the target business are obtained, and the changes between the current recommendation data and the historical recommendation data are analyzed using a preset clustering model. The business recommendation strategy is reasonably adjusted according to the changes to obtain a business recommendation strategy that meets the needs of the target business again.

Furthermore, the step of analyzing the change between the current recommendation data and the historical recommendation data based on the preset clustering model includes:

Step S201, analyzing the current recommendation data based on the historical recommendation data and the preset clustering model to determine changes in user participation, conversion rate, and order volume in the current recommendation data.

In the specific implementation, the historical recommendation data is compared with the current recommendation data to determine the changes in user participation, conversion rate and order volume, so as to determine the business recommendation strategy such as the recommendation strength and recommendation method for re-recommending the target business based on the user participation, conversion rate and order volume.

Optionally, after the step of obtaining the current recommendation data of the target service, the step further includes:

Step Sa1, reviewing the current recommendation data to determine the current cloud users participating in the target business, as well as the target monthly consumption data, target relationship set value, target product information, and target attention data of each current cloud user;

Step Sa2, updating and iterating the preset clustering model based on the target monthly consumption data, the target relationship set value, the target product information and the target attention data to obtain an optimized FGCP model;

Step Sa3, analyzing the influence of the monthly consumption data, the relationship set value, the product information and the attention data on the recommendation effect based on the current recommendation data.

It should be noted that in order to enable the preset clustering model to always accurately locate the target users from the cloud home users, the preset clustering model will determine the target monthly consumption data, target relationship set value, target product information and target attention data based on the recommendation data each time it obtains the recommendation data, and update and iterate the cluster center points in the preset clustering model based on these data to ensure that the distance between the cluster center points and the monthly consumption data, relationship set value, product information and target attention data always remains stable.

In the specific implementation, the current cloud users of the parameter target users, as well as the target monthly consumption data, target relationship set value, target product information and target attention data of each current cloud user are analyzed according to the recommendation data. Based on these data, the preset clustering model is iterated more finely according to the process of iterating the training preset clustering model to obtain the optimized FGCP model.

The present application also provides a service recommendation device. Referring to FIG6 , the service recommendation device includes:

Collection module 601, used to collect order data and behavior data of cloud family members initially configured for the target business;

A data analysis module 602 is used to predict the required data of the target user from each of the cloud family members based on the order data and the behavior data analysis, wherein the required data at least includes the monthly consumption data, relationship set value, product information and attention data of the cloud family members to the target business;

A clustering module 603 is used to perform cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the concerned data as parameters;

The prediction module 604 is used to predict the target users of the target service from the members of the cloud family according to the clustering result, and recommend the target service to the target users.

Optionally, the acquisition module 601 is also used to obtain historical cloud members participating in the target business and determine the initial point of the target business; cluster the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point; based on the cluster center point, construct the FGCP model of the target business to obtain a preset clustering model.

Optionally, the acquisition module 601 is also used to determine the clustering distance of each of the historical cloud members to the initial point based on the clustering algorithm; cluster the historical cloud members based on the clustering distance to determine the clustering clusters of each of the historical cloud members; obtain the historical monthly consumption data, historical relationship set value, historical product information and historical attention data of each of the historical cloud members for the target business; determine the cluster center point of each of the clustering clusters based on the historical monthly consumption data, the historical relationship set value, the historical product information and the historical attention data.

Optionally, the product information includes at least product attributes and package quotas used by the cloud family members, and the attention data includes at least browsing data and click data of the cloud family members on the target service;

The collection module 601 is also used to analyze the reference monthly consumption data, the product attributes and the package amount of each cloud family member from the order data; and analyze the reference relationship set value, the browsing data and the click data of each cloud family member from the behavior data.

Optionally, the service recommendation device further includes:

An acquisition module 605 is used to acquire historical recommendation data and current recommendation data of the target service;

The recommendation analysis module 606 is used to analyze the changes between the current recommendation data and the historical recommendation data based on the preset clustering model;

The recommendation strategy formulation module 607 is used to determine the service recommendation strategy required to recommend the target service again based on the change situation.

Optionally, the recommendation analysis module 606 is further used to analyze the current recommendation data based on the historical recommendation data and the preset clustering model to determine changes in user participation, conversion rate and order volume in the current recommendation data.

Optionally, the recommendation analysis module 606 is also used to review the current recommendation data, determine the current cloud users participating in the target business, and the target monthly consumption data, target relationship set value, target product information and target attention data of each current cloud user; update and iterate the preset clustering model based on the target monthly consumption data, the target relationship set value, the target product information and the target attention data to obtain an optimized FGCP model; analyze the influence of the monthly consumption data, the relationship set value, the product information and the attention data on the recommendation effect based on the current recommendation data.

The specific implementation of the service recommendation device of the present application is basically the same as the embodiments of the service recommendation method described above, and will not be described in detail here.

An embodiment of the present application provides a storage medium, and the storage medium stores one or more programs, and the one or more programs can also be executed by one or more processors to implement the steps of any of the above-mentioned business recommendation methods.

The specific implementation of the storage medium of the present application is basically the same as the embodiments of the above-mentioned service recommendation method, and will not be repeated here.

It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes an etc." does not exclude the presence of other identical elements in the process, method, article or device including the element.

The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of each embodiment of the present application.

The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent mechanism or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims (10)

1. A service recommendation method, characterized in that the service recommendation method comprises: Collect order data and behavior data of the cloud family members initially configured for the target business; Predicting required data of the target user from each member of the cloud family based on the order data and the behavior data analysis, wherein the required data at least includes monthly consumption data, relationship set value, product information and attention data of the cloud family members to the target business; Performing cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the concerned data as parameters; The target users of the target service are predicted from the members of the cloud family according to the clustering result, and the target service is recommended to the target users. 2. The service recommendation method according to claim 1, characterized in that before the step of collecting order data and behavior data of cloud family members initially configured for the target service, it also includes: Acquire historical cloud members participating in the target business and determine the initial point of the target business; Clustering the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point; Based on the cluster center point, the FGCP model of the target business is constructed to obtain a preset clustering model. 3. The service recommendation method according to claim 2, wherein the step of clustering the historical cloud members based on the clustering algorithm and the initial point to determine the cluster center point comprises: Determine the clustering distance of each of the historical cloud members to the initial point based on the clustering algorithm; Clustering the historical cloud members based on the clustering distance to determine a clustering cluster of each historical cloud member; Obtaining historical monthly consumption data, historical relationship set values, historical product information, and historical attention data for the target business of each of the historical cloud members; The cluster center point of each cluster cluster is determined based on the historical monthly consumption data, the historical relationship set value, the historical product information and the historical attention data. 4. The service recommendation method according to claim 1, wherein the product information at least includes product attributes and package quotas used by the cloud family members, the attention data at least includes browsing data and click data of the cloud family members on the target service, and the step of predicting the required data of the target user from each of the cloud family members based on the order data and the behavior data analysis comprises: Analyzing the reference monthly consumption data of each member of the cloud family, the product attributes and the package amount from the order data; The reference relationship set value of each member of the cloud family, the browsing data and the click data are analyzed from the behavior data. 5. The service recommendation method according to any one of claims 1 to 4, characterized in that after the step of predicting the target user of the target service from the cloud family members according to the clustering result and recommending the target service to the target user, it further comprises: Obtain historical recommendation data and current recommendation data of the target business; Analyzing the changes between the current recommendation data and the historical recommendation data based on the preset clustering model; Determine a service recommendation strategy for recommending the target service again based on the change. 6. The service recommendation method according to claim 5, characterized in that the step of analyzing the change between the current recommendation data and the historical recommendation data based on the preset clustering model comprises: The current recommendation data is analyzed based on the historical recommendation data and the preset clustering model to determine changes in user participation, conversion rate, and order volume in the current recommendation data. 7. The service recommendation method according to claim 5, characterized in that after the step of obtaining the current recommendation data of the target service, it further comprises: Review the recommended data to determine the current cloud users participating in the target business, as well as the target monthly consumption data, target relationship set value, target product information, and target attention data of each current cloud user; The preset clustering model is updated and iterated based on the target monthly consumption data, the target relationship set value, the target product information, and the target attention data to obtain an optimized FGCP model; The influence of the monthly consumption data, the relationship set value, the product information and the attention data on the recommendation effect is analyzed based on the current recommendation data. 8. A service recommendation device, characterized in that the service recommendation device comprises: A collection module, used to collect order data and behavior data of cloud family members initially configured for the target business; An analysis module, configured to predict required data of a target user from each member of the cloud family based on the order data and the behavior data analysis, wherein the required data at least includes monthly consumption data, relationship set values, product information, and attention data for the target business of the member of the cloud family; A clustering module, used to perform cluster analysis on each of the cloud family members based on a preset clustering model and the required data to obtain a clustering result, wherein the preset clustering model includes a clustering algorithm with the monthly consumption data, the relationship set value, the product information and the concerned data as parameters; A prediction module is used to predict target users of the target service from among the members of the cloud family according to the clustering result, and recommend the target service to the target users. 9. A business recommendation device, characterized in that the business recommendation device comprises: a memory, a processor, and a business recommendation program stored in the memory and executable on the processor, wherein the business recommendation program is configured to implement the steps of the business recommendation method as described in any one of claims 1 to 7. 10. A storage medium, characterized in that a program for implementing a service recommendation method is stored on the storage medium, and the program for implementing the service recommendation method is executed by a processor to implement the steps of the service recommendation method as described in any one of claims 1 to 7.