CN113077272B

CN113077272B - Communication business marketing scheme optimization method and device

Info

Publication number: CN113077272B
Application number: CN202010004062.5A
Authority: CN
Inventors: 区晓江; 林银娜
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Priority date: 2020-01-03
Filing date: 2020-01-03
Publication date: 2023-07-21
Anticipated expiration: 2040-01-03
Also published as: CN113077272A

Abstract

One embodiment of the present specification provides a method and apparatus for optimizing a communication service marketing scheme, where the method includes: user portrait corresponding to the user and the user ordering record aiming at the communication service; determining a target user which does not accord with the ordering condition corresponding to the communication service among users ordering the communication service according to the marketing scheme information of the communication service and the ordering record through a target user determining model; determining risk users in users ordering the communication service according to user figures corresponding to the users ordering the communication service through a risk user determining model; and optimizing the marketing scheme information of the communication service according to the order record of the target user and the order record of the risk user. Through the embodiment, the problem of low optimization efficiency caused by optimizing the marketing scheme information of the communication service in a manual mode can be solved.

Description

Communication business marketing scheme optimization method and device

Technical Field

The present document relates to the field of computer technologies, and in particular, to a method and apparatus for optimizing a communication service marketing scheme.

Background

Communication operators often push for various communication services, the specific marketing content and marketing rules of which are recorded in the marketing scheme information of the communication service. The marketing scheme information of the communication service can be exemplified as: "59 Yuan/month, including 50G traffic, the service expiration date is 3 years old from the date of the transaction, allowing only new users to transact. Because the marketing case information of the communication service is mainly customized and obtained by staff according to service requirements, in order to avoid illegal arbitrage behaviors of users caused by the existence of holes in the marketing case information, whether the marketing case information has service missing copper or not can be checked according to the handling condition of the users after the communication service handling is finished, and the marketing case information is optimized according to the checking result so as to facilitate subsequent service handling.

At present, after the communication service is transacted in a manual mode, the marketing scheme information of the communication service is checked and optimized according to the transacting condition of a user, and the problem of low efficiency of the marketing scheme information optimization is solved.

Disclosure of Invention

An object of one embodiment of the present disclosure is to provide a method and an apparatus for optimizing marketing cases of communication services, so as to solve the problem of low optimization efficiency caused by manually optimizing marketing case information of communication services.

To solve the above technical problems, an embodiment of the present specification is implemented as follows:

in a first aspect, an embodiment of the present disclosure provides a method for optimizing a communication service marketing plan, including:

obtaining marketing scheme information of a communication service to be optimized, and obtaining a user portrait corresponding to a user ordering the communication service and an ordering record of the user for the communication service;

determining a target user which does not accord with the ordering condition corresponding to the communication service among users ordering the communication service according to the marketing scheme information of the communication service and the ordering record through a target user determining model;

determining risk users in users ordering the communication service according to user figures corresponding to the users ordering the communication service through a risk user determining model;

and optimizing the marketing scheme information of the communication service according to the order record of the target user and the order record of the risk user.

In a second aspect, another embodiment of the present disclosure provides a communication service marketing plan optimizing apparatus, including:

the acquisition module is used for acquiring marketing information of the communication service to be optimized, and acquiring a user portrait corresponding to a user ordering the communication service and an ordering record of the user for the communication service;

The first determining module is used for determining a target user which does not accord with the ordering condition corresponding to the communication service in the users ordering the communication service according to the marketing scheme information of the communication service and the ordering record through a target user determining model;

the second determining module is used for determining risk users in users ordering the communication service according to user portraits corresponding to the users ordering the communication service through a risk user determining model;

and the optimizing module is used for optimizing the marketing scheme information of the communication service according to the order record of the target user and the order record of the risk user.

In a third aspect, a further embodiment of the present specification provides a communications service marketing optimizing device, comprising: a memory, a processor, and computer-executable instructions stored on the memory and executable on the processor, which when executed by the processor, implement the steps of the communication traffic pattern optimization method as described in the first aspect above.

In a fourth aspect, a further embodiment of the present specification provides a computer readable storage medium for storing computer executable instructions which, when executed by a processor, implement the steps of the communication traffic marketing pattern optimizing method as described in the first aspect above.

In this embodiment, first, the marketing scheme information of the communication service to be optimized is obtained, the user portrait corresponding to the user who subscribes to the communication service and the subscription record of the user for the communication service are obtained, then, according to the marketing scheme information of the communication service and the subscription record, the target user who does not meet the subscription condition corresponding to the communication service is determined among the users who subscribe to the communication service through a target user determination model, then, according to the user portrait corresponding to the user who subscribes to the communication service, the risk user is determined among the users who subscribe to the communication service through a risk user determination model, and finally, the marketing scheme information of the communication service is optimized according to the subscription record of the target user and the subscription record of the risk user. Therefore, according to the embodiment, the target user and the risk user can be automatically determined based on the target user determination model and the risk user determination model, and the marketing scheme information of the communication service is automatically optimized according to the order record of the target user and the order record of the risk user, so that the optimization efficiency of the marketing scheme information of the communication service is improved, and the problem of low optimization efficiency caused by manually optimizing the marketing scheme information of the communication service is solved.

Drawings

In order to more clearly illustrate the technical solution in one or more embodiments of the present description, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments described in the present description, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art.

Fig. 1 is a flow chart of a communication service marketing scheme optimizing method according to an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a communication traffic marketing scheme optimizing system according to an embodiment of the present disclosure;

fig. 3 is a schematic block diagram of a communication service marketing optimizing device according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a communication service marketing optimizing device according to an embodiment of the present disclosure.

Detailed Description

In order to enable a person skilled in the art to better understand the technical solutions in one or more embodiments of the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one or more embodiments of the present disclosure without inventive faculty, are intended to be within the scope of the present disclosure.

An object of one embodiment of the present disclosure is to provide a method and an apparatus for optimizing marketing cases of communication services, so as to solve the problem of low optimization efficiency caused by manually optimizing marketing case information of communication services. The method can be applied to a server side and executed by the server.

Fig. 1 is a flow chart of a communication service marketing scheme optimizing method according to an embodiment of the present disclosure, as shown in fig. 1, the flow chart includes the following steps:

step S102, obtaining marketing plan information of a communication service to be optimized, and obtaining a user portrait corresponding to a user ordering the communication service and an ordering record of the user for the communication service;

step S104, determining the target users which do not accord with the ordering conditions corresponding to the communication service among the users ordering the communication service according to the marketing scheme information of the communication service and the ordering record through the target user determining model;

step S106, determining risk users in users ordering the communication service according to user figures corresponding to the users ordering the communication service through a risk user determination model;

step S108, optimizing the marketing scheme information of the communication service according to the order record of the target user and the order record of the risk user.

In the step S102, the marketing scheme information of the communication service to be optimized is obtained, where the marketing scheme information may be exemplified as follows: "59 Yuan/month, including 50G traffic, the service expiration date is 3 years old from the date of the transaction, allowing only new users to transact. And acquiring a user portrait corresponding to the user subscribed to the communication service. The user portrait includes a plurality of user features and corresponding feature values, for example, the user features are the number of the owned mobile phone cards, the feature values are the number of the corresponding cards, the user features are the monthly telephone charge amount of the user, and the feature values are the corresponding amount values. In one embodiment, the user portrait includes 32 user features and corresponding feature values, where 11 user attribute features, 2 contact circle features, 3 cost features, 3 location information features, 3 internet surfing behavior information, 8 usage behavior features, and 2 credit features.

In step S102 described above, a subscription record for the communication service is also acquired for the user subscribing to the communication service. The order record records the order time of the user ordering the communication service, the order channel (network or counter order), the payment mode, the order number, the staff work number, the service package held by the user before and other information. Data and content related to the user's subscription to the communication service may be recorded in the subscription record.

In the step S104, the target user determining model determines, according to the marketing plan information of the communication service and the subscription record, a target user who does not meet the subscription condition corresponding to the communication service among the users subscribing to the communication service.

Specifically, since the vulnerability of the marketing scheme information of the communication service is likely to cause some users not conforming to the subscription conditions to successfully subscribe to the communication service, in this embodiment, by determining the target users not conforming to the subscription conditions corresponding to the communication service, the vulnerability in the marketing scheme information of the communication service can be determined, thereby optimizing the marketing scheme information of the communication service.

The step S104 specifically includes:

(a1) Determining a sub-model through conditions in a target user determining model, and determining subscription conditions corresponding to the communication service based on marketing scheme information of the communication service;

(a2) And comparing the subscription records of the users subscribing to the communication services with the subscription conditions corresponding to the communication services through a data comparison sub-model in the target user determination model, and determining the target user according to the comparison result.

Specifically, since the subscription conditions corresponding to the communication service are generally recorded in the marketing pattern information of the communication service, in the above-described operation (a 1), the subscription conditions corresponding to the communication service are determined based on the marketing pattern information of the communication service by the condition determination sub-model in the target user determination model.

The action (a 1) specifically includes:

(a11) Extracting a field value of a target field from marketing scheme information of the communication service, and determining a subscription condition corresponding to the communication service according to the field value of the target field;

and/or the number of the groups of groups,

(a12) And carrying out word segmentation processing on the marketing scheme information of the communication service, selecting a target word from words obtained by word segmentation through a preset word stock, extracting text content with text association relation with the target word from the marketing scheme information of the communication service, and determining and obtaining ordering conditions corresponding to the communication service from the text content.

In this embodiment, the subscription condition corresponding to the communication service may be determined by at least one of the above (a 1) or (a 2).

In the act (a 11), a condition determination sub-model in the target user determination model may have an information extraction function, by which a field value of a target field is extracted from the marketing pattern information of the communication service, the target field may be determined according to a writing rule of the marketing pattern information of the communication service, for example, a writing rule of the marketing pattern information of the communication service specifies that a subscription condition is recorded in a chapter of "configuration information", the target field may be "configuration information", and for example, a writing rule of the marketing pattern information of the communication service specifies that a subscription condition is recorded in a chapter of "subscription attribute", and the target field may be "subscription attribute". The condition determining sub-model extracts the field value of the target field from the marketing scheme information of the communication service, wherein the field value can be the chapter content of the chapter of the 'configuration information' in the example or the chapter content of the chapter of the 'subscription attribute'.

When determining the subscription condition corresponding to the communication service according to the field value of the target field, the field value of the extracted target field can be provided for a worker to browse, so that the subscription condition corresponding to the communication service is determined from the field value of the target field in a manual mode. Or determining and obtaining the subscription condition corresponding to the communication service from the field value of the target field by a text analysis method. The subscription conditions corresponding to the communication service may be exemplified as: "New subscriber-only subscription" or "Mobile phone number for subscription service is used for longer than 3 years".

In the operation (a 12), the marketing information of the communication service is subjected to word segmentation, and here, the marketing information of the communication service may be subjected to word segmentation through the CRF model. Specifically, a neural network algorithm is utilized to learn word segmentation rules according to training samples, so that word segmentation-part-of-speech tagging on a marketing scheme based on the rules is realized. The word segmentation and the part of speech tagging are performed simultaneously, and the completion of the two tasks in one model can reduce error propagation. The word segmentation includes lexical analysis, syntactic analysis, and semantic analysis. Part of speech tagging is tagging a sentence (a series of words or phrases) with tags like PN, VB, etc., such as a PN tag for pronouns, an MD tag for stateful verbs, a VV tag for verbs, etc. And defining characteristic functions through the CRF model, and endowing each characteristic function f_j with a weight lambda_j so as to determine final word segmentation and part-of-speech tagging results.

In this embodiment, other word segmentation methods may also be used. For example, word segmentation is performed by means of forward maximum matching, reverse maximum matching, bidirectional maximum matching, minimum segmentation and the like, so that multiple word segmentation results are obtained, and an optimal word segmentation result is selected from the multiple word segmentation results, so that the problem of ambiguity in word segmentation is solved. If the text string is "mobile phone package cost", firstly, performing entry retrieval (generally using Trie storage), finding out all matched entries (mobile phone, package, cost, mobile phone case), representing in a word grid form, then performing path search, finding out an optimal path based on a marketing and sales statistics language model (such as n-gram), and determining the word segmentation result as an optimal result.

After word segmentation is performed on marketing scheme information of communication service, selecting a target word from words obtained by word segmentation through a preset word stock, for example, searching each word in the preset word stock from words obtained by word segmentation, and taking the searched word as the target word. Then, text content with text association relation with the target vocabulary is extracted from the marketing scheme information of the communication service, and the content with text association relation with the target vocabulary can be the context information of the target vocabulary. Finally, determining the subscription condition corresponding to the communication service in the text content, wherein the advanced content can be sent to manual processing, and the subscription condition is determined in the advanced content manually.

In one example, the word segmentation obtains a plurality of terms such as "order condition", "user information", "background rule", and the like, and the vocabulary of "order condition" is recorded in a preset word stock, so that the "order condition" is determined as a target vocabulary. And extracting text content with text association relation with the word of the ordering condition from the marketing scheme information of the communication service, such as the context information of the word, and finally determining and obtaining the ordering condition corresponding to the communication service from the context information of the word by a manual mode or a text analysis mode.

In the above-mentioned action (a 2), the subscription record of each subscriber subscribing to the communication service and the subscription condition corresponding to the communication service are compared by the data comparison sub-model in the target subscriber determination model, and the target subscriber is determined according to the comparison result. Specifically, the data comparison sub-model has a data comparison function, and through the data comparison sub-model, the order records of the users who subscribe to the communication service and the order conditions corresponding to the communication service are compared, and the users whose order records do not meet the order conditions are determined as target users.

In a specific embodiment, a subscription condition corresponding to the communication service is determined from the marketing scheme information of the communication service, such as a start date, an end date, a subscription object, a mutual exclusion relation, a dependency relation, a forward limit, and the like, a target user which does not meet the subscription condition is determined from the subscriber according to the subscription condition, and information such as a subscription channel of the target user, a job number of a corresponding staff, and the like is determined. In this embodiment, various target users, such as a target user who repeatedly subscribes, a target user who has a time-out-of-effect > use validity period, a target user who has specified an outside-the-ground office service, a target user who has transacted after the time-out, and the like, can be analyzed.

After the target user is determined, in step S106, the risk user is determined among the users who subscribe to the communication service according to the user portraits corresponding to the users who subscribe to the communication service through the risk user determination model. The method specifically comprises the following steps:

(b1) Determining a Gaussian mixture clustering sub-model in the model by a risk user, clustering the users ordering the communication service according to user images corresponding to the users ordering the communication service, and determining a risk user group according to a clustering result;

(b2) And determining the risk users in the risk user group according to the predetermined normal user portrait and the risk user portrait by the user comparison sub-model in the risk user determination model.

In the above-mentioned action (b 1), the users subscribed to the communication service are clustered according to the user images corresponding to the users subscribed to the communication service in a clustering manner, and the risk user group is determined according to the clustering result. The process of clustering users using gaussian models may refer to prior art processes and are not repeated here. Of course, the K-Means algorithm may be used to cluster the users subscribed to the communication service according to the user images corresponding to the users subscribed to the communication service, which is not limited in the embodiment of the present disclosure.

When the k-means algorithm is used for clustering users, the clustering quality is determined by evaluating the separation condition of the classes, and the closer the classes are, the larger the inter-class distance is, the higher the quality is. For k-means clustering, there is a class center. The intra-class distance is: the sum of the distances from each sample in the class to the center of the class is the average. The inter-class distance is as follows: average value of sum of center distances of each sample in the class to other classes. If a is a risk group, the result of clustering for a plurality of K values is that the intra-class distance of a is the smallest and the inter-class distance of a from other classes is the largest. Because of the lateral comparison, the intra-class distance/inter-class distance comparison of a is taken here to take the minimum. Preferably, k=5.

When the user is clustered through the Gaussian mixture clustering sub-model, the Gaussian curve is equivalent to the class center, the intra-class distance is equivalent to 1 minus the average value of the sum of the probabilities that each sample belongs to the sample, and the inter-class distance is equivalent to 1 minus the average value of the sum of the probabilities that each sample belongs to other groups. The risk user group is still the group with the smallest intra-class distance/inter-class distance ratio.

After the risk user group is obtained through the clustering of the action (b 1), the risk user is determined in the risk user group according to the normal user portrait and the risk user portrait which are determined in advance through the user comparison sub-model in the risk user determination model through the action (b 2).

Action (b 2) specifically includes:

(b21) Comparing the user portraits of the users in the risk user group with the normal user portraits, determining the normal users in the risk user group according to the comparison result, and removing the normal users;

(b22) And comparing the user portraits of the users remaining after the elimination in the risk user group with the risk user portraits, and determining the risk users from the users remaining after the elimination according to the comparison result.

The user comparison sub-model in the risk user determination model has the function of comparing user portraits. Firstly, comparing a user portrait of a user in a risk user group with a normal user portrait, for example, if N feature values exist in a value range corresponding to the normal user portrait in each feature value of a certain user in the risk user group, and N/M is larger than a preset threshold value, determining that the comparison is consistent, determining that the user is a normal user, if N feature values exist in a value range corresponding to the normal user portrait in each feature value of a certain user in the risk user group, and N/M is not larger than a preset threshold value, determining that the comparison is inconsistent, and determining that the user is not a normal user. Wherein N is a positive integer, and M is the total number of the feature values of the certain user. Through the above process, the users with consistent comparison in the risk user group are determined to be normal users, and are removed from the risk user group.

After removing normal users from the risk user group, comparing the user portraits of the rest users with the risk user portraits, for example, if N characteristic values exist in the value range corresponding to the risk user portraits in each characteristic value of a rest user in the risk user group, and N/M is larger than a preset threshold value, determining that the comparison is consistent, determining that the user is a risk user, if N characteristic values exist in the value range corresponding to the risk user portraits in each characteristic value of a rest user in the risk user group, and N/M is not larger than the preset threshold value, determining that the comparison is inconsistent, and determining that the user is not a risk user. Wherein N is a positive integer, and M is the total number of the feature values of the certain user. Through the above process, the risk users are determined by comparing the consistent users in the rest users in the risk user group.

In this embodiment, normal user portraits and risk user portraits may be established by taking all users in the whole network, and through the above process, risk users are determined and obtained from the users in the risk user group, where the risk users may include card-keeping users. The normal user portrait describing process is as follows: and regarding the total users as normal user groups, selecting quantitative characteristics to describe portraits, such as dimensions of ARPU (automatic request per unit time), communication, flow and the like, wherein the higher the characteristic values of the ARPU and the like are, the higher the probability of the normal users is, and taking 90% of the dimension intervals of the users from high to low as normal user intervals to describe the normal user portraits. The depicting process of the portrait of the risk user is as follows: from the investigation it is known that: the internet card (pull) user has the following features: (1) from the standpoint of maximizing benefit: the number of the account opening numbers under the same certificate is more than 1; (2) from a centralization point of view: the Internet card-keeping users have the advantages of concentrated account opening, concentrated business handling, concentrated residence and working places, and the working places are the same as the residence; (3) Because the internet card vendor cooperates with the code receiving platform, it cannot operate if it is stopped. The downtime of the user to weeding is 0. From these features, a risk user representation is depicted. In the normal user portrayal and the risk user portrayal, the number and the kind of the user features are the same as those in the user portrayal of the user who subscribes to the communication service. Through analyzing the risk users, the risk users such as the weeding can be found, so that the marketing scheme information is optimized as the cut-in point.

After the target user and the risk user are determined, the marketing scheme information of the communication service is optimized according to the order record of the target user and the order record of the risk user through step S108.

The method specifically comprises the following steps:

(c1) Determining risk factors of marketing scheme information of the communication service according to the order records of the target user and the order records of the risk user;

(c2) And determining an optimization strategy of the marketing scheme information of the communication service according to the risk factors of the marketing scheme information of the communication service, and optimizing the marketing scheme information of the communication service based on the optimization strategy.

Firstly, determining risk factors of marketing scheme information of a communication service according to an order record of a target user and an order record of a risk user, specifically, firstly, analyzing the order record of the target user and the order record of the risk user to obtain a plurality of service order parameters contained in the order record of the target user and the order record of the risk user, then, searching for target order parameters which do not meet the order conditions corresponding to the communication service in the service order parameters, finally, acquiring content related to the target order parameters from marketing scheme information of the communication service, and determining the risk factors of the marketing scheme information of the communication service according to the related content.

The subscription record is composed of a plurality of service subscription parameters, and the service subscription parameters comprise subscription channels, subscription time, user identity information, specific information of the held service when the user subscribes, and the like. Firstly, analyzing the order records of the target user and the order records of the risk user to obtain the order records of the target user and a plurality of service order parameters contained in the order records of the risk user, wherein the step is equivalent to decomposing the order records of the target user and the order records of the risk user to obtain a plurality of service order parameters. Since the target user and the risk user are users who do not wish to subscribe to the communication service, the marketing plan information of the communication service can be optimized starting from a plurality of service subscription parameters.

After decomposing to obtain a plurality of service subscription parameters, searching a target subscription parameter which does not meet the subscription conditions corresponding to the communication service in each service subscription parameter, for example, if a certain target subscription parameter is 'a user previously subscribed with a 58-element 4G traffic package', but the user is required to be not allowed to subscribe with other 4G packages before in the subscription conditions, the target subscription parameter does not meet the subscription conditions, and searching the target subscription parameter. And finally, acquiring the content related to the target ordering parameters from the marketing scheme information of the communication service, and determining the risk factors of the marketing scheme information of the communication service according to the related content. In this process, taking the target subscription parameter as an example of "the user has subscribed to a 58-element 4G traffic package before", the content related to the target subscription parameter is content limited by the constraint on the service subscribed to before by the user, and the risk factor of the marketing scheme information is determined from the content.

In a specific example, after determining to obtain the target subscription parameter, the target subscription parameter is provided to a staff member, and the staff member extracts relevant content from the marketing scheme information according to the target subscription parameter, and determines risk factors of the marketing scheme information according to the relevant content. In the above example, the staff member searches the content of constraint restriction on the service subscribed before by the user in the marketing case information according to the target subscription parameter "the user subscribes to have a 58-element 4G traffic package before", and finds that the constraint on the service subscribed before by the user is not clear enough by the content, so that when the staff member transacts the service, a transacting error exists, and the staff member determines that the risk factor of marketing case information is "the constraint on the service subscribed before by the user is not clear enough".

In the above-mentioned action (c 2), the staff may determine an optimization policy of the marketing scheme information of the communication service according to the risk factors of the marketing scheme information of the communication service, and optimize the marketing scheme information of the communication service based on the optimization policy. For example, in the above example, the staff determines that the optimization policy is "further define the limitation condition of the service subscribed to before by the user" according to the risk factor "the limitation of the service subscribed to before by the user is not sufficiently defined", so that the staff optimizes the marketing information of the communication service, for example, changes the content of the communication marketing scheme, so as to further define the limitation condition of the service subscribed to before by the user according to the optimization policy.

The target user determination model and the risk user determination model in the above embodiments may be neural network convolution models, and the training process of the target user determination model and the risk user determination model may refer to the existing model training process, which is not described herein.

Fig. 2 is a schematic diagram of a communication traffic marketing scheme optimizing system according to an embodiment of the present disclosure, which is used to implement the marketing scheme optimizing method according to the present embodiment. The system as shown in fig. 2 comprises: a data layer, a rules layer, an application layer, and an interface layer.

The data layer is mainly used for storing various data for optimizing marketing and sales information, and comprises the following steps: the system comprises the following components of demand data of marketing cases of market business departments, data of business support marketing case configuration, log records of user marketing case handling and behavior data of using marketing case resources by users. The log records of the user in the marketing business and the behavior data of the user using the marketing business resources are effectively displayed. The rule layer comprises a target user identification model and a risk user identification model, and the target user identification model and the risk user identification model can be realized based on an AI artificial intelligence algorithm. The application layer comprises target user identification, risk user identification and optimization strategy determination. The interface layer comprises a man-machine interaction interface and is used for displaying contents such as a target user list, a risk user list, risk factors, an optimization strategy and the like.

In summary, compared with the existing manual analysis of the handling situation of the user business and the manner of marketing information, in the embodiment, the method and the device for optimizing the marketing information of the communication business can automatically determine the target user and the risk user based on the target user determination model and the risk user determination model, automatically optimize the marketing information of the communication business according to the order record of the target user and the order record of the risk user, improve the optimization efficiency of the marketing information of the communication business, and solve the problem of low optimization efficiency caused by optimizing the marketing information of the communication business in a manual manner.

Fig. 3 is a schematic block diagram of a communication service marketing optimizing device according to an embodiment of the present disclosure, and as shown in fig. 3, the device includes:

the obtaining module 31 is configured to obtain marketing information of a communication service to be optimized, and obtain a user portrait corresponding to a user who subscribes to the communication service and a subscription record of the user for the communication service;

a first determining module 32, configured to determine, according to a target user determining model and the marketing plan information of the communication service and the subscription record, a target user that does not meet a subscription condition corresponding to the communication service among users subscribed to the communication service;

A second determining module 33, configured to determine, according to a risk user determining model, a risk user among users who subscribe to the communication service according to a user portrait corresponding to the user who subscribe to the communication service;

an optimizing module 34, configured to optimize the marketing plan information of the communication service according to the subscription record of the target user and the subscription record of the risk user.

Optionally, the first determining module 32 is specifically configured to: determining a condition determining sub-model in a target user determining model, and determining and obtaining a subscription condition corresponding to the communication service based on the marketing scheme information of the communication service; and comparing the subscription records of the users subscribing the communication service with the subscription conditions corresponding to the communication service through a data comparison sub-model in a target user determination model, and determining the target user according to a comparison result.

Optionally, the first determining module 32 is further specifically configured to: extracting a field value of a target field from the marketing scheme information of the communication service, and determining a subscription condition corresponding to the communication service according to the field value of the target field; and/or, word segmentation processing is carried out on the marketing scheme information of the communication service, a target word is selected from words obtained by word segmentation through a preset word bank, text content with text association relation with the target word is extracted from the marketing scheme information of the communication service, and ordering conditions corresponding to the communication service are determined in the text content.

Optionally, the second determining module 33 is specifically configured to: determining a Gaussian mixture clustering sub-model in the model by the risk user, clustering the users ordering the communication service according to the user images corresponding to the users ordering the communication service, and determining a risk user group according to a clustering result; and determining the risk users in the risk user group according to the predetermined normal user portrait and the risk user portrait by the user comparison sub-model in the risk user determination model.

Optionally, the second determining module 33 is further specifically configured to: comparing the user portraits of the users in the risk user group with the normal user portraits, determining normal users in the risk user group according to the comparison result, and eliminating the normal users; and comparing the user portraits of the users remaining after the elimination in the risk user group with the risk user portraits, and determining the risk users from the remaining users after the elimination according to the comparison result.

Optionally, the optimization module 34 is specifically configured to: determining risk factors of marketing plan information of the communication service according to the order records of the target user and the order records of the risk user; and determining an optimization strategy of the marketing scheme information of the communication service according to the risk factors of the marketing scheme information of the communication service, and optimizing the marketing scheme information of the communication service based on the optimization strategy.

Optionally, the optimization module 34 is further specifically configured to: analyzing the order record of the target user and the order record of the risk user to obtain a plurality of business order parameters contained in the order record of the target user and the order record of the risk user; searching target subscription parameters which do not accord with the subscription conditions corresponding to the communication service in each service subscription parameter; and acquiring content related to the target ordering parameters from the marketing scheme information of the communication service, and determining risk factors of the marketing scheme information of the communication service according to the related content.

The communication service marketing scheme optimizing device provided by an embodiment of the present disclosure can implement each process in the foregoing method embodiment, and achieve the same functions and effects, which are not repeated here.

Further, an embodiment of the present disclosure further provides a communication service marketing optimizing device, and fig. 4 is a schematic structural diagram of the communication service marketing optimizing device provided in an embodiment of the present disclosure, as shown in fig. 4, where the device includes: memory 401, processor 402, bus 403, and communication interface 404. The memory 401, processor 402, and communication interface 404 communicate over a bus 403, and the communication interface 404 may include input output interfaces including, but not limited to, a keyboard, mouse, display, microphone, loudspeaker, and the like.

In fig. 4, the memory 401 stores computer executable instructions executable on the processor 402, which when executed by the processor 402 implement the following procedures:

Optionally, when the computer executable instructions are executed by the processor, determining, by a target user determining model, according to the marketing plan information of the communication service and the subscription record, among users subscribed to the communication service, a target user that does not meet a subscription condition corresponding to the communication service, including: determining a condition determining sub-model in a target user determining model, and determining and obtaining a subscription condition corresponding to the communication service based on the marketing scheme information of the communication service; and comparing the subscription records of the users subscribing the communication service with the subscription conditions corresponding to the communication service through a data comparison sub-model in a target user determination model, and determining the target user according to a comparison result.

Optionally, when the computer executable instructions are executed by the processor, determining, by the condition determining sub-model in the target user determining model, based on the marketing plan information of the communication service, a subscription condition corresponding to the communication service, including: extracting a field value of a target field from the marketing scheme information of the communication service, and determining a subscription condition corresponding to the communication service according to the field value of the target field; and/or, word segmentation processing is carried out on the marketing scheme information of the communication service, a target word is selected from words obtained by word segmentation through a preset word bank, text content with text association relation with the target word is extracted from the marketing scheme information of the communication service, and ordering conditions corresponding to the communication service are determined in the text content.

Optionally, when the computer executable instructions are executed by the processor, determining, by a risk user determination model, a risk user among users subscribed to the communication service according to user portraits corresponding to users subscribed to the communication service, including: determining a Gaussian mixture clustering sub-model in the model by the risk user, clustering the users ordering the communication service according to the user images corresponding to the users ordering the communication service, and determining a risk user group according to a clustering result; and determining the risk users in the risk user group according to the predetermined normal user portrait and the risk user portrait by the user comparison sub-model in the risk user determination model.

Optionally, when the computer executable instructions are executed by the processor, determining, by the user alignment sub-model in the risk user determination model, a risk user in the risk user group from a predetermined normal user profile and a risk user profile, comprising: comparing the user portraits of the users in the risk user group with the normal user portraits, determining normal users in the risk user group according to the comparison result, and eliminating the normal users; and comparing the user portraits of the users remaining after the elimination in the risk user group with the risk user portraits, and determining the risk users from the remaining users after the elimination according to the comparison result.

Optionally, the computer executable instructions, when executed by the processor, optimize marketing pattern information for the communication service based on the subscription record for the target user and the subscription record for the risk user, comprising: determining risk factors of marketing plan information of the communication service according to the order records of the target user and the order records of the risk user; and determining an optimization strategy of the marketing scheme information of the communication service according to the risk factors of the marketing scheme information of the communication service, and optimizing the marketing scheme information of the communication service based on the optimization strategy.

Optionally, the computer executable instructions, when executed by the processor, determine a risk factor for marketing plan information for the communication service based on the subscription record for the target user and the subscription record for the risk user, comprising: analyzing the order record of the target user and the order record of the risk user to obtain a plurality of business order parameters contained in the order record of the target user and the order record of the risk user; searching target subscription parameters which do not accord with the subscription conditions corresponding to the communication service in each service subscription parameter; and acquiring content related to the target ordering parameters from the marketing scheme information of the communication service, and determining risk factors of the marketing scheme information of the communication service according to the related content.

The communication service marketing scheme optimizing device provided in an embodiment of the present disclosure can implement each process in the foregoing method embodiment, and achieve the same functions and effects, which are not repeated here.

Further, another embodiment of the present specification also provides a computer-readable storage medium for storing computer-executable instructions that when executed by a processor implement the following:

Optionally, when the computer executable instructions are executed by the processor, determining, by a target user determining model, a target user that does not meet a subscription condition corresponding to the communication service from users subscribed to the communication service according to the marketing plan information of the communication service and the subscription record, including: determining a condition determining sub-model in a target user determining model, and determining and obtaining a subscription condition corresponding to the communication service based on the marketing scheme information of the communication service; and comparing the subscription records of the users subscribing the communication service with the subscription conditions corresponding to the communication service through a data comparison sub-model in a target user determination model, and determining the target user according to a comparison result.

Optionally, when the computer executable instructions are executed by the processor, determining, by a risk user determination model, a risk user among users who subscribe to the communication service according to a user portrait corresponding to the user who subscribes to the communication service, including: determining a Gaussian mixture clustering sub-model in the model by the risk user, clustering the users ordering the communication service according to the user images corresponding to the users ordering the communication service, and determining a risk user group according to a clustering result; and determining the risk users in the risk user group according to the predetermined normal user portrait and the risk user portrait by the user comparison sub-model in the risk user determination model.

Optionally, when the computer executable instructions are executed by the processor, determining, by the user alignment sub-model in the risk user determination model, a risk user in the risk user group according to a predetermined normal user profile and risk user profile, including: comparing the user portraits of the users in the risk user group with the normal user portraits, determining normal users in the risk user group according to the comparison result, and eliminating the normal users; and comparing the user portraits of the users remaining after the elimination in the risk user group with the risk user portraits, and determining the risk users from the remaining users after the elimination according to the comparison result.

Optionally, the computer executable instructions, when executed by the processor, optimize marketing pattern information of the communication service based on the subscription record of the target user and the subscription record of the risk user, comprising: determining risk factors of marketing plan information of the communication service according to the order records of the target user and the order records of the risk user; and determining an optimization strategy of the marketing scheme information of the communication service according to the risk factors of the marketing scheme information of the communication service, and optimizing the marketing scheme information of the communication service based on the optimization strategy.

Optionally, the computer executable instructions, when executed by the processor, determine a risk factor for the marketing plan information of the communication service based on the subscription record of the target user and the subscription record of the risk user, comprising: analyzing the order record of the target user and the order record of the risk user to obtain a plurality of business order parameters contained in the order record of the target user and the order record of the risk user; searching target subscription parameters which do not accord with the subscription conditions corresponding to the communication service in each service subscription parameter; and acquiring content related to the target ordering parameters from the marketing scheme information of the communication service, and determining risk factors of the marketing scheme information of the communication service according to the related content.

The computer readable storage medium includes Read-Only Memory (ROM), random access Memory (Random Access Memory RAM), magnetic disk or optical disk, etc.

The storage medium provided in an embodiment of the present disclosure can implement each process in the foregoing method embodiment and achieve the same functions and effects, and will not be repeated here.

It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method for optimizing a communication traffic marketing plan, comprising:

optimizing marketing plan information of the communication service according to the order record of the target user and the order record of the risk user;

the optimizing the marketing plan information of the communication service according to the order record of the target user and the order record of the risk user comprises the following steps:

determining risk factors of marketing plan information of the communication service according to the order records of the target user and the order records of the risk user;

determining an optimization strategy of the marketing scheme information of the communication service according to risk factors of the marketing scheme information of the communication service, and optimizing the marketing scheme information of the communication service based on the optimization strategy;

determining risk factors of marketing plan information of the communication service according to the order records of the target user and the order records of the risk user, including:

analyzing the order record of the target user and the order record of the risk user to obtain a plurality of business order parameters contained in the order record of the target user and the order record of the risk user;

Searching target subscription parameters which do not accord with the subscription conditions corresponding to the communication service in each service subscription parameter;

and acquiring content related to the target ordering parameters from the marketing scheme information of the communication service, and determining risk factors of the marketing scheme information of the communication service according to the related content.

2. The method according to claim 1, wherein determining, by a target user determination model, a target user who does not meet a subscription condition corresponding to the communication service among users who subscribe to the communication service according to the marketing plan information of the communication service and the subscription record, comprises:

determining a condition determining sub-model in a target user determining model, and determining and obtaining a subscription condition corresponding to the communication service based on the marketing scheme information of the communication service;

and comparing the subscription records of the users subscribing the communication service with the subscription conditions corresponding to the communication service through a data comparison sub-model in a target user determination model, and determining the target user according to a comparison result.

3. The method of claim 2, wherein determining subscription conditions corresponding to the communication service based on the marketing pattern information of the communication service by a condition determination sub-model in a target user determination model comprises:

Extracting a field value of a target field from the marketing scheme information of the communication service, and determining a subscription condition corresponding to the communication service according to the field value of the target field;

and/or the number of the groups of groups,

and carrying out word segmentation processing on the marketing scheme information of the communication service, selecting a target word from words obtained by word segmentation through a preset word stock, extracting text content with text association relation with the target word from the marketing scheme information of the communication service, and determining ordering conditions corresponding to the communication service in the text content.

4. The method of claim 1, wherein determining, by a risk user determination model, risk users among users who subscribe to the communication service based on user portraits corresponding to users who subscribe to the communication service, comprises:

determining a Gaussian mixture clustering sub-model in the model by the risk user, clustering the users ordering the communication service according to the user images corresponding to the users ordering the communication service, and determining a risk user group according to a clustering result;

and determining the risk users in the risk user group according to the predetermined normal user portrait and the risk user portrait by the user comparison sub-model in the risk user determination model.

5. The method of claim 4, wherein determining risk users in the risk user group from a predetermined normal user profile and risk user profile by a user comparison sub-model in the risk user determination model comprises:

comparing the user portraits of the users in the risk user group with the normal user portraits, determining normal users in the risk user group according to the comparison result, and eliminating the normal users;

and comparing the user portraits of the users remaining after the elimination in the risk user group with the risk user portraits, and determining the risk users from the remaining users after the elimination according to the comparison result.

6. A communications service marketing optimizing apparatus, comprising:

the optimizing module is used for optimizing the marketing scheme information of the communication service according to the order record of the target user and the order record of the risk user;

the optimizing module is specifically configured to determine risk factors of marketing plan information of the communication service according to the order record of the target user and the order record of the risk user;

the optimizing module is further specifically configured to parse the subscription record of the target user and the subscription record of the risk user to obtain a plurality of service subscription parameters included in the subscription record of the target user and the subscription record of the risk user;

7. A communications traffic marketing optimization device comprising a memory and a processor, the memory having stored thereon computer executable instructions that, when executed on the processor, are capable of carrying out the steps of the communications traffic marketing optimization method of any of the preceding claims 1-5.

8. A storage medium having stored therein computer executable instructions which, when executed by a processor, are capable of carrying out the steps of the communication traffic pattern optimization method according to any of the preceding claims 1-5.