Search

CN-121998674-A - Tag information determining method and device, electronic equipment and medium

CN121998674ACN 121998674 ACN121998674 ACN 121998674ACN-121998674-A

Abstract

The invention discloses a method and a device for determining tag information, electronic equipment and medium teeth, and relates to the technical fields of data statistical analysis, big data and the like. The method comprises the steps of obtaining multiple characteristics and core service indexes of each user in multiple users, obtaining correlation coefficients of the characteristics and the core service indexes based on the multiple characteristics and the core service indexes of each user in the multiple users, obtaining preset number of reference indexes from the multiple characteristics based on the correlation coefficients of the characteristics and the core service indexes, and determining label information based on the preset number of reference indexes and a preset barrel dividing mode.

Inventors

  • NI NA
  • LI LIRAN

Assignees

  • 北京百度网讯科技有限公司

Dates

Publication Date
20260508
Application Date
20251219

Claims (12)

  1. 1. A method of determining tag information, comprising: Acquiring a plurality of characteristics and core service indexes of each user in a plurality of users; Based on a plurality of characteristics and core service indexes of each user in the plurality of users, acquiring a correlation coefficient of each characteristic and the core service index; Acquiring a preset number of reference indexes from the plurality of characteristics based on the correlation coefficient of each characteristic and the core service index; and determining label information based on the preset number of reference indexes and a preset barrel dividing mode.
  2. 2. The method of claim 1, wherein determining tag information based on the preset number of reference indicators and a preset bucket pattern comprises: based on the reference indexes, carrying out dynamic barrel division on a test user data set according to a preset barrel division mode to obtain a barrel division result, wherein the test user data set is a user data set which is acquired from historical behavior data of a plurality of users and comprises a preset number of reference indexes; combining the barrel dividing results of the reference indexes to obtain label information based on the preset number of reference indexes and the preset barrel dividing mode; And verifying and determining that the label information based on the preset number of reference indexes and the preset barrel dividing mode is valid based on the reference indexes of the user data.
  3. 3. The method of claim 2, wherein verifying and determining that tag information based on the preset number of reference indicators and the preset bucket pattern is valid based on each of the reference indicators of each of the user data comprises: unsupervised clustering of each of the reference indicators of each of the user data; Acquiring the variance of the core business index of each user data of each cluster and the overall variance of the test user data set; Verifying and determining that label information corresponding to each cluster is valid based on the variance of the core service index of each user data of each cluster and the overall variance of the test user data set; and if the label information of all the clusters is valid, determining that the label information based on the preset number of reference indexes and the preset barrel dividing mode is valid.
  4. 4. The method of claim 1, wherein each of the plurality of features of the user comprises at least one of a browsing feature of the user, a transaction feature of the user, and a master site feature of the user; The browsing characteristics of the user comprise at least one of watching and broadcasting days, watching and broadcasting time length, watching and broadcasting times, intention categories, browsing commodity numbers and commodity card click rate in a preset time length before the current moment; The transaction characteristics of the user comprise transaction total amount paid by the user within a preset time length before the current moment, total number of orders, number of days to place, price of customers, order occupation rate of platform subsidy, refund order rate, concentration of purchased commodity class and cross-class purchase behavior characteristics; The master station characteristics of the user comprise at least one of activity of the master station at the current moment of the user, use depth of the user, login days in a preset time length before the current moment, continuous check-in days, application push opening rate, product comment issuing times, sun list times, platform activity participating times and the number of successful invitation of new users.
  5. 5. The method of claim 1, wherein obtaining a correlation coefficient for each of the features and the core traffic index based on a plurality of features and core traffic index for each of the plurality of users comprises: Determining the type of the value of each of the features; determining the type of the correlation coefficient based on the type of the value of each of the features; and analyzing the correlation coefficient of the corresponding type based on a plurality of characteristics and core service indexes of each user in the plurality of users.
  6. 6. The method of claim 5, wherein determining the type of correlation coefficient based on the value type of each of the features comprises: if the type of the value of the characteristic is numerical, determining that the type of the correlation coefficient is a pearson correlation coefficient; and if the type of the value of the characteristic is text type, determining that the type of the correlation coefficient is a Kendell class correlation coefficient.
  7. 7. The method of claim 1, wherein obtaining a preset number of reference indicators from the plurality of features based on correlation coefficients of each of the features and the core traffic indicator, comprises: And acquiring a preset number of features, of which the correlation coefficient with the core service index is larger than a preset coefficient threshold, and the confidence coefficient also reaches the preset confidence coefficient threshold, from the plurality of features, wherein the confidence coefficient corresponding to each feature is used for identifying the confidence degree that the correlation coefficient of the feature and the core service index is larger than the preset coefficient threshold.
  8. 8. The method of any of claims 1-7, wherein the method further comprises: acquiring the value of each reference index of the target user; and classifying the target users based on the values of the reference indexes of the target users and the determined label information.
  9. 9. A tag information determining apparatus, comprising: The feature acquisition module is used for acquiring a plurality of features and core service indexes of each user in the plurality of users; the coefficient acquisition module is used for acquiring the correlation coefficient of each characteristic and the core service index based on a plurality of characteristics and the core service index of each user in the plurality of users; The index acquisition module is used for acquiring a preset number of reference indexes from a plurality of characteristics of the user based on the correlation coefficient of each characteristic and the core service index; The scheme determining module is used for determining the label information based on the preset number of reference indexes and a preset barrel dividing mode.
  10. 10. An electronic device, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-8.
  11. 11. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-8.
  12. 12. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-8.

Description

Tag information determining method and device, electronic equipment and medium Technical Field The disclosure relates to the technical field of computers, in particular to the technical fields of data statistics analysis, big data and the like, and particularly relates to a method and a device for determining tag information, electronic equipment and a medium. Background In the current e-commerce environment, user size has reached the billion level, and user behavior data has shown explosive growth. The traditional rough operation mode can not meet the market competition requirement, and the fine user layering becomes a key for improving the core competitiveness of the platform. The effective user layering can enable enterprises to deeply understand the characteristics and requirements of different user groups, provide core basis for accurate marketing, personalized recommendation and product optimization, and finally achieve maximization of life cycle value of users. Disclosure of Invention The disclosure provides a method, a device, electronic equipment and a medium for determining tag information. According to an aspect of the present disclosure, there is provided a method of determining tag information, including: Acquiring a plurality of characteristics and core service indexes of each user in a plurality of users; Based on a plurality of characteristics and core service indexes of each user in the plurality of users, acquiring a correlation coefficient of each characteristic and the core service index; Acquiring a preset number of reference indexes from a plurality of characteristics of the user based on the correlation coefficient of each characteristic and the core service index; and determining label information based on the preset number of reference indexes and a preset barrel dividing mode. According to another aspect of the present disclosure, there is provided a tag information determining apparatus including: The feature acquisition module is used for acquiring a plurality of features and core service indexes of each user in the plurality of users; the coefficient acquisition module is used for acquiring the correlation coefficient of each characteristic and the core service index based on a plurality of characteristics and the core service index of each user in the plurality of users; The index acquisition module is used for acquiring a preset number of reference indexes from a plurality of characteristics of the user based on the correlation coefficient of each characteristic and the core service index; The scheme determining module is used for determining the label information based on the preset number of reference indexes and a preset barrel dividing mode. According to still another aspect of the present disclosure, there is provided an electronic apparatus including: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the aspects and methods of any one of the possible implementations described above. According to yet another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of the aspects and any possible implementation described above. According to yet another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method of the aspects and any one of the possible implementations described above. According to the technology disclosed by the invention, the rationality and the accuracy of the determined label information can be effectively improved. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification. Detailed Description The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein: FIG. 1 is a schematic diagram according to a first embodiment of the present disclosure; FIG. 2 is a schematic diagram according to a second embodiment of the present disclosure; FIG. 3 is a schematic diagram according to a third embodiment of the present disclosure; FIG. 4 is a schematic diagram according to a fourth embodiment of the present disclosure; Fig. 5 is a block diagram of an electronic device used to implement the methods of embodiments of the present disclosure. Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate und