CN108830298B - Method and device for determining user feature tag - Google Patents
Method and device for determining user feature tag Download PDFInfo
- Publication number
- CN108830298B CN108830298B CN201810485700.2A CN201810485700A CN108830298B CN 108830298 B CN108830298 B CN 108830298B CN 201810485700 A CN201810485700 A CN 201810485700A CN 108830298 B CN108830298 B CN 108830298B
- Authority
- CN
- China
- Prior art keywords
- user
- determining
- application
- regional
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method and a device for determining a user feature label, which are used for improving the accuracy and comprehensiveness of determining the user feature label and are beneficial to accurately and comprehensively knowing the user requirements. The method comprises the following steps: determining areas where the users are located and application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application; determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area; clustering is carried out on the basis of the areas, the corresponding area attributes, the areas where the users are located, the areas where the users belong and the corresponding user attributes, and a plurality of area user groups are generated; and clustering the application labels of the user terminals installed and applied in the plurality of regional user groups, and determining the characteristic labels of the plurality of regional user groups.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a user feature tag.
Background
With the development of terminals and the internet, users can acquire various internet information, and under the condition of gradually refining the internet information classification, the individuation of user groups is more and more prominent, so that the feature tags of the users are determined, which is particularly important for knowing the requirements of the users.
In general, the feature tag of the user may be determined and the user's needs may be known according to the user's own settings, for example, the feature tag that the user adds in the application program may be obtained, however, not all users may be willing to add the feature tag by himself, so the accuracy of determining the feature tag of the user in this way is low, not comprehensive enough, and is not beneficial to accurately and comprehensively knowing the user's needs.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining a user feature label, which are used for improving the accuracy and comprehensiveness of determining the user feature label and are beneficial to accurately and comprehensively knowing the requirements of a user.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
the embodiment of the application adopts the following technical scheme:
a method of determining a user characteristic label, comprising:
determining areas where the users are located and application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area;
clustering is carried out on the basis of the areas, the corresponding area attributes, the areas where the users are located, the areas where the users belong and the corresponding user attributes, and a plurality of area user groups are generated;
clustering application labels of the user terminals in the plurality of regional user groups for application installation, and determining characteristic labels of the plurality of regional user groups; and the application label is determined according to the application installed by the user terminal.
Preferably, determining the feature labels of the plurality of regional user groups comprises:
and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group.
Preferably, determining the feature labels of the plurality of regional user groups comprises:
sorting the cluster clusters corresponding to the plurality of regional user groups from big to small;
determining a plurality of ranks of a particular cluster in the plurality of regional user groups;
determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio;
and taking the specific cluster corresponding to the target ranking as a feature label of the regional user group corresponding to the target ranking.
And deleting the candidate feature tags with the occurrence frequency exceeding the preset frequency, and taking the remaining candidate feature tags as the feature tags of the plurality of regional user groups.
Preferably, determining the feature labels of the plurality of regional user groups comprises:
determining candidate feature labels of the plurality of regional user groups;
and determining candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group.
Preferably, determining the candidate feature tag corresponding to only the target regional user group as the feature tag of the target regional user group includes:
and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group.
An apparatus for determining a user characteristic tag, comprising: a first determination module, a second determination module, a first clustering module, and a second clustering module, wherein,
the first determining module is used for determining the areas where the users are located and the application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
the second determining module is configured to determine, according to the application installed in the user terminal and the application list corresponding to each area, an area to which the user belongs;
the first clustering module is used for clustering based on the regions, the corresponding region attributes, the regions where the users are located, the regions where the users belong and the corresponding user attributes to generate a plurality of region user groups;
the second clustering module is used for clustering application labels of the user terminals in the plurality of regional user groups for application installation and determining the characteristic labels of the plurality of regional user groups; and the application label is determined according to the application installed by the user terminal.
Preferably, the second clustering module is configured to:
and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group.
Preferably, the second clustering module is configured to:
sorting the cluster clusters corresponding to the plurality of regional user groups from big to small;
determining a plurality of ranks of a particular cluster in the plurality of regional user groups;
determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio;
and taking the specific cluster corresponding to the target ranking as a feature label of the regional user group corresponding to the target ranking.
Preferably, the second clustering module is configured to:
determining candidate feature labels of the plurality of regional user groups;
and determining candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group.
Preferably, the second clustering module is configured to:
and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group.
According to the technical scheme provided by the embodiment, the area where the user is located and the application list of each area can be determined according to the position of the user and the application installed by the user terminal, the area where the user belongs can be determined according to the matching degree of the application installed by the user and each application list, the area where the user is located, the area where the user belongs and the corresponding user attributes can be clustered based on each area and the corresponding area attributes, a plurality of area user groups can be generated, and finally the feature tags of each area user group can be determined based on the tags of the applications installed by the users in each area user group. Compared with the method and the device for determining the user feature label according to the user self-setting, the embodiment of the application can combine the area factor and the factor of the user actually installing the application to generate the area user group in a clustering mode, and then determine the feature of the area user group according to the label of the user installing the application. The accuracy and comprehensiveness of determining the user feature label are improved, and the method is favorable for accurately and comprehensively knowing the requirements of the user.
Drawings
In order to more clearly illustrate the embodiments or prior art solutions of the present application, the drawings needed for describing the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and that other drawings can be obtained by those skilled in the art without inventive exercise.
Fig. 1 is a schematic flowchart of a method for determining a user feature tag according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for determining a user feature tag according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an apparatus for determining a user feature tag according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following embodiments and accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Example 1
The embodiment of the application provides a method for determining a user feature label, which is used for improving the accuracy and comprehensiveness when determining the user feature label, so that the user requirements can be accurately and comprehensively known. The flow diagram of the method is shown in fig. 1, and it is assumed that the execution subject may be a server, including:
step 11: and determining the areas where the users are located and the application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals.
The location information of the user may refer to a location where the user is located when using the terminal, for example, for a mobile terminal, the user may generate the location information by hardware in the mobile terminal during the use process, so that a server executing the method may passively receive the location information uploaded by the terminal, or actively send a request to the terminal, so as to obtain the location information of the terminal.
The terminal-installed Application may refer to an Application (APP) installed to satisfy various requirements during a process of using the terminal by a user. In this step, the location information of the full-network user and the application installed in the full-network user terminal may be acquired. The selection of the users over the network can be determined according to actual requirements, such as worldwide, nationwide, provincial, etc.
In practical applications, for various reasons, the regions may be divided according to different geographic information dimensions, for example, the regions may be divided according to dimensions such as continents, countries, provinces and cities, religions, humanity, and the like, so that a plurality of regions may be divided in advance according to the geographic information in this step, that is, the regions in this step may be divided in advance according to the geographic information, for example, the regions of the number may be divided according to the number of countries all over the world. Each area may be a range represented by location information, for example, the location information may be latitude and longitude information, and each area may be an area composed of a plurality of latitude and longitude information.
After the location information of the user and the pre-divided regions are obtained, the region where the user is located can be determined, for example, china may be a region composed of a plurality of latitude and longitude information, and when the latitude and longitude information of the user falls within the region, the region where the user is located may be considered as china.
The application list corresponding to each area may be a ranking list of the number of times of applications installed in the terminal by the user in each area, for example, if the number of times of the user installing the APP1 in the terminal is the largest in a certain area, the APP1 may be ranked first in the application list in the area, that is, the application list may be determined according to the number of times of the applications installed. The practical significance of the method is that different areas may have different demands for the APP due to differences in development degree, life rhythm, culture and the like, and for users living in the same area, the demands for the APP generally meet the common demands of the area. For example, for a first-line city, the living hinges gather faster and have less idle time, so online shopping APPs and traffic APPs may be very popular, but for a third-line city, the living hinges gather slower and have more idle time, and online shopping APPs and traffic APPs may have less demand. Therefore, an APP list can be determined for each region according to the condition of installing the APP at the user terminal, and the list can contain a preset number of APP lists with the APP installation times in the corresponding region from large to small. And the APP list also embodies the characteristics of the corresponding area to a certain extent.
In practical applications, the area where the user is located and the internet information list corresponding to each area may also be determined according to the behavior record of the user on the internet information in the terminal, for example, the audio list, the video list, the news list, and the like may be determined according to the audio playing record, the video playing record, the news reading record, and the like. However, the behavior records of the internet information are greatly influenced by the flow factors, the accuracy of reflecting the requirements is low, and the APP is generally high in utilization rate in daily life and can accurately reflect the characteristics of the user.
Step 12: and determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area.
In the current society, with the development of transportation and the frequent communication in many fields, users can frequently go in and out of different areas, such as a large number of foreigners, outsiders, etc., which is the embodiment that users frequently go in and out of different areas. Therefore, the area where the user is located does not necessarily represent the area where the user belongs, that is, the area where the user is located, and does not necessarily indicate that the user belongs to the area.
However, as described above, the APP installed in the user terminal can reflect the features of the user more accurately, for example, a foreigner who travels temporarily, the APP installed in the terminal still conforms to the features required by the country, and for foreigners who live in foreign countries, the APP in the terminal has a high possibility that the APP is similar to the features of the place of residence. Specifically, for example, while americans travel in china, the APP in the terminal still meets the requirements of most americans, but americans live in china and the APP installed in the terminal basically meets the requirements of the americans. Therefore, in this step, the area to which the user belongs can be determined according to the APP installed in the user terminal and the application list of each area. Specifically, the APP installed in the user terminal may be matched with the APP list, and a group with the highest matching degree is selected, so as to determine the area to which the user belongs, where the user belongs, may also be referred to as a behavior area, for example, for the area is a country, the behavior country of the user may be determined.
Step 13: and clustering based on each region, the corresponding region attribute, the region where the user is located, the region where the user belongs and the corresponding user attribute to generate a plurality of region user groups.
In practical applications, since the regions are pre-divided, for example, for the case that the regions are countries, but different countries do not mean different characteristics, and it has been described above that the regions where the users are located and the regions where the users belong may not be consistent, the step may perform clustering based on the regions, and the regions where the users are located and the regions where the users belong, to obtain the regional user group.
As described above, when dividing the regions, the regions may be divided according to different dimensions, and specifically, different regions may have different region attributes, such as location, religion, belief, culture, etc., level of income and expense of the region, average age, etc., which may each characterize different characteristics to some extent.
Different user attributes may exist for the user, and specifically, different languages may be set, different brands may be purchased, different time zones may be set, different unlocking manners may be set, and the like when the terminal is used.
Therefore, the clustering may be performed based on the above parameters, and specifically, the clustering may be performed based on the identifier of each region, the region attribute corresponding to each region, the identifier of the region where each user is located in the entire network, the identifier of the region to which the user belongs, and the user attribute corresponding to each user, so as to generate a plurality of region user groups. Specifically, a K-means algorithm can be selected for clustering, the K-means algorithm is a more typical distance-based clustering algorithm, and the distance is used as an evaluation index of similarity, that is, the closer the distance between two objects is, the greater the similarity of the two objects is. The algorithm considers clusters to be composed of objects that are close together, so that a compact and independent cluster (or cluster center) is taken as the final target. Specifically, for example, when each region is a country, 10 to 20 regional user groups are determined by repeated tests.
Step 14: and clustering the application labels of the user terminals installed and applied in the plurality of regional user groups to determine the characteristic labels of the plurality of regional user groups.
In the foregoing step, a plurality of regional user groups have been determined, and as mentioned above, the APP installed by the user terminal can reflect the user's requirements more truly, so that the step can determine the characteristics of the regional user groups according to the APP installed by the user terminal in the regional user groups.
Specifically, the APP tag can be determined for the APP installed at the terminal by the user over the whole network, that is, the APP tag can be determined according to the APP installed at the user terminal. Further, the label of the APP can be determined from the description of the APP by the developer. Specifically, for example, the description of the application may be obtained in a google play application store, so as to extract the description and determine the APP tag. In one embodiment, semantic tag extraction can be performed through algorithms such as TextRank, TFIDF and Rake, or NER named entity recognition can be performed, named entities such as product names in descriptions are extracted, and the two are combined to generate tags of the APP. In practical application, one or both of them can be selected according to actual requirements.
After determining the APP tags, the APP tags of the user terminal installation APPs can be clustered in a plurality of regional user groups, the feature tags of the plurality of regional user groups are determined, specifically, the APP tags can be vectorized through a Glove algorithm first, so that clustering is performed by using a DBSCAN algorithm according to the APP tags vectorized, different clusters are generated, and the different clusters are used as the feature tags, so that the feature tags of the plurality of regional user groups are determined. For example, for a certain regional user group, APP tags of all APPs installed in a terminal by users of the user group may be obtained, vectorized representation is performed on the APP tags, and n cluster clusters are determined through a DBSCAN algorithm, so that n feature tags of the regional user group are determined.
In practical application, a plurality of feature labels can be determined for the regional user groups, but in the clustering result, the size of each clustering cluster is different, and the clustering clusters in the clustering result are different in size, generally, the larger the clustering cluster is, the stronger the feature is, so that the clustering clusters can be sorted from large to small, and the feature can be better embodied before the ranking than after the ranking, so that in an implementation mode, determining the feature labels of the regional user groups can include: and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group. Specifically, the feature labels corresponding to the first preset number of the clustered clusters from large to small may be feature labels that best embody features, for example, the first preset number may be 6, and then the 6 corresponding feature labels with the largest clustered clusters may be determined as the feature labels of the user groups in each area.
In practical applications, there may be a case where a plurality of regional user groups have the same feature tag, for example, a total of 10 regional user groups, and a sports feature tag appears in 6 regional user groups, that is, a sports cluster appears in 6 regional user groups, but as described above, a larger cluster indicates a stronger feature, and accordingly the cluster can be sorted from large to small, so it can be understood that, for the same cluster, a higher rank in a regional user group may represent the feature of the regional user group to a certain extent compared with other regional user groups, and if a lower rank in a regional user group may not represent the feature of the regional user group to a certain extent compared with other regional user groups. Therefore, in one embodiment, determining the feature labels of the plurality of regional user groups may include: sorting the cluster clusters corresponding to the plurality of regional user groups from big to small; determining a plurality of ranks of a specific clustering cluster in a plurality of regional user groups; determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio; and taking the specific cluster corresponding to the target ranking as a characteristic label of the regional user group corresponding to the target ranking. Specifically, after clustering the application labels of the applications installed in the user terminals in each regional user group, a plurality of cluster clusters for each regional user group can be obtained, and accordingly the cluster clusters can be sorted from big to small, the higher the rank is, the more strongly the corresponding feature representing the regional user group is represented, after which at least one specific cluster, such as the sports cluster, thereby determining a plurality of ranks of the specific cluster in a plurality of regional user groups, such as in regional user group 1, the ranking of the sports cluster is 2 nd, in the regional user group 2, the ranking of the sports cluster is 3 rd, in the regional user group 3, the ranking of the sports cluster is 8 th, and the like, and if the sports cluster appears in 6 regional user groups, 6 rankings can be obtained. Further, a target rank may be determined from the 6 ranks, and for the selection of the target rank, the ratio of other ranks lower than the target rank may exceed a predetermined ratio, for example, it may be assumed that the candidate target rank is the 2 nd rank (in the regional user group 1), the predetermined ratio may be 30%, and if the ratio of other ranks lower than the 2 nd rank exceeds 30%, the candidate target rank may be determined as the target rank. Specifically, for example, for this example, if 5 ranks are all lower than the 2 nd rank, the percentage of the other ranks lower than the 2 nd rank is 83.3%, and if it exceeds the predetermined percentage of 30%, it may be determined as the target rank. Finally, the specific cluster corresponding to the target rank may be used as the feature tag of the regional user group corresponding to the target rank, for example, if the specific cluster corresponding to the 2 nd rank is sports, and the regional user group corresponding to the 2 nd rank is regional user group 1, the sports may be used as the feature tag of the regional user group 1. Similarly, it may be further assumed that the candidate target rank is rank 3 (in the regional user group 2), and if 4 ranks are all lower than rank 3, the percentage of the other ranks lower than rank 3 is 66.7%, and also exceeds the predetermined percentage of 30%. Sports may also be used as a feature label for regional user groups 2.
In practical applications, it is possible that the feature tags determined by different regional user groups are the same, for example, for football, the feature tags may exist in a plurality of regional user groups, and for china, the feature tags exist in a plurality of provinces and cities due to rich infrastructure, frequent updating and maintenance, and navigation. In one embodiment, in order to highlight the specificity of the feature tags of the regional user groups and enable the feature tags to further highlight the features of the user groups, the determining the feature tags of the regional user groups may include: determining candidate feature labels of a plurality of regional user groups; and deleting the candidate feature tags with the occurrence frequency exceeding the preset frequency, and taking the remaining candidate feature tags as the feature tags of the plurality of regional user groups. Specifically, the candidate feature tags of the multiple regional user groups may be determined according to a clustering result obtained (by clustering application tags installed and applied in the user terminals in the multiple regional user groups), for example, n candidate feature tags may be determined by the regional user group 1, m candidate feature tags may be determined by the regional user group 2, and p candidate feature tags may be determined by the regional user group 3. And then, searching candidate feature tags with the occurrence frequency exceeding the preset frequency from the candidate feature tags in each region, for example, if the preset frequency can be 4, searching candidate feature tags with the occurrence frequency of 5 times from the candidate feature tags in each region, that is, the candidate feature tags appearing in at least 5 region user groups. If the effect of the candidate labels on the characteristics of the user groups in the embodied areas is not obvious, the candidate labels can be deleted, and the remaining candidate labels are used as the labels of the characteristics of the user groups in the plurality of areas.
In one embodiment, in order to further emphasize the specificity of the feature labels of the regional user groups and make the feature labels more prominently represent the features of the user groups, deleting the candidate feature labels with the occurrence frequency exceeding the preset frequency, and using the remaining candidate feature labels as the feature labels of the plurality of regional user groups, the method may include: and determining the candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group. Specifically, for the purpose of highlighting the feature of the regional user group as much as possible, the candidate feature tag corresponding to only the target regional user group may be determined as the feature tag of the target regional user group. For example, if a candidate feature tag appears only in the regional user group 1, the candidate feature tag may be determined as the feature tag of the regional user group 1.
As described above, the cluster sizes in the clustering result are different, and the features of the clusters closer to the front row position can be better represented than those of the clusters closer to the rear row position. Therefore, in an embodiment, determining the candidate feature tag corresponding to only the target area user group as the feature tag of the target area user group may include: and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group. Specifically, similar to the above description, candidate feature tags only corresponding to the target area user group are selected, and then, from these candidate feature tags, the second predetermined number of candidate feature tags before the cluster is from large to small are selected. For example, if the second predetermined number is 6, the 6 corresponding candidate feature labels that have appeared only in the regional user group 1 and have the largest clustering cluster may be selected as the feature labels of the regional user group 1.
As can be seen from the technical solutions provided in the above embodiments, in this embodiment, the location area of the user and the application list of each area may be determined according to the location of the user and the application installed in the user terminal, the area to which the user belongs may be determined according to the matching degree between the application installed by the user and each application list, and then the location area, the area to which the user belongs, and the corresponding user attributes of each user may be clustered based on each area and the corresponding area attributes to generate a plurality of area user groups, and finally, the feature tags of each area user group may be determined based on the tags of the applications installed in the user groups in each area. Compared with the method and the device for determining the user feature label according to the user self-setting, the embodiment of the application can combine the area factor and the factor of the user actually installing the application to generate the area user group in a clustering mode, and then determine the feature of the area user group according to the label of the user installing the application. The accuracy and comprehensiveness of determining the user feature label are improved, and the method is favorable for accurately and comprehensively knowing the requirements of the user.
Example 2
Based on the same inventive concept, by taking each country in the world as a unit area, the method for determining the user feature tag is provided, and is used for improving the accuracy and comprehensiveness when determining the user feature tag, so that the requirements of the user can be accurately and comprehensively known. The flow chart of the method is shown in fig. 2, and it is assumed that the execution subject may be a server, including:
step 21: and determining the country where the user is located and the application hot list of each country according to the position information of the user and the application installed on the user terminal.
Every country all can have a set of scope of confirming by longitude and latitude information, can be according to user terminal's positional information, determine the country of locating, and through terminal installation's application, can determine each country to the hot list of installation of APP, according to APP installation number of times promptly, the APP that determines is listed as a list of going to the wrong place.
Step 22: and determining the behavior country of the user according to the application installed by the user terminal and the application hot list of each country.
The behavior country may refer to a country to which the user belongs, and may be determined by matching APP installed in the terminal by the user with APP hot lists of various countries.
Step 23: based on the country and the country attribute, the country of the user and the user attribute are clustered, and a plurality of regional user groups are generated.
Clustering can be performed based on the name of a country, religions of the country, beliefs, culture, income and expenditure level, the name of the country where the user is located, the name of the country where the user belongs, terminal equipment of the user, language, time zone, unlocking mode and the like, and a plurality of regional users are generated. Specifically, 10-20 regional user groups can be determined through a K-means algorithm, for example, the regional user groups can be embodied in an actual geographic location and include a plurality of regional user groups such as east asia, south asia, europe, northern europe, central europe, and north america.
Step 24: and clustering the application labels of the user terminals installed and applied in the plurality of regional user groups to determine the characteristic labels of the plurality of regional user groups.
In this step, the APP tags of each APP may be determined by extracting the description of the whole-network application, and when determining the feature tags of the target area user group, the feature tags of each area user group may be determined by clustering based on all the APP tags installed in the target area user group to generate a plurality of clustering centers (clustering clusters), and then by using one of the manners in embodiment 1.
As can be seen from the technical solutions provided in the above embodiments, in this embodiment, the country in which the user is located and the application hot list of each country may be determined according to the location of the user and the application installed in the user terminal, the user behavior country may be determined according to the matching degree between the application installed by the user and each application hot list, and then, based on each country and the corresponding country attributes, the country in which the user is located, the country in which the user belongs, and the corresponding user attributes may be clustered to generate a plurality of regional user groups, and finally, based on the tags of the applications installed by the users in each regional user group, the feature tags of each regional user group may be determined. Compared with the method and the device for determining the user feature label according to the user self-setting, the embodiment of the application can combine the area factor and the factor of the user actually installing the application to generate the area user group in a clustering mode, and then determine the feature of the area user group according to the label of the user installing the application. The accuracy and comprehensiveness of determining the user feature label are improved, and the method is favorable for accurately and comprehensively knowing the requirements of the user.
Example 3
Based on the same inventive concept, embodiment 3 of the present application provides an apparatus for determining a user feature tag, so as to implement the methods described in embodiments 1 and 2. The schematic structural diagram of the device is shown in fig. 3, and the device comprises: a first determination module 31, a second determination module 32, a first clustering module 33, and a second clustering module 34, wherein,
the first determining module 31 may be configured to determine, according to the location information of the user and the application installed in the user terminal, an area where the user is located and an application list corresponding to each area; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
the second determining module 32 may be configured to determine, according to the application installed in the user terminal and the application list corresponding to each area, an area to which the user belongs;
the first clustering module 33 may be configured to perform clustering based on the regions, the corresponding region attributes, and the regions, the regions to which the users belong, and the corresponding user attributes, so as to generate a plurality of region user groups;
the second clustering module 34 may be configured to cluster application tags of applications installed in the user terminals in the multiple regional user groups, and determine feature tags of the multiple regional user groups; and the application label is determined according to the application installed by the user terminal.
In one embodiment, the second clustering module 34 may be configured to:
and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group.
In one embodiment, the second clustering module 34 may be configured to:
sorting the cluster clusters corresponding to the plurality of regional user groups from big to small;
determining a plurality of ranks of a particular cluster in the plurality of regional user groups;
determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio;
and taking the specific cluster corresponding to the target ranking as a feature label of the regional user group corresponding to the target ranking.
In one embodiment, the second clustering module 34 may be configured to:
determining candidate feature labels of the plurality of regional user groups;
and determining candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group.
In one embodiment, the second clustering module 34 may be configured to:
and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group.
As can be seen from the apparatus provided in the foregoing embodiment, in this embodiment, the location area of the user and the application list of each area may be determined according to the location of the user and the application installed in the user terminal, the area to which the user belongs may be determined according to the matching degree between the application installed by the user and each application list, and then the location area, the area to which the user belongs, and the corresponding user attributes of each user may be clustered based on each area and the corresponding area attributes to generate a plurality of area user groups, and finally, the feature tags of each area user group may be determined based on the tags of the applications installed in the user groups in each area. Compared with the method and the device for determining the user feature label according to the user self-setting, the embodiment of the application can combine the area factor and the factor of the user actually installing the application to generate the area user group in a clustering mode, and then determine the feature of the area user group according to the label of the user installing the application. The accuracy and comprehensiveness of determining the user feature label are improved, and the method is favorable for accurately and comprehensively knowing the requirements of the user.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. On the hardware level, the electronic device comprises a processor and optionally an internal bus, a network interface and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form a device for determining the user characteristic label on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
determining areas where the users are located and application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area;
clustering is carried out on the basis of the areas, the corresponding area attributes, the areas where the users are located, the areas where the users belong and the corresponding user attributes, and a plurality of area user groups are generated;
clustering application labels of the user terminals in the plurality of regional user groups for application installation, and determining characteristic labels of the plurality of regional user groups; and the application label is determined according to the application installed by the user terminal.
The method performed by the apparatus for determining a user feature tag according to the embodiment shown in fig. 4 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further perform the functions of the apparatus for determining a user feature tag provided in the embodiment shown in fig. 3 in the embodiment shown in fig. 4, which are not described herein again in this embodiment of the application.
An embodiment of the present application further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method performed by the apparatus for determining a user feature tag in the embodiment shown in fig. 3, and are specifically configured to perform:
determining areas where the users are located and application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area;
clustering is carried out on the basis of the areas, the corresponding area attributes, the areas where the users are located, the areas where the users belong and the corresponding user attributes, and a plurality of area user groups are generated;
clustering application labels of the user terminals in the plurality of regional user groups for application installation, and determining characteristic labels of the plurality of regional user groups; and the application label is determined according to the application installed by the user terminal.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, 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 present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
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 computer storage media 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 that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
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 an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, 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 application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. A method of determining a user profile tag, comprising:
determining areas where the users are located and application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
determining the area to which the user belongs according to the application installed by the user terminal and the application list corresponding to each area;
clustering is carried out on the basis of the areas, the corresponding area attributes, the areas where the users are located, the areas where the users belong and the corresponding user attributes, and a plurality of area user groups are generated;
clustering application labels of the user terminals in the plurality of regional user groups for application installation, and determining characteristic labels of the plurality of regional user groups; the application label is determined according to the application installed by the user terminal;
the determining feature labels of the plurality of regional user groups comprises:
sorting the cluster clusters corresponding to the plurality of regional user groups from big to small;
determining a plurality of ranks of a particular cluster in the plurality of regional user groups; determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio;
and taking the specific cluster corresponding to the target ranking as a feature label of the regional user group corresponding to the target ranking.
2. The method of claim 1, wherein determining the feature labels for the plurality of regional user groups comprises:
and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group.
3. The method of claim 1, wherein determining the feature labels for the plurality of regional user groups comprises:
determining candidate feature labels of the plurality of regional user groups;
and determining candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group.
4. The method of claim 3, wherein determining a candidate feature label corresponding only to a target regional user group as a feature label for the target regional user group comprises:
and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group.
5. An apparatus for determining a user profile tag, comprising: a first determination module, a second determination module, a first clustering module, and a second clustering module, wherein,
the first determining module is used for determining the areas where the users are located and the application lists corresponding to the areas according to the position information of the users and the applications installed on the user terminals; the area is divided in advance according to geographic information, and the application list is determined according to the installation times of the application;
the second determining module is configured to determine, according to the application installed in the user terminal and the application list corresponding to each area, an area to which the user belongs;
the first clustering module is used for clustering based on the regions, the corresponding region attributes, the regions where the users are located, the regions where the users belong and the corresponding user attributes to generate a plurality of region user groups;
the second clustering module is used for clustering application labels of the user terminals in the plurality of regional user groups for application installation and determining the characteristic labels of the plurality of regional user groups; the application label is determined according to the application installed by the user terminal;
the second polymer module is specifically configured to:
sorting the cluster clusters corresponding to the plurality of regional user groups from big to small;
determining a plurality of ranks of a particular cluster in the plurality of regional user groups; determining a target rank in the plurality of ranks, wherein the ratio of other ranks lower than the target rank exceeds a predetermined ratio;
and taking the specific cluster corresponding to the target ranking as a feature label of the regional user group corresponding to the target ranking.
6. The apparatus of claim 5, wherein the second clustering module is to:
and determining the characteristic labels corresponding to the first preset number of the clustering clusters from large to small in each regional user group as the characteristic labels of each regional user group.
7. The apparatus of claim 5, wherein the second clustering module is to:
determining candidate feature labels of the plurality of regional user groups;
and determining candidate feature tags only corresponding to the target area user group as the feature tags of the target area user group.
8. The apparatus of claim 7, wherein the second clustering module is to:
and determining candidate feature labels corresponding to a second preset number of previous feature labels which are only in the target area user group and of which the clustering cluster is from large to small as the feature labels of the target area user group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810485700.2A CN108830298B (en) | 2018-05-21 | 2018-05-21 | Method and device for determining user feature tag |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810485700.2A CN108830298B (en) | 2018-05-21 | 2018-05-21 | Method and device for determining user feature tag |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108830298A CN108830298A (en) | 2018-11-16 |
| CN108830298B true CN108830298B (en) | 2021-07-23 |
Family
ID=64148987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810485700.2A Active CN108830298B (en) | 2018-05-21 | 2018-05-21 | Method and device for determining user feature tag |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108830298B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110191154B (en) * | 2019-04-29 | 2022-03-01 | 创新先进技术有限公司 | User tag determination method and device |
| CN110197402B (en) * | 2019-06-05 | 2022-07-15 | 中国联合网络通信集团有限公司 | User label analysis method, device, equipment and storage medium based on user group |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637178A (en) * | 2011-02-14 | 2012-08-15 | 北京瑞信在线系统技术有限公司 | Music recommending method, music recommending device and music recommending system |
| CN104573304A (en) * | 2014-07-30 | 2015-04-29 | 南京坦道信息科技有限公司 | User property state assessment method based on information entropy and cluster grouping |
| CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
| CN106649380A (en) * | 2015-11-02 | 2017-05-10 | 天脉聚源（北京）科技有限公司 | Hot spot recommendation method and system based on tag |
| CN107704868A (en) * | 2017-08-29 | 2018-02-16 | 重庆邮电大学 | Tenant group clustering method based on Mobile solution usage behavior |
| CN107977445A (en) * | 2017-12-11 | 2018-05-01 | 北京麒麟合盛网络技术有限公司 | Application program recommends method and device |
| CN107992884A (en) * | 2017-11-24 | 2018-05-04 | 武汉科技大学 | A kind of android application permissions cluster and population characteristic analysis method based on big data |
-
2018
- 2018-05-21 CN CN201810485700.2A patent/CN108830298B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102637178A (en) * | 2011-02-14 | 2012-08-15 | 北京瑞信在线系统技术有限公司 | Music recommending method, music recommending device and music recommending system |
| CN104573304A (en) * | 2014-07-30 | 2015-04-29 | 南京坦道信息科技有限公司 | User property state assessment method based on information entropy and cluster grouping |
| CN105869001A (en) * | 2015-01-19 | 2016-08-17 | 苏宁云商集团股份有限公司 | Customized product recommendation guiding method and system |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN106649380A (en) * | 2015-11-02 | 2017-05-10 | 天脉聚源（北京）科技有限公司 | Hot spot recommendation method and system based on tag |
| CN106503269A (en) * | 2016-12-08 | 2017-03-15 | 广州优视网络科技有限公司 | Method, device and server that application is recommended |
| CN107704868A (en) * | 2017-08-29 | 2018-02-16 | 重庆邮电大学 | Tenant group clustering method based on Mobile solution usage behavior |
| CN107992884A (en) * | 2017-11-24 | 2018-05-04 | 武汉科技大学 | A kind of android application permissions cluster and population characteristic analysis method based on big data |
| CN107977445A (en) * | 2017-12-11 | 2018-05-01 | 北京麒麟合盛网络技术有限公司 | Application program recommends method and device |
Non-Patent Citations (2)
| Title |
|---|
| Analysis of power consumer behavior based on the complementation of K-means and DBSCAN;Liping Zhang et al.;《 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2)》;20180104;全文 * |
| 一种基于用户标签的社交网络好友推荐算法;汪强 等;《长沙大学学报》;20180315;第1卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108830298A (en) | 2018-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110874440B (en) | Information pushing method and device, model training method and device, and electronic equipment | |
| CN107589855B (en) | Method and device for recommending candidate words according to geographic positions | |
| CN108268617B (en) | User intention determining method and device | |
| CN115935428A (en) | Information desensitization method, device and system | |
| CN107977445B (en) | Application program recommendation method and device | |
| CN109726280B (en) | Disambiguation method and device for homonyms | |
| CN108416616A (en) | The sort method and device of complaints and denunciation classification | |
| WO2014169672A1 (en) | Method, apparatus and system for pushing micro-blogs | |
| CN113505272B (en) | Control method and device based on behavior habit, electronic equipment and storage medium | |
| CN113010795B (en) | User dynamic image generation method, system, storage medium and electronic device | |
| CN112182391A (en) | User portrait drawing method and device | |
| CN108830298B (en) | Method and device for determining user feature tag | |
| WO2018161719A1 (en) | Method and apparatus for recommending articles to users on basis of regional characteristics | |
| CN112346951B (en) | Service testing method and device | |
| CN116108150A (en) | Intelligent question-answering method, device, system and electronic equipment | |
| CN110909266A (en) | Deep paging method and device and server | |
| CN111639269B (en) | Site recommendation method and device | |
| CN113343069A (en) | User information processing method, device, medium and electronic equipment | |
| CN113343095A (en) | Model training and information recommendation method and device | |
| CN114840762B (en) | Recommended content determining method and device and electronic equipment | |
| CN109241208B (en) | Address positioning method, address monitoring method, information processing method and device | |
| CN105653533B (en) | A kind of method and apparatus updating classification associated set of words | |
| CN110634024A (en) | User attribute marking method and device, electronic equipment and storage medium | |
| CN113254800A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN114048797A (en) | Method, device, medium and electronic equipment for determining address similarity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |