CN-121998679-A - Telecom marketing strategy generation method, device and storage medium

CN121998679ACN 121998679 ACN121998679 ACN 121998679ACN-121998679-A

Abstract

The application provides a telecommunication marketing strategy generation method, a telecommunication marketing strategy generation device and a storage medium, relates to the field of telecommunication marketing, and can solve the problem of low marketing efficiency. The method comprises the steps of carrying out intention recognition based on voice information of a user in a telecom customer service hotline to obtain intention probability distribution, carrying out feature extraction on user data to obtain user portraits, wherein the user portraits are used for representing objective attributes of the telecom service currently used by the user and subjective feelings of the user, determining user scores based on the intention probability distribution and the user portraits, wherein the user scores are used for representing the intention degree of the user to install bandwidth service, determining marketing strategies of broadband services corresponding to the user scores under the condition that the user scores are larger than a user score threshold, and pushing the marketing strategies to terminals of the user. The method and the system can accurately match different requirements of different users, push different marketing strategies for different users, improve marketing efficiency and improve user experience.

Inventors

ZHAI LIZHU
CHANG ZHENLEI
SUN MIAO
HAN GAN
LU WENCHENG
QU YOUJUN
CHEN QIAN
YU DONGJU
WANG ZHIJUN
Tian yikun
LI HONGPENG

Assignees

中国联合网络通信集团有限公司

Dates

Publication Date: 20260508
Application Date: 20260119

Claims (10)

1. A telecommunications marketing strategy generation method, the method comprising: Carrying out intention recognition based on voice information of a user in a telecom customer service hotline to obtain intention probability distribution, wherein the intention probability distribution is used for indicating the probability that the user handles each telecom service based on the voice information; Extracting characteristics of user data to obtain a user portrait, wherein the user portrait is used for representing objective attributes of telecommunication services currently used by the user and subjective feelings of the user; determining a user score based on the intent probability distribution and the user representation, the user score being used to characterize the extent of intent of the user to install bandwidth traffic; And under the condition that the user score is larger than a user score threshold, determining a marketing strategy of the broadband service corresponding to the user score, and pushing the marketing strategy to the terminal of the user.
2. The method of claim 1, wherein the performing intent recognition based on the voice information of the user in the telecom customer service hotline to obtain the intent probability distribution comprises: performing voice recognition on the voice information through a Wav2Vec model, and converting the voice information into text information; and carrying out intention recognition through a pre-trained intention recognition model based on the text information to obtain the intention probability distribution.
3. The method of claim 1, wherein the user data comprises location information of the user, business information of the user, voice information of the user; The feature extraction is performed on the user data to obtain a user portrait, which comprises the following steps: Extracting features from the position information of the user and the service information of the user to obtain explicit features of the user, wherein the explicit features are used for representing objective attributes of the user when the telecommunication service is used; Extracting features from the voice information of the user to obtain implicit features of the user and emotion features of the user, wherein the implicit features are used for representing potential requirements of the user when the user uses the telecommunication service, and the emotion features are used for representing satisfaction degree of the user on the telecommunication service; and carrying out weighted summation on the dominant features, the recessive features and the emotion features to obtain the user portrait.
4. The method of claim 1, wherein the determining a user score based on the intent probability distribution and the user representation comprises: And determining the user score based on the intention probability distribution, the user portrait and market environment information, wherein the market environment information is used for representing the marketing condition of broadband business of the area where the user is located.
5. The method of claim 4, wherein the determining the user score based on the intent probability distribution, the user representation, and market environment information comprises: And processing the intention probability distribution, the user portraits and the market environment information through an integrated learning model based on a gradient lifting decision tree to obtain the user scores.
6. The method of claim 1, wherein the determining a marketing strategy for broadband traffic corresponding to the user score comprises at least any one of: Determining a marketing strategy of the broadband service corresponding to the user score based on a first mapping relation, wherein the first mapping relation is used for representing the corresponding relation between the user score and the marketing strategy of the broadband service; determining a marketing strategy of the broadband service according to the user score and the probability of installing the broadband service in the intention probability distribution; Determining a marketing strategy of the broadband service according to the user scores and the economic development degree of the area where the user is located; and determining the marketing strategy of the broadband service according to the user score and whether the bid information exists in the voice information.
7. A telecommunications marketing strategy generation apparatus, the apparatus comprising: the recognition unit is used for carrying out intention recognition based on the voice information of the user in the telecom customer service hotline to obtain intention probability distribution, wherein the intention probability distribution is used for indicating the probability that the user handles each telecom service obtained based on the voice information; The extraction unit is used for extracting the characteristics of the user data to obtain a user portrait, wherein the user portrait is used for representing the objective attribute of the telecommunication service currently used by the user and the subjective feeling of the user; A determining unit configured to determine a user score based on the intention probability distribution and the user representation, the user score being used to characterize the degree of intention of the user to install bandwidth traffic; And the generation unit is used for determining the marketing strategy of the broadband service corresponding to the user score and pushing the marketing strategy to the terminal of the user under the condition that the user score is larger than the user score threshold.
8. An electronic device comprising a processor and a communication interface, the communication interface and the processor being coupled, the processor being operable to execute a computer program or instructions to implement the method of any of claims 1-6.
9. A computer readable storage medium having instructions stored therein, which when executed by a computer, perform the method of any of claims 1-6.
10. A computer program product comprising computer instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-6.

Description

Telecom marketing strategy generation method, device and storage medium Technical Field The present application relates to the field of telecommunications marketing, and in particular, to a telecommunications marketing policy generation method, apparatus, and storage medium. Background With the rapid development of communication technology and the wide popularization of broadband services, telecom operators face a serious challenge of how to efficiently mine the potential user demands and improve the marketing conversion rate. At present, marketing resources are usually put into users through schemes such as keyword matching and the like. But marketing strategies generated by these schemes cannot match user demand, resulting in inefficient marketing. Disclosure of Invention The application provides a telecommunication marketing strategy generation method, a telecommunication marketing strategy generation device and a storage medium, which can improve marketing efficiency. In order to achieve the above purpose, the application adopts the following technical scheme: The method comprises the steps of carrying out intention recognition based on voice information of a user in a telecommunication customer service hotline to obtain intention probability distribution, carrying out feature extraction on user data to obtain user portraits, determining user scores based on the intention probability distribution and the user portraits, wherein the user scores are used for representing the intention degree of the user for installing bandwidth service, determining marketing strategies of broadband service corresponding to the user scores under the condition that the user scores are larger than a user score threshold, and pushing the marketing strategies to terminals of the user. With reference to the first aspect, in one possible implementation manner, the intention recognition is performed based on the voice information of the user in the telecom customer service hotline to obtain the intention probability distribution, which includes performing voice recognition on the voice information through a Wav2Vec model, converting the voice information into text information, and performing intention recognition on the basis of the text information through a pre-trained intention recognition model to obtain the intention probability distribution. With reference to the first aspect, in one possible implementation manner, the user data includes user location information, user service information and user voice information, the feature extraction is performed on the user data to obtain a user portrait, the feature extraction is performed on the user location information and the user service information to obtain an explicit feature of the user, the explicit feature is used for representing objective attributes of the user when the user uses the telecommunication service, the feature extraction is performed on the user voice information to obtain an implicit feature of the user and an emotion feature of the user, the implicit feature is used for representing potential requirements of the user when the user uses the telecommunication service, the emotion feature is used for representing satisfaction degree of the user to the telecommunication service, and the weighted summation is performed on the explicit feature, the implicit feature and the emotion feature to obtain the user portrait. With reference to the first aspect, in a possible implementation manner, determining the user score based on the intent probability distribution and the user portrait includes determining the user score based on the intent probability distribution, the user portrait, and market environment information, where the market environment information is used to characterize marketing conditions of broadband services in an area where the user is located. With reference to the first aspect, in one possible implementation manner, determining the user score based on the intent probability distribution, the user portrait and the market environment information includes processing the intent probability distribution, the user portrait and the market environment information through an integrated learning model based on a gradient lifting decision tree to obtain the user score. With reference to the first aspect, in one possible implementation manner, determining a marketing strategy of the broadband service corresponding to the user score includes at least any one of determining a marketing strategy of the broadband service corresponding to the user score based on a first mapping relationship, wherein the first mapping relationship is used for representing a corresponding relationship between the user score and the marketing strategy of the broadband service, determining the marketing strategy of the broadband service according to the probability of installing the broadband service in the user score and the intention probability distribution, determining the marketi