CN-122027593-A - Information pushing method, device, equipment and medium

CN122027593ACN 122027593 ACN122027593 ACN 122027593ACN-122027593-A

Abstract

The invention provides an information pushing method, an information pushing device, information pushing equipment and an information pushing medium, and relates to the technical fields of big data and the like; the method comprises the steps of obtaining information styles of all push numbers in a push number list to obtain target information of all the push numbers based on candidate information, and obtaining target push time of each of a plurality of target information to push the plurality of target information. The method improves the adaptation degree between the information style and the user preference, improves the adaptation degree between the information pushing time and the readable information time of the user, improves the possibility of reading information of the user, improves the pushing precision of target information to the user side where the push number is located, and improves the effectiveness of information transmission by taking the target information as a carrier.

Inventors

CHEN JIACHENG

Assignees

中移互联网有限公司
中国移动通信集团有限公司

Dates

Publication Date: 20260512
Application Date: 20251229

Claims (15)

1. An information pushing method, characterized in that the method comprises: Determining candidate information to be pushed and a push number list from the information push requirement; Acquiring the information style of each push number in the push number list so as to obtain the target information of each push number based on the candidate information; And acquiring the target pushing time of each of the plurality of target information so as to push the plurality of target information.
2. The method of claim 1, wherein the obtaining the information style of each push number in the push number list to obtain the target information of each push number based on the candidate information comprises: obtaining a target user cluster to which each push number belongs in the push number list; determining the information style of each push number according to the user cluster style of the target user cluster; And aiming at any push number, carrying out style conversion on the candidate information according to the information style corresponding to the push number to obtain target information of the push number, wherein the target information is obtained by editing the style and the content of the candidate information based on the information style of the push number and the short message editing condition carried in the information push requirement through the model capability of a large language model.
3. The method of claim 2, wherein the obtaining the target user cluster to which each push number in the push number list belongs comprises: Determining first communication data and second communication data of each user according to communication behavior data of each user in a user cluster, wherein the first communication data at least comprises call month average expense, short message month average receiving quantity and short message month average sending quantity which are included in the communication behavior data, and the second communication data at least comprises resource release short message month average receiving proportion, individual short message month average sending proportion, resource release short message month average unsubscribing quantity and resource release short message unsubscribing proportion in the communication behavior data; clustering the user clusters according to the first communication data to obtain a plurality of group clusters; Clustering the users included in each of the plurality of group clusters according to the second communication data to obtain a plurality of user clusters included in each of the plurality of group clusters; and determining the target user cluster of each push number from the plurality of user clusters.
4. The method of claim 1, wherein the obtaining a target pushing time of each of the plurality of target information to push the plurality of target information comprises: for any target information, a plurality of push information groups are obtained by respectively combining an information style corresponding to the target information with each candidate push time in a plurality of preset candidate push times; Acquiring push evaluation values of the push information in the push information groups, and determining target push time of the target information from the candidate push time according to the push evaluation values; pushing the target information at the target pushing time.
5. The method of claim 4, wherein the obtaining a push evaluation value for each push information in the plurality of push information groups and determining a target push time for the target information from the plurality of candidate push times based on the push evaluation value comprises: Aiming at any piece of target information, according to first resource delivery data of a target enterprise cluster to which a demand initiator of the information push demand belongs, first communication data of a target user cluster to which the target information belongs and load data of a server cluster, respective push evaluation values of a plurality of push information groups corresponding to the target information are obtained, wherein the first resource delivery data is obtained based on resource delivery behavior data of the target enterprise cluster, and the push evaluation values are obtained based on an evaluation model; and determining the candidate push time in any push evaluation value as the target push time of the target information in response to the fact that any push evaluation value meets a set condition.
6. The method of claim 4, wherein pushing the target information at the target push time comprises: Determining a pushing time period to which target pushing time of each target information belongs and a target information set to be pushed in each pushing time period; Determining a pushing sequence of each piece of target information in a target information set corresponding to a pushing time period and a target pushing number corresponding to each piece of target information in the pushing number list according to any pushing time period; And pushing the target information to the corresponding target push numbers according to the push sequence.
7. The method of claim 6, wherein determining, for any push time period, a push order of each target information in the target information set corresponding to the push time period, includes: for any pushing time period, determining a demand initiator corresponding to each piece of target information in a target information set to be pushed in the pushing time period; and determining the push grade of each demand initiator, and determining the push sequence of each target information according to the push grade.
8. The method of claim 7, wherein the determining a push level of each demand initiator and determining a push order of each target information according to the push level comprises: For any pushing time period, determining target information subsets to be pushed by each demand initiator from target information sets corresponding to the pushing time period, so as to obtain information pushing quantity of each demand initiator in the pushing time period; Carrying out set division on each demand initiator based on the information pushing quantity to obtain a plurality of initiator sets; determining respective aggregate service level parameters of the plurality of initiator aggregates, and determining aggregate service orders of the plurality of initiator aggregates according to the aggregate service level parameters; and determining the pushing sequence of each piece of target information according to the set service sequence.
9. The method of claim 8, wherein the grouping the demand initiators based on the information push quantity to obtain a plurality of initiator sets comprises: Determining the minimum information pushing quantity from the information pushing quantities; For any information pushing quantity, acquiring a ratio between the information pushing quantity and the minimum information pushing quantity, and determining a pushing parameter corresponding to a demand initiator corresponding to the information pushing quantity according to the ratio, wherein the pushing parameter is obtained by rounding up based on the ratio; And carrying out set division on each demand initiator according to the push parameters to obtain a plurality of divided initiator sets, wherein the absolute value of the difference value between the sum value of the push parameters of each initiator included in the initiator set i and the sum value of the push parameters of each initiator included in the initiator set j in the plurality of initiator sets is smaller than or equal to a set threshold value.
10. The method according to any one of claims 1-9, further comprising: Based on the set time interval, updating first resource release data of each enterprise in the enterprise cluster, load data of each server cluster and first communication data of each user in the user cluster, so as to push information based on the new first resource release data, the new load data and the new first communication data.
11. The method according to any one of claims 1-9, further comprising: Obtaining corresponding information delivery rewards based on second communication data of users included in each of the plurality of user clusters and second resource delivery data of enterprises included in each of the plurality of enterprise clusters; and carrying out model optimization on the evaluation model for obtaining the pushing evaluation value based on the information throwing rewards to obtain an optimized new evaluation model, and carrying out information pushing based on the new evaluation model.
12. The method of claim 11, wherein obtaining the plurality of enterprise clusters comprises: Determining first resource delivery data and second resource delivery data of each enterprise according to resource delivery behavior data of each enterprise in an enterprise cluster, wherein the first resource delivery data at least comprises business data, business volume grade data, monthly resource delivery expenditure and total unsubscribing proportion of resource delivery short messages, which are included in the resource delivery behavior data, and the second resource delivery data at least comprises short message month average push quantity, short message day average push quantity, month average unsubscribing quantity of resource delivery short messages and immediate unsubscribing proportion of resource delivery short messages in the resource delivery behavior data; clustering the enterprise clusters according to the first resource release data to obtain a plurality of clusters; And clustering enterprises included in the plurality of clusters according to the second resource release data to obtain a plurality of enterprise clusters respectively included in the plurality of clusters.
13. An information pushing apparatus, characterized in that the apparatus comprises: The determining module is used for determining candidate information to be pushed and a push number list from the information push requirement; the acquisition module is used for acquiring the information style of each push number in the push number list so as to acquire the target information of each push number based on the candidate information; The pushing module is used for acquiring the target pushing time of each of the plurality of target information so as to push the plurality of target information.
14. An electronic device, comprising a memory and a processor; Wherein the processor runs a program corresponding to executable program code stored in the memory by reading the executable program code for implementing the method according to any one of claims 1-12.
15. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-12.

Description

Information pushing method, device, equipment and medium Technical Field The disclosure relates to the technical field of big data, and in particular relates to an information pushing method, device, equipment and medium. Background Along with the development of technology, people have higher and higher dependence on mobile phones in work and life, and under the scene, people can acquire favorite objects through mobile phone ends, so that enterprises can carry out information delivery on the mobile phone ends of people to achieve the related propaganda purpose. Therefore, how to accurately deliver information to a mobile phone end used by a user adapting to information content is very important. Disclosure of Invention The object of the present disclosure is to solve at least one of the technical problems in the art described above to some extent. The first aspect of the disclosure provides an information pushing method, comprising the steps of determining candidate information to be pushed and a push number list from information pushing requirements, and acquiring information styles of push numbers in the push number list to obtain target information of the push numbers based on the candidate information; And acquiring the target pushing time of each of the plurality of target information so as to push the plurality of target information. The information pushing method provided in the first aspect of the present disclosure further has the following technical features, including: According to one embodiment of the disclosure, the obtaining the information style of each push number in the push number list to obtain target information of each push number based on the candidate information includes obtaining a target user cluster to which each push number in the push number list belongs, determining the information style of each push number according to the user cluster style of the target user cluster, and performing style conversion on the candidate information according to the information style corresponding to the push number for any push number to obtain the target information of the push number, wherein the target information is obtained by editing style and content of the candidate information based on the information style of the push number and a short message editing condition carried in the information push requirement through model capability of a large language model. According to one embodiment of the disclosure, the method for obtaining target user clusters to which each push number belongs in the push number list comprises the steps of determining first communication data and second communication data of each user according to communication behavior data of each user in a user cluster, wherein the first communication data at least comprise conversation month average cost, short message month average receiving amount and short message month average sending amount which are included in the communication behavior data, the second communication data at least comprise resource release short message month average receiving proportion, personal short message month average sending proportion, resource release short message month average unsubscribing amount and resource release short message unsubscribing proportion in the communication behavior data, clustering the user cluster according to the first communication data to obtain a plurality of group clusters, clustering the users included in the plurality of group clusters according to the second communication data to obtain a plurality of user clusters included in the plurality of group clusters, and determining the target user clusters of each push number from the plurality of user clusters. According to one embodiment of the disclosure, the method for obtaining the target pushing time of each of a plurality of target information to push the plurality of target information includes obtaining a plurality of pushing information groups obtained by respectively combining an information style corresponding to any one target information with each candidate pushing time in a plurality of preset candidate pushing times, obtaining pushing evaluation values of each pushing information in the plurality of pushing information groups, determining target pushing time of the target information from the plurality of candidate pushing times according to the pushing evaluation values, and pushing the target information at the target pushing time. According to one embodiment of the disclosure, the method for obtaining the push evaluation value of each push information in the plurality of push information groups and determining the target push time of the target information from the plurality of candidate push times according to the push evaluation value comprises the steps of obtaining respective push evaluation values of the plurality of push information groups corresponding to the target information according to first resource delivery data of a target enterprise cl