CN117436963A

CN117436963A - Telecommunication service recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN117436963A
Application number: CN202311344677.2A
Authority: CN
Inventors: 李豆豆; 李亚旭
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2023-10-17
Filing date: 2023-10-17
Publication date: 2024-01-23

Abstract

The embodiment of the application discloses a telecommunication service recommending method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining the association degree between each service product to be recommended and each recommendation policy link according to the historical service order record, wherein the recommendation policy links are links formed by a plurality of recommendation policies and are generated based on the association relation between the service products corresponding to the recommendation policies; determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree; and determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation strategy link. The embodiment of the application realizes that the telecommunication service products are recommended in the link form, so that the recommendation efficiency can be improved, and the recommendation is performed by combining the historical service order record and the target user data, so that the accuracy of the recommendation result can be improved.

Description

Telecommunication service recommendation method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of internet, in particular to a telecommunication service recommending method, a device, electronic equipment and a storage medium.

Background

In the prior art, when the telecommunication service recommendation is performed, customer service personnel can perform single service recommendation based on experience or user intention records; the method can also be used for semi-automatic recommendation, single service recommendation is carried out on the basis of the explicit requirements and feedback of the user, and enough data cannot be obtained, so that the description of the user preference is inaccurate and the recommendation effect is not high; full-automatic recommendation can be performed, single-service recommendation is performed to users by using user features of an operator system, but users cannot be more comprehensively described based on the user features of a single system, deeper features cannot be mined from user data, and recommendation accuracy is low.

Therefore, in the prior art, various recommendation modes are all to recommend single service, a large amount of manpower resources and time are required to be consumed, the recommendation efficiency is low, and the recommendation accuracy is low.

Disclosure of Invention

The embodiment of the application provides a telecommunication service recommending method, a device, electronic equipment and a storage medium, which are beneficial to improving recommending efficiency and recommending accuracy.

In order to solve the above problem, in a first aspect, an embodiment of the present application provides a telecommunications service recommendation method, including:

Determining the association degree between each service product to be recommended and each recommendation policy link according to the historical service order record, wherein the recommendation policy links are links formed by a plurality of recommendation policies and are generated based on the association relation between the service products corresponding to the recommendation policies;

determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree;

and determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation strategy link.

In a second aspect, an embodiment of the present application provides a telecommunications service recommendation device, including:

the association degree determining module is used for determining association degree between each service product to be recommended and each recommendation policy link according to the historical service ordering record, wherein the recommendation policy links are links formed by a plurality of recommendation policies and are generated based on association relations between service products corresponding to the recommendation policies;

the preference degree determining module is used for determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree;

And the recommendation result determining module is used for determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation strategy link.

In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the computer program is executed by the processor to implement the telecommunication service recommendation method described in the embodiment of the present application.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs a telecommunications service recommendation method as disclosed in embodiments of the present application.

According to the telecommunication service recommending method, device, electronic equipment and storage medium, the relevancy between each service product to be recommended and each recommending strategy link is determined according to the historical service ordering records, the preference of the target user for the service product to be recommended is determined according to the target user data and the relevancy corresponding to the target user identification, the link of the service product to be recommended corresponding to the target user identification is determined according to the preference and each recommending strategy link, the telecommunication service product is recommended in the link mode instead of single service, so that a user can conveniently select the service product, time wasted by the user for actively knowing other service products after selecting one service product can be saved, recommending efficiency is improved, and the accuracy of a recommending result can be improved by combining the historical service ordering records and the target user data.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a telecommunication service recommendation method provided in an embodiment of the present application;

FIG. 2 is an example diagram of associations of business products in an embodiment of the present application;

FIG. 3 is a business product association diagram in an embodiment of the present application;

FIG. 4 is a schematic diagram of a scattered swim lane diagram of a historical business order record in an embodiment of the present application;

FIG. 5 is a schematic flow chart of a telecommunications service recommendation in an embodiment of the present application;

fig. 6 is a flowchart of a telecommunication service recommendation method provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a telecommunications service recommendation device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

Fig. 1 is a flowchart of a telecommunication service recommendation method provided in an embodiment of the present application, where a telecommunication service refers to a service provided by a telecommunication network to the public. The telecommunication service is classified into basic telecommunication service and value-added telecommunication service according to the service type; the network providing services can be classified into a fixed telecommunication service, a wireless telecommunication service, and the like. As shown in fig. 1, the method includes: steps 110 to 130.

Step 110, determining the association degree between each service product to be recommended and each recommended policy link according to the historical service order record, wherein the recommended policy links are links formed by a plurality of recommended policies and are generated based on the association relation between the service products corresponding to the recommended policies.

The historical service ordering record is the ordered historical record of the service product and comprises information such as user identification, the service product, ordering time and the like. The recommendation policy is a recommendation rule of a business product (i.e. how to recommend the business product), and one recommendation policy may correspond to a plurality of business products. The association relation between the business products is determined based on the business products ordered by the user, if the user orders a plurality of business products in a short time, the business products are determined to have the association relation, and the business products correspond to the recommendation strategies, so that a recommendation strategy link can be obtained. The recommended policy links are pre-stored in a recommended policy database, and each recommended policy link can be obtained from the recommended policy database when the telecommunication service recommendation is performed.

And analyzing the historical service order records to determine the association degree between each service product to be recommended and each recommendation policy link. The association degree between the to-be-recommended service product and the recommendation policy link reflects the association degree between the to-be-recommended service product and the recommendation policy link, and the higher the association degree is, the greater the possibility that the to-be-recommended service product and the service product in the recommendation policy link are recommended together is, and the lower the association degree is, the lower the possibility that the to-be-recommended service product and the service product in the recommendation policy link are recommended together is. For example, dynamic planning may be adopted, according to a threshold of the association degree, ordering links from one business product to each business product are carded, according to machine learning analysis historical business ordering records, optimal peripheral business products of the business products are analyzed, a chessboard divide-and-conquer algorithm is adopted to plan the peripheral business products, and the association degree of the business products to be recommended and more business products in the recommendation policy links is obtained by automatically learning the coefficient of the association degree of each recommendation policy in the business products to be recommended and the recommendation policy links.

In one embodiment of the present application, the determining, according to the historical service subscription record, the association degree between each service product to be recommended and each recommendation policy link includes: for each service product to be recommended and each recommended strategy link, determining a first weight of the service product to be recommended in each recommended strategy in the recommended strategy links according to the historical service order record, and determining the fitness of each recommended strategy to the recommended strategy links; and determining the association degree between the service product to be recommended and the policy link to be recommended according to the first weight and the adaptation degree.

And respectively calculating the association degree between each service product to be recommended and each policy link to be recommended. And analyzing the historical service order records aiming at the currently calculated service products to be recommended and the recommendation policy links, and determining the first weight of the service products to be recommended in each recommendation policy in the recommendation policy links. For example, the number of links with the service product to be recommended as a starting point and the service product under each policy link in the recommended policy links as an ending point may be obtained from a history service subscription record, the total number of all links with the service product under each policy link in the recommended policy links as an ending point may be obtained from the history service subscription record, and the ratio of the number to the total number may be determined as the first weight.

The historical service order records can be learned based on a machine learning mode, the fitness of each recommendation strategy in the recommendation strategy link to the recommendation strategy link is determined, the fitness represents the fitness score corresponding to a route taking a service product corresponding to the recommendation strategy as a starting point and a service product corresponding to a termination recommendation strategy of the recommendation strategy link as an ending point, and the relevance score of the service product corresponding to the recommendation strategy when the service product corresponding to the termination recommendation strategy is associated is represented. The machine learning method may, for example, adopt a supervised learning method, and a training sample is constructed based on historical data, where the training sample includes sample data and an adaptability label, and the sample data includes service product data, policy data, link data, and the like of each recommendation policy in the recommendation policy link, and the adaptability label is a adaptability label of one recommendation policy in the recommendation policy link to the recommendation policy link.

For each recommendation strategy in the recommendation strategy link, determining the product of the first weight corresponding to the recommendation strategy and the adaptability corresponding to the recommendation strategy, and adding the products obtained by each recommendation strategy in the recommendation strategy link to obtain the association degree between the service product to be recommended and the recommendation strategy link. That is, according to the first weight and the fitness, determining the association degree between the service product to be recommended and the recommended policy link according to the following formula:

wherein A (b, S) represents the association degree between the service product b to be recommended and the recommended policy link S, W (b, i) represents the first weight of the service product b to be recommended to the ith recommended policy in the recommended policy links (the recommended policy before the recommended policy is terminated in the recommended policy link S), and S (i, S) represents the adaptability of the ith recommended policy in the recommended policy links to the recommended policy link S.

The method comprises the steps of processing each to-be-recommended service product and each recommendation policy link respectively, determining a first weight of the to-be-recommended service product in each recommendation policy and the fitness of each recommendation policy to the recommendation policy link based on a historical service order record, and further determining the association degree between the to-be-recommended service product and the to-be-recommended policy link based on the first weight and the fitness, so that more accurate association degree can be obtained, and further, the accuracy of telecommunication service recommendation can be improved.

The business products have a certain relation, some main business products have peripheral business products, the main business products and the peripheral business products form a tree diagram, and the relation between different business products can be determined based on the history business ordering record. Fig. 2 is an example diagram of association of business products in the embodiment of the present application, as shown in fig. 2, a tree diagram is formed by a product a, a product a1, a product a2, a product a3, and a product a4, where the product a is a main business product, and the product a1, the product a2, the product a3, and the product a4 are peripheral business products; the product B, the product B1, the product B2 and the product B3 form a tree diagram, wherein the product B is a main business product, and the product B1, the product B2 and the product B3 are peripheral business products; the product F, the product F1, the product F2, the product F3 and the product F4 form a tree diagram, wherein the product F is a main business product, and the product F1, the product F2, the product F3 and the product F4 are peripheral business products. As shown in fig. 2, a certain association relationship exists among a product a, a product B and a product F, corresponding recommendation strategies respectively form recommendation strategy links according to the association relationship, when the product F is used as a service product to be recommended, the association degree between the product a and the recommendation strategy links is calculated, the association degree of the link of the product F- > product F2- > product a3- > product B2 is the maximum after calculation, and the service product links with the association degree can be obtained after the same calculation, as shown in the service product association diagram shown in fig. 3.

And 120, determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree.

The target user data is user data collected based on various software and hardware resources in the cloud environment, and comprises user data in a plurality of systems, such as a daily service system, a charging system, a service operation system, a website, a device base station and other data of software and hardware environment resources related to the user, and the user data in the plurality of systems are integrated.

In the process of recommending telecommunication services, the recommendation can be performed to a single user or to a user group. When a recommendation is made to a single user, the target user identifier is an identifier of a target user, and the target user data is user data of the target user, including basic data, historical behavior data and the like. When recommending to a user group, the target user identification is the identification of the user group and comprises the identification of all users in the user group, and the target user data comprises the user data of all users in the user group and comprises common information of each group, historical behavior data of each user in the group and the like.

And determining the preference condition of the target user on the service product to be recommended based on the target user data and the association degree between the service product to be recommended and each recommendation policy link, and obtaining the preference degree of the target user on the service product to be recommended.

In an embodiment of the present application, the determining, according to the target user data corresponding to the target user identifier and the association degree, the preference degree of the target user for the service product to be recommended includes: determining, for each recommended policy link, a second weight of the target user identifier to each recommended policy in the recommended policy link according to the target user data; and determining the preference degree of the target user for the service product to be recommended according to the association degree and the second weight.

Each recommendation policy link is respectively analyzed, target user data is analyzed aiming at the current recommendation policy link, and a second weight of each recommendation policy in the recommendation policy link by the target user identification is determined, wherein the second weight is the influence of attributes such as preference and specialty on the recommendation policy, which are corresponding to the target user identification, of the target user, and is expressed as the preference degree of the target user on the service products under the recommendation policy and is also equivalent to the preference weight value of the target user on the recommendation policy. For example, the number of behaviors of the target user corresponding to the target user identifier for browsing and/or subscribing the service product under one recommendation policy in the recommendation policy link and the total number of behaviors of the target user corresponding to the target user identifier for browsing and/or subscribing may be determined, and the ratio of the number of behaviors corresponding to one recommendation policy to the total number of behaviors is determined as the second weight of the target user identifier to the recommendation policy in the recommendation policy link.

For a recommended policy link, determining the product of the association degree and the second weight of each recommended policy respectively, summing the products obtained by the recommended policies in the recommended policy link to obtain the total association degree of the recommended policy link, determining the sum of the second weights of the recommended policies in the recommended policy link as the weight sum, and determining the quotient of dividing the total association degree by the weight sum as the preference degree of a target user to the recommended service product. That is, according to the association degree and the second weight, determining the preference degree of the target user to the recommended service product according to the following formula:

wherein R (u, b) represents the preference degree of the target user u to the recommended service product b, A (b, s) represents the association degree between the recommended service product b and the recommended policy link s, and W (u, i) represents the second weight of the target user u to the ith recommended policy in the recommended policy link.

The second weight of the target user identification to each recommendation strategy can be accurately determined according to the target user data, and the preference of the target user to the recommended service products can be obtained based on the association degree and the second weight, and the preference can accurately reflect the preference condition of the target user to the recommended service products, so that the recommendation accuracy can be improved.

And step 130, determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation policy link.

Based on the preference degree of the target user to the recommended service products, a preset number of the service products to be recommended can be selected according to the order of the preference degree from large to small, the preset number of the service products to be recommended can be used as a final recommendation result, and the service product links to be recommended corresponding to the target user identification can be determined based on the preset number of the service products to be recommended and the recommendation policy links, and the service product links to be recommended are used as the final recommendation result. If the selected preset number of service products to be recommended includes service products under each recommendation strategy in one or more recommendation strategy links, the service products to be recommended under the recommendation strategies can be formed into links according to the sequence of each recommendation strategy in the recommendation strategy links, and the service product links to be recommended are obtained. And obtaining the service corresponding to each recommended service product in the service product link to be recommended, and taking the service and the service product link to be recommended together as a final recommendation result.

After determining the final recommendation result, pushing the recommendation result (the preset number of to-be-recommended service products and/or to-be-recommended service product links) to the user terminal of the target user. The recommendation mode may include one or more of telephone recommendation, mailbox recommendation, public number recommendation, applet recommendation, internet mailbox recommendation, and short message recommendation.

The recommendation result is mainly based on the service product to be recommended with the highest preference, other service products to be recommended with low preference are auxiliary, and the recommendation result can also contain a strongly-associated service product link to be recommended and service chain information corresponding to a preset number of service products to be recommended. The recommending effect of the telecommunication service product can enable the target user to have service subscription options, and enable service to be clear and processed. The recommendation sequence of the service products can automatically carry out alternate priority ordering according to the proportion of the adopted quantity of the service products, the service products adopted by the target users can also be tracked and automatically arranged, and finally, a friendly, comprehensive and high-quality brand-new service recommendation scheme under the service adding service mode is formed.

According to the telecommunication service recommending method, the association degree between each service product to be recommended and each recommending strategy link is determined according to the historical service ordering records, the preference degree of the target user for the service product to be recommended is determined according to the target user data and the association degree corresponding to the target user identification, the service product links to be recommended corresponding to the target user identification are determined according to the preference degree and each recommending strategy link, the telecommunication service product is recommended in the form of the links instead of single service, the service product selection is facilitated for the user, the time wasted by the user to know other service products actively after selecting one service product can be saved, and recommending efficiency is improved.

On the basis of the technical scheme, before the association degree between each service product to be recommended and each recommendation policy link is determined according to the historical service subscription record, the method further comprises the following steps: according to the historical service order record, determining the association relation among a plurality of service products, and generating recommendation strategy links among recommendation strategies corresponding to the service products respectively based on the association relation; and storing the recommended strategy link into a recommended strategy database.

Subdividing all the telecommunication services, and then collecting and sorting the data of the telecommunication services; searching and correcting the data after finishing to obtain accurate business characteristics; and determining service demand characteristics according to the service characteristics, and determining recommendation strategies corresponding to the service products based on the service demand characteristics. All telecommunication services are subdivided, the association relation between service products can be obtained, some service products are main service products, other service products can be associated with the periphery of the main service products, the main service products are called periphery service products, recommended strategies corresponding to the main service products and the periphery service products can be the same, and a tree diagram corresponding to the main service products and the periphery service products can be generated based on the association relation between the main service products and the periphery service products.

Analyzing the historical service order records, determining that a plurality of service products ordered by the same user have an association relationship, generating recommended strategy links among recommended strategies corresponding to the service products respectively based on the association relationship, and storing the recommended strategy links in a recommended strategy database.

All recommended policy links stored in the recommended policy database form a policy data set, which may be expressed as follows:

Tactics＝{{t0,(t1,t3,t4)},{t1,(t0,t3,t5)}...}

where Tactics represents a policy dataset, { t0, (t 1, t3, t 4) } represents a recommended policy link, t0 represents a primary recommended policy in the recommended policy links, that is, the first recommended policy in the recommended policy links, (t 1, t3, t 4) represents other recommended policies strongly related to the primary recommended policy t0, and subsequent recommended policy links { t1, (t 0, t3, t 5) }, etc. are similar to the explanation of the recommended policy links described above, and will not be repeated here. The above description of the recommended policy links is given by taking 4 recommended policies as an example of the recommended policy links, and those skilled in the art will understand that other numbers of recommended policies may also form a recommended policy link, for example, 2 recommended policies or more, so the above description of the recommended policy links is merely by way of example and not by way of limitation.

The service recommendation policy points can mutually contain, so that the relevance of service recommendation is conveniently triggered, meanwhile, the service recommendation policy points also contain the product service chain information corresponding to the service, and the service chain of the product is derived from elements and characteristics in the service ordering process. The formation and recommendation sequence of the recommendation policy links are derived from historical business product ordering data fluctuation, and the recommendation policy links are automatically generated according to a relevance algorithm (namely an algorithm for determining the relevance between business products and the recommendation policy links). The formation of the recommended policy links can be divided into two types, one is formed by performing automatic analysis based on actual historical service subscription data, the recommended policy links are automatically constructed, and the other is to manually designate corresponding recommended policy links.

By analyzing the historical service order records, the association relation among a plurality of service products can be accurately obtained, so that an accurate recommendation strategy link is generated, and the recommendation accuracy is improved.

On the basis of the above technical solution, the determining an association relationship between service products according to the historical service subscription record, and generating a recommended policy link between recommended policies corresponding to the service products respectively based on the association relationship, includes: acquiring a plurality of business products subscribed by the same user in the same time period from a historical business subscription record; establishing an association relationship among the plurality of business products according to the ordering sequence of the plurality of business products; and generating recommended strategy links among recommended strategies corresponding to the plurality of business products respectively according to the association relation.

FIG. 4 is a schematic diagram of a scattered swim lane diagram of a historical business order record in an embodiment of the present application. The method comprises the steps of analyzing the attribute of each business product, generating a scattered lane graph based on a historical business order record, acquiring a plurality of business products ordered by the same user in the same time period from the historical business order record, considering that different business products ordered by the same user in the same shorter time period have an association relationship, taking the order sequence of the business products as the order of the association relationship among the business products, and establishing the association relationship among the business products. For example, a scattered lane diagram corresponding to a plurality of business products subscribed by the same user in the same time period may be generated, and as shown in fig. 4, subscription record 1 is that the same user subscribes to product a2 and product a3 in the same time period, and it is determined that product a2 and product a3 have an association relationship.

And determining a recommendation strategy corresponding to each service product in the plurality of service products, and generating recommendation strategy links among the recommendation strategies corresponding to the plurality of service products respectively based on the sequence of the association relation of the plurality of service products.

The method comprises the steps of acquiring a plurality of business products ordered by the same user in the same time period from a historical business ordering record, establishing association relations of the business products, and further generating recommendation strategy links among recommendation strategies corresponding to the business products respectively, wherein the generated recommendation strategy links can accurately reflect the association relations among the business products under the recommendation strategies, and therefore accuracy of the business product recommendation links can be improved.

On the basis of the technical scheme, the method further comprises the following steps: and acquiring a specified recommended strategy link, and storing the specified recommended strategy link into the recommended strategy database.

In addition to generating the recommendation policy links based on the historical service subscription records described above, manually specified recommendation policy links may be obtained and stored in the recommendation policy database. The burstiness of external factors is fully considered by acquiring the artificially specified recommended policy link, the regulation of the recommended policy can be carried out, the balance mechanism of the service recommended policy is guided, the service recommended direction can be timely regulated, the development direction regulation of the service recommendation is maintained, the flow direction control of users and the service is promoted, a sustainable development market adaptation mechanism is formed, the recommendation sequence of each recommended policy in the recommended policy link can be automatically adapted (determined based on historical service order records) and the directional control (artificially specified) is realized.

On the basis of the above technical solution, before determining the preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identifier and the association degree, the method further includes: acquiring initial user data in each data system through an interface between the initial user data and each data system; integrating the initial user data in each data system according to the user identification to obtain integrated data; dividing the integrated data into first data sets respectively corresponding to each of a plurality of target dimensions according to the target dimensions, and storing the first data sets according to the target dimensions; combining partial data of the same service attribute in the first data set corresponding to each target dimension to obtain a second data set corresponding to the service attribute, and storing the second data set according to a recommendation strategy corresponding to the service attribute;

Before determining the preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree, the method further comprises the following steps: and acquiring target user data corresponding to the target user identification from the second data set.

And collecting user information based on software and hardware resources in a telecom cloud environment to form a user data warehouse, and at least obtaining a user multidimensional data set after finishing the user information.

Specifically, the method comprises the following steps: determining the accurate position of the user according to different base stations by utilizing data resources according to the service recommendation range; collecting effective user data information and analyzing the contact point of the client; creating a user preference behavior database according to the contact points; a user preference is determined in the database to establish a user data set.

Based on various software and hardware data information resources on a cloud environment, multi-dimensional data are regularly explored through a data interface mode, various data resources are integrated to form a user data warehouse, a user Identification (ID) system is opened, available, useful and practical user data are continuously accumulated and integrated to the user data warehouse, a user multi-dimensional data set is obtained after the user data are sorted, each user data set is divided into a plurality of sub data sets according to a recommendation strategy and combined to form a user behavior database, and user data in the user behavior database can be used for user data representation.

Specifically, user data is collected based on software and hardware resources in a cloud environment, and initial user data from a daily service system, a charging system, a service operation system, a telecommunication website, a device base station and other telecommunication software and hardware environment resource systems related to users are mainly collected, a data collection interface layer is constructed, the initial user data is subjected to data collection in a data interface mode to form a user data warehouse, the data interface connected with each data system regularly pulls the initial user data from the data system, and after the initial user data in each data system is pulled, the initial user data is analyzed, integrated and stored according to user identification and stored in the data warehouse. The data interface is responsible for collecting data, the data warehouse is responsible for storing data results, and before data storage, the data warehouse needs to integrate various data resources, and opens up a user identification system to form a clean and unified user system, so as to realize an extensible and sustainable accumulation mode, which comprises the following steps: determining the accurate position of the user according to different base stations by utilizing the acquired initial user data according to the service recommendation range (initial user data aiming at the same user identifier in different data systems); collecting valid user data information and analyzing the user's points of contact (business products related to the user, including business products used by the user, and business products associated with business products used by or used by the user); and creating a user preference behavior database according to the contact points, continuously accumulating available, useful and practical user data, and analyzing and integrating the user data into a user data warehouse. Data warehouses will become increasingly wide with development, and the information dimension of data collection will also become increasingly wide, as will user data sets. When defining the user data set, a multidimensional construction mode is adopted to support expansion and more comprehensive expression of user information, and the user data set is defined as follows:

UserDataset＝{(u0,d0,s0)...(uk,dk,sk)...(un-1,dn-1,sn-1)|0≤k≤n-1}

Userdaset represents a collection of first datasets, which are multi-dimensional user datasets, where |u| is the user's dataset business scenario (i.e., base business), |d| represents user data attributes, |s| represents information points, and (uk, dk, sk) form a first dataset of a target dimension. n represents the total amount of user data sets, i.e. the number of target dimensions. The user data attributes include the user's business data, user tags, historical behavior records, and the like. The information points are the recommended service product information corresponding to the user identification, which is determined based on the data of the same user identification in the integrated data.

After initial user data are respectively obtained from each data system, integrating the data aiming at the same user identification in each data system to obtain integrated data, dividing the integrated data according to target dimensions, taking the data belonging to the same target dimensions in the integrated data as a first data set, and storing the first data set according to the target dimensions.

The target dimension may include dimensions of customer groups, industries, geographic locations, product types, business records, or ordering channels, and each dimension further includes different classifications, and corresponding data is stored according to the classifications. For each first data set, the first data set is divided into a plurality of sub data sets according to service attributes (service attributes of service products used by users), sub data sets with the same service attribute in the first data sets with different target dimensions are combined to obtain a second data set corresponding to the service attributes, so that user data of the same user are stored in the same second data set, and the second data set is stored according to a recommended strategy corresponding to the service attributes. For example, in the first data set, the data of the same user are stored in two different first data sets, and the service attributes of the service products to be recommended in the two first data sets are the same, such as video color ring and business color ring, both belong to the service of the color ring, and then the data of the same service attribute in the two first data sets can be combined. Wherein, the business attribute and the recommendation policy are in one-to-one correspondence. Exemplary, the service attributes include historical consumption grade, historical service attention times, historical answering service promotion duration and webpage clicking times; the high-consumption users in the user data set are summarized to a historical consumption grade data set, the high-frequency users focusing on the historical service are summarized to a historical service focusing number data set, the users receiving the service popularization calls for many times are summarized to a historical answering service popularization time data set, and the users accessing the webpage for many times are summarized to a webpage clicking number data set; the data sets of the same business attribute are numbered as a second, different data set.

The second data set may be represented as follows:

UserTactics＝{{t0,(u0,d0,s0)}...{tj,(uj,dj,sj)}...{tm,(um,dm,sm)}|0≤j≤m-1}

where UserTactics represents the set of recommended policies, |t| is the policy type, { tj, (uj, dj, sj) } represents a second data set, and m represents the total number of recommended policies.

The second data set stored in the data repository serves as the basis data for the telecommunications service recommendation. And when the telecommunication service recommendation is carried out on the target user corresponding to the target user identifier, acquiring target user data corresponding to the target user identifier from the second data set. Based on the recommendation policy corresponding to the service product to be recommended, a second data set corresponding to the recommendation policy can be obtained from the data warehouse, and the target user is determined from the second data set, so that the target user data is obtained.

By acquiring and integrating user data from each data system, enough user data can be acquired as basic data of telecommunication service recommendation, and the preference condition of the user on the telecommunication service can be sufficiently described, so that the accuracy of telecommunication service recommendation can be improved.

Fig. 5 is a schematic flow chart of telecommunication service recommendation in the embodiment of the present application, as shown in fig. 5, the data of each data source (data system) is collected, and the open ID system is collected for data integration (for specific integration, reference is made to the above embodiment, and details are not repeated here), so as to obtain a user data set (i.e. the second data set); user data of each user can be used as a user attribute node; each recommended policy link (including information such as business links, service links, etc.) is stored in the recommended policy database; performing association calculation on the user data and the recommended policy links, and determining the to-be-recommended service product links corresponding to the target users; and pushing the service product link to be recommended to the user side.

Fig. 6 is a flowchart of a telecommunication service recommendation method provided in an embodiment of the present application, and as shown in fig. 6, the telecommunication service recommendation method includes:

in step 610, the initial user data in each data system is analyzed and integrated, and the integrated user data is divided into corresponding first data sets according to the target dimension.

The specific processing procedure of the method comprises the following steps: acquiring initial user data in each data system through an interface between the initial user data and each data system; integrating the initial user data in each data system according to the user identification to obtain integrated data; dividing the integrated data into first data sets respectively corresponding to each of a plurality of target dimensions according to the target dimensions, and storing the first data sets according to the target dimensions.

Step 620, dividing the first data set into a plurality of sub data sets according to the recommended policy, and merging the sub data sets with the same service attribute to obtain a second data set.

And merging partial data (sub-data sets) of the same service attribute in the first data set corresponding to each target dimension to obtain a second data set corresponding to the service attribute, and storing the second data set according to a recommendation strategy corresponding to the service attribute.

Step 630, determining an association relationship between a plurality of service products according to the historical service order record, and generating recommended policy links between recommended policies corresponding to the plurality of service products respectively based on the association relationship.

And step 640, determining the association degree between each service product to be recommended and each recommendation policy link according to the historical service order record.

And step 650, determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree.

And step 660, determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation policy link.

Step 670, sending the service product link to be recommended to a target user terminal corresponding to the target user identifier.

For the specific implementation of each step, reference may be made to the above embodiments, and details are not repeated here.

The method and the device for recommending the service product by the user describe preference information of the user by combining multidimensional user data in each data system, further, the preference degree of the user to the service product to be recommended can be accurately determined based on the association degree between the service product to be recommended and the recommendation policy link, further, a corresponding service product link to be recommended can be given, the embodiment realizes the recommendation of the telecommunication service in the form of the service link, the recommendation efficiency can be improved, and the recommendation accuracy of the service product can be improved.

It should be noted that, the user data acquired in the embodiments of the present application are acquired under the condition of user authorization.

Fig. 7 is a schematic structural diagram of a telecommunications service recommendation device according to an embodiment of the present application, as shown in fig. 7, where the device includes:

the association determining module 710 is configured to determine, according to the historical service subscription record, an association degree between each service product to be recommended and each recommended policy link, where the recommended policy link is a link formed by a plurality of recommended policies and is generated based on an association relationship between service products corresponding to the recommended policies;

a preference determining module 720, configured to determine a preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identifier and the association degree;

and a recommendation result determining module 730, configured to determine, according to the preference degree and each recommendation policy link, a service product link to be recommended corresponding to the target user identifier.

Optionally, the apparatus further includes:

the policy link generation module is used for determining the association relation among a plurality of service products according to the historical service order record and generating recommended policy links among recommended policies corresponding to the service products respectively based on the association relation;

And the policy link saving module is used for saving the recommended policy link into a recommended policy database.

Optionally, the policy link generation module is specifically configured to:

acquiring a plurality of business products subscribed by the same user in the same time period from a historical business subscription record;

establishing an association relationship among the plurality of business products according to the ordering sequence of the plurality of business products;

and generating recommended strategy links among recommended strategies corresponding to the plurality of business products respectively according to the association relation.

Optionally, the apparatus further includes:

the specified link saving module is used for acquiring a specified recommended policy link and storing the specified recommended policy link into the recommended policy database.

Optionally, the apparatus further includes:

the user data collection module is used for acquiring initial user data in each data system through an interface between the user data collection module and each data system;

the data integration module is used for integrating the initial user data in each data system according to the user identification to obtain integrated data;

the first data set construction module is used for dividing the integrated data into first data sets respectively corresponding to each of a plurality of target dimensions according to the target dimensions, and storing the first data sets according to the target dimensions;

The data merging module is used for merging partial data of the same service attribute in the first data set corresponding to each target dimension to obtain a second data set corresponding to the service attribute, and storing the second data set according to a recommendation strategy corresponding to the service attribute;

the device comprises:

and the target user data acquisition module is used for acquiring target user data corresponding to the target user identification from the second data set.

Optionally, the association degree determining module is specifically configured to:

for each service product to be recommended and each recommended strategy link, determining a first weight of the service product to be recommended in each recommended strategy in the recommended strategy links according to the historical service order record, and determining the fitness of each recommended strategy to the recommended strategy links;

and determining the association degree between the service product to be recommended and the policy link to be recommended according to the first weight and the adaptation degree.

Optionally, the preference determining module is specifically configured to:

determining, for each recommended policy link, a second weight of the target user identifier to each recommended policy in the recommended policy link according to the target user data;

And determining the preference degree of the target user for the service product to be recommended according to the association degree and the second weight.

The telecom service recommending device provided in the embodiment of the present application is used for implementing each step of the telecom service recommending method described in the embodiment of the present application, and specific implementation manners of each module of the device refer to corresponding steps, which are not repeated herein.

According to the telecommunication service recommending device provided by the embodiment of the invention, the association degree between each service product to be recommended and each recommending strategy link is determined according to the historical service ordering record, the preference degree of the target user for the service product to be recommended is determined according to the target user data and the association degree corresponding to the target user identification, and the service product link to be recommended corresponding to the target user identification is determined according to the preference degree and each recommending strategy link, so that the telecommunication service product is recommended in a link mode instead of a single service.

Referring to fig. 8, fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application. In an embodiment of the present application, an electronic device may include a processor and a memory, where the processor and the memory are connected by a communication bus; the processor is used for calling and executing the program stored in the memory; the memory is used for storing a program, and the program is used for realizing the telecommunication service recommending method according to the embodiment of the application.

By way of example, the electronic devices in the disclosed embodiments of the present application may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), car terminals (e.g., car navigation terminals), and the like, as well as stationary terminals such as digital TVs, desktop computers, servers, and the like. The electronic device shown in fig. 8 is only an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present application.

As shown in fig. 8, the electronic device may include a processing means (e.g., a central processor, a graphics processor, etc.) 801 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

In general, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, etc.; storage 808 including, for example, magnetic tape, hard disk, etc.; communication means 809. The communication means 809 may allow the electronic device to communicate wirelessly or by wire with other devices to exchange data. While fig. 8 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the business recommendation method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication device 809, or installed from storage device 808, or installed from ROM 802. When the computer program is executed by the processing means 801, the above-described functions defined in the telecommunication service recommendation method of the embodiment of the present application are performed.

Those skilled in the art will appreciate that the hardware architecture shown in fig. 8 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

In addition, the embodiment of the invention also provides a computer readable storage medium. The computer readable storage medium stores a computer program which, when executed by a processor, implements the telecommunication service recommendation method according to the embodiments of the present application.

The computer-readable storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: determining the association degree between each service product to be recommended and each recommendation policy link according to the historical service order record, wherein the recommendation policy links are links formed by a plurality of recommendation policies and are generated based on the association relation between the service products corresponding to the recommendation policies; determining the preference degree of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree; and determining a service product link to be recommended corresponding to the target user identifier according to the preference degree and each recommendation strategy link.

In the context of this disclosure, a computer-readable storage medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may be a machine readable signal medium or a machine readable storage medium. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a computer-readable storage medium would include one or more wire-based electrical connections, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer-readable storage medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

The foregoing describes in detail a method, apparatus, electronic device and storage medium for recommending a telecommunication service according to the embodiments of the present application, and specific examples are applied to describe the principles and implementations of the present application, where the description of the foregoing examples is only for helping to understand the method and core idea of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Claims

1. A telecommunications service recommendation method, comprising:

2. The method of claim 1, further comprising, prior to said determining the degree of association between each of the to-be-recommended business products and the respective recommendation policy links based on the historical business subscription record:

according to the historical service order record, determining the association relation among a plurality of service products, and generating recommendation strategy links among recommendation strategies corresponding to the service products respectively based on the association relation;

and storing the recommended strategy link into a recommended strategy database.

3. The method according to claim 2, wherein determining an association relationship between service products according to the historical service subscription record, and generating recommended policy links between recommended policies respectively corresponding to the service products based on the association relationship, comprises:

4. The method as recited in claim 2, further comprising:

and acquiring a specified recommended strategy link, and storing the specified recommended strategy link into the recommended strategy database.

5. The method according to any one of claims 1-4, further comprising, before determining the preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree:

acquiring initial user data in each data system through an interface between the initial user data and each data system;

Integrating the initial user data in each data system according to the user identification to obtain integrated data;

dividing the integrated data into first data sets respectively corresponding to each of a plurality of target dimensions according to the target dimensions, and storing the first data sets according to the target dimensions;

combining partial data of the same service attribute in the first data set corresponding to each target dimension to obtain a second data set corresponding to the service attribute, and storing the second data set according to a recommendation strategy corresponding to the service attribute;

before determining the preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identification and the association degree, the method comprises the following steps:

and acquiring target user data corresponding to the target user identification from the second data set.

6. The method according to any one of claims 1-4, wherein determining the degree of association between each service product to be recommended and the respective recommendation policy link based on the historical service subscription record comprises:

7. The method according to any one of claims 1-4, wherein determining the preference of the target user for the service product to be recommended according to the target user data corresponding to the target user identifier and the association degree includes:

8. A telecommunications service recommendation device, comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the telecommunication service recommendation method according to any one of claims 1 to 7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the telecommunication service recommendation method according to any of claims 1 to 7.