CN113792201A - Method and device for pushing information - Google Patents

Abstract

The embodiment of the disclosure discloses a method and a device for pushing information. One embodiment of the method comprises: acquiring behavior data of users in a user group, and determining a classification identifier set aiming at the user group, wherein the classification identifier in the classification identifier set is used for indicating a classification mode of classifying the user group to obtain a sub-user cluster; for the classification marks in the classification mark set, determining the difference degree between the behavior data of the sub-user groups in the sub-user groups corresponding to the classification marks according to the behavior data; selecting a classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree; and pushing information to each sub-user group in the sub-user group corresponding to the target classification identification. The embodiment realizes the personalized pushing of the information.

Description

Method and device for pushing information

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for pushing information.

Background

With the rapid development of network technology, people's lives are gradually and comprehensively shifted to the internet and the mobile internet. The Internet brings convenience to people and also brings the problem of information explosion. For the user, how to find the desired information in the massive information of the internet is a problem to be solved or further optimized.

Based on this, some researchers propose to help users to screen out information desired by users from massive information by using methods such as data mining and data analysis based on big data. At present, many applications such as information applications, social applications, e-commerce platforms, reading applications and the like adopt the means to push or display information screened for users, so as to further improve the experience of the users in the process of using the internet.

For example, some applications or platforms typically assign a corresponding user tag to each user based on mining and analysis of the user's historical behavior data. Furthermore, the users can be divided into user groups respectively corresponding to different labels based on the user labels, so that different services (such as pushing different information and the like) can be respectively provided for the user groups with different labels, and thus, the users can quickly obtain the required services.

Disclosure of Invention

The embodiment of the disclosure provides a method and a device for pushing information.

In a first aspect, an embodiment of the present disclosure provides a method for pushing information, where the method includes: acquiring behavior data of users in a user group, and determining a classification identifier set aiming at the user group, wherein the classification identifier in the classification identifier set is used for indicating a classification mode of classifying the user group to obtain a sub-user cluster; for the classification marks in the classification mark set, determining the difference degree between the behavior data of the sub-user groups in the sub-user groups corresponding to the classification marks according to the behavior data; selecting a classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree; and pushing information to each sub-user group in the sub-user group corresponding to the target classification identification.

In a second aspect, an embodiment of the present disclosure provides an apparatus for pushing information, the apparatus including: the device comprises an acquisition unit, a judgment unit and a display unit, wherein the acquisition unit is configured to acquire behavior data of users in a user group and determine a classification identifier set aiming at the user group, and classification identifiers in the classification identifier set are used for indicating classification modes of classifying the user group to obtain sub-user clusters; a determining unit configured to determine, for a class identifier in the class identifier set, a degree of difference between behavior data of a sub-user group in the sub-user group corresponding to the class identifier according to the behavior data of users in the user group; a selecting unit configured to select a classification identifier from the classification identifier set as a target classification identifier according to the corresponding degree of difference; and the pushing unit is configured to push information to each sub-user group in the sub-user group corresponding to the target classification identifier.

In a third aspect, an embodiment of the present disclosure provides a server, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, which computer program, when executed by a processor, implements the method as described in any of the implementations of the first aspect.

According to the method and the device for pushing the information, the difference between the behavior data of the users in the sub-user groups obtained in each classification mode of the user group is determined through the behavior data of the users in the user group, so that the discrimination between the sub-user groups obtained in each classification mode can be known, the classification mode can be selected according to the difference corresponding to each classification mode, the information can be respectively pushed to each sub-user group corresponding to the classification mode, and therefore flexible control over the classification mode of the user group and flexible control over the information pushed to the users in the user group can be achieved according to different requirements.

Drawings

Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:

FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present disclosure may be applied;

FIG. 2 is a flow diagram for one embodiment of a method for pushing information, according to the present disclosure;

FIG. 3 is a schematic diagram of one application scenario of a method for pushing information according to an embodiment of the present disclosure;

FIG. 4 is a flow diagram for one embodiment of updating target class identifications, according to the present disclosure;

FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for pushing information in accordance with the present disclosure;

FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.

Detailed Description

The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 shows an exemplary architecture 100 to which embodiments of the method for pushing information or the apparatus for pushing information of the present disclosure may be applied.

As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The terminal devices 101, 102, 103 interact with a server 105 via a network 104 to receive or send messages or the like. Various client applications may be installed on the terminal devices 101, 102, 103. For example, browser-like applications, search-like applications, shopping-like applications, social platforms, information-flow-like applications, and the like.

The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.

The server 105 may be a server that provides various services, such as a backend server that provides support for client applications installed on the terminal devices 101, 102, 103. For example, the server 105 may obtain behavior data of users in the user group from the terminal devices 101, 102, and 103, determine difference degrees corresponding to different classification manners for the user group according to the behavior data, select a classification manner for the user group according to the obtained difference degrees, and push information to the sub-user groups obtained by using the selected classification manner.

The behavior data of the users in the user group may be directly stored locally in the server 105, and the server 105 may directly extract and process the behavior data of the users in the user group stored locally, in which case, the terminal apparatuses 101, 102, and 103 and the network 104 may not be present.

It should be noted that the method for pushing information provided by the embodiment of the present disclosure is generally performed by the server 105, and accordingly, the apparatus for pushing information is generally disposed in the server 105.

It should be further noted that the terminal devices 101, 102, and 103 may also obtain behavior data of users in the user group from a local or other storage device, determine difference degrees corresponding to different classification manners of the user group according to the behavior data, select a classification manner for the user group according to the obtained difference degrees, and respectively push information to the sub-user groups obtained by using the selected classification manner. At this time, the method for pushing information may also be executed by the terminal devices 101, 102, 103, and accordingly, the means for pushing information may also be provided in the terminal devices 101, 102, 103. At this point, the exemplary system architecture 100 may not have the server 105 and the network 104.

The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for pushing information in accordance with the present disclosure is shown. The method for pushing the information comprises the following steps:

step 201, acquiring behavior data of users in a user group, and determining a classification identification set for the user group.

In the present embodiment, the user group is composed of users. The user group can be determined according to the actual application requirement. For example, the user group may be specified in advance by a technician or the like. For another example, the user group may be determined according to the filtering condition. Wherein, the screening condition can be flexibly set. As an example, different filtering conditions may be set in advance for different user groups. Then, according to the currently received screening condition, the user group corresponding to the current screening condition may be selected.

The behavior data of the user may refer to various data related to the behavior of the user, and may be determined according to actual application requirements or application scenarios. The user behavior can also be flexibly set according to the actual application requirements or application scenarios. For example, user behavior includes, but is not limited to, browsing behavior, clicking behavior, trading behavior, and the like. As another example, user behavior includes, but is not limited to, one or more browsing behaviors for specified information, one or more trading behaviors for specified information, and the like.

By way of example, where the user behavior comprises browsing behavior, the behavior data of the user may include, but is not limited to: browsing times, browsing duration, browsing occurrence time, etc. Where the user behavior comprises transaction behavior, the behavior data of the user may include, but is not limited to: number of transactions, time of occurrence of transactions, etc.

In this embodiment, an executing entity (e.g., a server shown in fig. 1) of the method for pushing information may obtain behavior data corresponding to each user in a user group from a local or other storage device (e.g., terminal devices 101, 102, 103 shown in fig. 1, or a connected database, etc.).

In this embodiment, the classification flag may be used to indicate a classification manner for the user group. Specifically, the user group may be divided into a number of sub-user groups by classifying the user group, thereby forming a sub-user cluster. Generally, the sub-user clusters obtained by classifying the user group in different classification manners may be different.

The set of class labels may be composed of different class labels. The classification identification set can be determined according to the actual application requirements. For example, the set of class identifications may be pre-specified by a technician or the like. For another example, the classification identifier set may be composed of classification identifiers corresponding to all classification methods for the user group, or may be composed of classification identifiers corresponding to part of the classification methods for the user group.

In this embodiment, the executing entity may obtain the pid set from a local or other storage device, or may receive the pid set input by its user.

Step 202, for the classification identifiers in the classification identifier set, according to the behavior data of the users in the user group, determining the difference between the behavior data of the sub-user groups in the sub-user group corresponding to the classification identifiers.

In this embodiment, the difference degree corresponding to each classification identifier may be used to represent the difference degree between behavior data corresponding to each sub-user group in the sub-user group corresponding to the classification identifier. The behavior data of the sub-user group may refer to behavior data corresponding to each user in the sub-user group.

For example, for a classification identifier, the difference between every two sub-user groups in the sub-user group corresponding to the classification identifier may be determined, and then the average value of all the obtained differences may be calculated as the difference corresponding to the classification identifier. Wherein the degree of difference between any two sub-user groups can be characterized by the number of different user behavior data possessed by the two sub-user groups.

And 203, selecting the classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree.

In this embodiment, various methods can be flexibly adopted to select the classification identifier from the classification identifier set according to the actual application scenario. For example, a category identifier with a corresponding degree of difference greater than a preset degree of difference threshold may be selected from the category identifier set.

And 204, pushing information to each sub-user group in the sub-user group corresponding to the target classification identifier.

In this embodiment, the information may be pushed to each sub-user group in the sub-user group corresponding to the target classification identifier. Specifically, the same or different information may be pushed to each sub-user group according to the behavior data corresponding to each sub-user group. The content of the information pushed for each sub-user group can be determined according to the actual application requirements and/or the behavior data of the users in the sub-user group.

Optionally, the classification identifier corresponding to the maximum difference degree may be selected from the classification identifier set as a target classification identifier, and then, information may be pushed to each sub-user group in the sub-user group corresponding to the target classification identifier. At this time, the behavior data of each sub-user group obtained by dividing the user group according to the classification mode indicated by the target classification identifier has the largest difference, and further, information can be pushed to each sub-user group in a targeted manner according to the differences, so that personalized information pushing of the users in the user group is realized.

In some optional implementation manners of this embodiment, the difference degree corresponding to each classification identifier may be determined according to the behavior data of the users in the user group through the following steps:

step one, for the sub-user group in the sub-user group corresponding to the classification identification, determining the behavior index value of the sub-user group according to the behavior data of the users in the sub-user group.

In this step, the behavior index of the sub-user group may be a behavior index set for the behavior of the user by a pointer, and may be specifically set in advance by a technician according to an actual application requirement. For example, behavioral indicators include, but are not limited to: click rate, conversion rate, retention rate, and the like. The behavior index value of the sub-user group may be determined by performing a statistical analysis or the like on the behavior data of each user in the sub-user group.

Alternatively, the behavior index value of the sub-user group may refer to a behavior index value corresponding to a target period. The target time period can be set according to specific application requirements. For example, the behavior index value may refer to a click rate or conversion rate or retention rate of the user within the last week, which is analyzed statistically. Therefore, the behavior index value of the sub-user group can be determined more flexibly and accurately according to the actually acquired behavior data of the users in the user group.

And step two, determining the difference degree corresponding to the classification identifier according to the behavior index values corresponding to the sub-user groups corresponding to the classification identifier.

In this step, after obtaining the behavior index values corresponding to the sub-user groups corresponding to the classification identifiers, various methods can be flexibly adopted to determine the degree of difference corresponding to the classification identifiers. For example, the variance or standard deviation of the behavior index value corresponding to each sub-user group may be calculated, and the obtained variance or standard deviation may be used to characterize the degree of difference corresponding to the category identifier.

The behavior index value due to the user group may reflect some attributes of the users in the user group. For example, click-through rates, conversion rates, etc. may reflect user preferences, etc. Therefore, the difference degree corresponding to the classification identifier is determined based on the behavior index value of each corresponding sub-user group, so that the difference of attributes such as the preference of the user in each sub-user group corresponding to the classification identifier can be accurately represented, and different services can be provided for the users with different attributes respectively, and the service quality is improved.

Optionally, the difference degree corresponding to each category identifier may be determined according to the behavior index value corresponding to each sub-user group corresponding to each category identifier by the following steps:

step one, the behavior index values corresponding to the sub-user groups corresponding to the classification identification are sequentially arranged to obtain a behavior index value sequence.

In this step, the behavior index values corresponding to the respective sub-user groups may be sequentially arranged according to the magnitude relationship of the corresponding behavior index values. For example, the behavior index values corresponding to the respective sub-user groups may be arranged in ascending order from small to large.

And step two, determining the difference value of the adjacent behavior index values in the behavior index value sequence.

In this step, the difference between each set of two adjacent behavior index values in the index value sequence may be calculated. As an example, if the index value sequence includes a first index value, a second index value, and a third index value, a difference between the first index value and the second index value, and a difference between the second index value and the third index value are determined, respectively. In general, the difference may be a non-negative number.

And step three, determining the difference degree corresponding to the classification identification according to the determined difference value.

In this step, various methods may be used to determine the degree of difference corresponding to the classification identifier according to the obtained difference values. For example, the variance or the average difference or the sum of the obtained differences may be calculated, and the calculated variance or the average difference or the sum may be used to characterize the degree of difference corresponding to the classification identifier.

For another example, for each set of two adjacent behavior index values, an adjacent difference fraction of the two behavior index values of the set may be calculated, wherein the adjacent difference fraction may represent a ratio of a difference of the two behavior index values to a larger behavior index value. Then, a sum of adjacent difference ratios respectively corresponding to each group of adjacent behavior index values may be calculated, and the calculated sum is used to characterize a difference degree corresponding to the classification identifier.

The user difference between the two sub-user groups can be more accurately represented by utilizing the adjacent difference proportion, so that the difference between the sub-user groups corresponding to each classification identifier can be more accurately represented, and the accuracy of the difference degree of the classification identifiers is improved.

In some optional implementations of this embodiment, the classification manner indicated by the class identifier in the class identifier set is used to classify the user group according to the time characteristic or the frequency characteristic of the target behavior of the user.

The target behavior may be various behaviors of the user, and may be determined in advance by a technician according to an actual application requirement. Temporal features may refer to features that are related to the time of occurrence of a target behavior of a user. For example, the temporal features may be characterized directly using the time of occurrence of the target behavior of the user. A frequency characteristic may refer to a characteristic related to the frequency with which a target behavior of a user occurs. For example, the frequency signature may be characterized using a frequency with which the user performs the target behavior.

Alternatively, the temporal features may be characterized using a time difference between a most recent occurrence time of the target behavior of the user and the target time. The target time can be flexibly set according to actual application requirements or application scenes. For example, the target time may be the current time or a preset time.

When classifying the user group according to the time characteristics, the classification of the users in the user group can be specifically realized by segmenting the time. For example, the temporal characteristics indicate the number of days between the user's last browsing activity and a preset date. Different classifications of user groups can be achieved at this time by different divisions of the number of days between the user's most recent browsing behavior and the preset date.

As an example, the classification identifier may be (3, 7,14), and the classification manner indicated by the classification identifier may divide the user group into 4 categories. The users with the number of days between the latest browsing behavior and the preset date within 3 days are in a first category, the users with the number of days between the latest browsing behavior and the preset date within 3 days are in a second category, the users with the number of days between the latest browsing behavior and the preset date within 7 days and 14 days are in a third category, and the users with the number of days between the latest browsing behavior and the preset date exceeding 14 days are in a fourth category.

Alternatively, the frequency signature may be characterized by a frequency with which the user performs the target behavior over the target time period. The target time period can be flexibly set according to specific application requirements. For example, the target time period may be within the last week or within the last year.

When classifying the user group according to the frequency characteristics, the classification of the users in the user group can be realized by specifically segmenting the frequency. For example, the frequency signature indicates the number of transactions that the user has performed within the last year. Different classifications of user groups can now be achieved by different divisions of the number of transaction activities within the user's last year.

As an example, the classification flag may be (5, 20), and the classification manner indicated by the classification flag may divide the user group into 3 categories. The users with the transaction behavior frequency within 5 times in the last year are in the first category, the users with the transaction behavior frequency within 5 times to 20 times in the last year are in the second category, and the users with the transaction behavior frequency exceeding 20 times in the last year are in the third category.

At this time, the acquired behavior data of the users in the user group may include data of a time characteristic or a frequency characteristic characterizing the target behavior of the user.

In some optional implementations of this embodiment, the user group may be determined according to the target object. For example, the relationship between the user group and the target object may be set in advance. At this time, the corresponding user group may be searched according to the target object. Specifically, a user group corresponding to a target object may be determined according to a pre-specified target object or a target object indicated by a currently received instruction, so as to obtain behavior data of users in the user group. At this time, the behavior data of the user in the user group may refer to the behavior data of the user with respect to the target object. Thereby, a classification of the relevant user group of the target object may be achieved.

The target object may be any object. For example, the target object may be various goods or services, and the like. As an example, when a target object is characterized using a specified category, the target object is all goods or services and the like included under the category.

Optionally, an information push request for a target object may be received, behavior data of users in the user group for the target object may be acquired, and then a target classification identifier may be selected from the classification identifier set according to the acquired behavior data, so as to push relevant information of the target object to each sub-user group in the sub-user group corresponding to the target classification identifier.

The target object may be any object. The user group may be composed of all or a portion of the users having the target behavior for the target object. The target behavior can be set according to a specific application scenario. Therefore, the user groups of the target objects can be flexibly classified, and the personalized push of the related information of the target objects is realized.

At this time, the corresponding relationship between the target object and the target classification identifier may be further stored.

In some optional implementations of the embodiment, the users in the user group belong to the same user category, and the user category is determined according to the behavior data of the users in the user group. At this time, the category identifiers in the category identifier set are used to indicate that the users are further sub-classified according to the behavior data of the users to determine the sub-category to which each user in the user group belongs.

For example, a user pushed with the related information of the target object belongs to a first category, a user browsing the related information of the target object belongs to a second category, a user performing a transaction action for the target object belongs to a third category, and a user performing a transaction action for the target object for a number of times greater than a preset threshold value belongs to a fourth category. In this case, the user group of the target object may be first divided into four categories according to the classification.

Then, for each category of user group, the method of step 201 and step 204 may be executed to determine the classification manner of the sub-user group, and then perform targeted information pushing according to the determined classification manner.

In many cases, the number of users is enormous, and even after classifying the users, the number of users included in the user group of each category is still very large. At this time, by further subdividing the user groups of each category, information pushing can be performed on each user more specifically, and the accuracy of information pushing is improved.

In some optional implementation manners of this embodiment, after the target classification identifier is selected from the classification identifier set, classification result information of the classification manner indicated by the target classification identifier for the user group may be further displayed.

The classification result information may refer to various information related to the classification result. For example, the classification result information may include sub-user clusters obtained by dividing the user group according to the target classification identifier.

Optionally, the classification result information may include attribute information of the sub-user cluster corresponding to the target classification identifier. The attribute information of the sub-user cluster may refer to information for describing various features of the sub-user cluster. For example, the attribute information of the sub-user group may include attribute information corresponding to each sub-user group. The attribute information of the sub user group may refer to information for describing various characteristics of the sub user group. For example, the attribute information of the sub-user group includes the number of users included in the sub-user group, the ratio of the number of included users to the total number of users included in the sub-user group, and the like.

Optionally, the attribute information of the sub-user clusters may further include behavior index values corresponding to the sub-user clusters, a difference degree corresponding to the sub-user clusters, and the like.

In addition, various data such as behavior data of users in the user group may be stored in the database in advance and updated in real time. The steps 201 and 204 may be executed in real time according to the stored data, or may be executed offline.

The database may store various data of users in the user group according to actual application requirements and application scenarios. For example, when the user has a transaction behavior, various data such as the transaction amount of the user and the transaction frequency in the last year are stored together with the transaction time of the user. In some cases, the transaction time may also include a transaction start time, a transaction end time, a transaction duration, and the like.

Alternatively, the classification identifier set may be composed of classification identifiers corresponding to all or selected classification manners for the user group. At this time, the classification identifier corresponding to a better classification manner can be selected from the classification identifier set to assist information push for users in the user group.

With continued reference to fig. 3, fig. 3 is an exemplary application scenario 300 of the method for pushing information according to the present embodiment. In the application scenario of fig. 3, the executing agent 301 may receive an input book category "a" and then obtain user identifications having interactions for books under category "a" from the database 302 to form a user group 303. Wherein each user identification may be used to identify a user.

The execution agent 301 may also receive two classification identifications as input: (3,10) and (7, 14). Wherein, the classification marks (3,10) are used for classifying the users into three types according to the time distance between the time of browsing the books of the category "A" and the days before the week (namely browsing interval days): the browsing interval days are within 3 days, the browsing interval days are between 3 days and 10 days, and the browsing interval days exceed 10 days.

The classification identifiers (7,14) are used for classifying the users into three categories according to the browsing interval days of the users: the browsing interval days are within 7 days, the browsing interval days are between 7 days and 14 days, and the browsing interval days exceed 14 days.

The database 302 also stores the browsing interval days and purchasing behavior of each user. Wherein, the purchasing behavior is used to indicate whether the user has purchasing behavior for the book of category "a" within the last week.

For the category identification (3,10), the user group 303 is divided into a first sub-user group, a second sub-user group and a third sub-user group according to the browsing interval days of the users stored in the database 302. Then, according to the purchasing behavior of the users stored in the database 302, the conversion rate of each sub-user group is determined by the ratio of the number of users having purchasing behavior in the sub-user group to the total number of users included in the sub-user group. Then, the difference corresponding to the classification identifier (3,10) is calculated according to the conversion rates corresponding to the first sub-user group, the second sub-user group, and the third sub-user group, and the specific calculation method may refer to the related description in the embodiment of fig. 2, which is not described herein again.

Likewise, for the classification identifiers (7,14), the user group 303 is divided into a fourth sub-user group, a fifth sub-user group and a sixth sub-user group according to the browsing interval days of the users stored in the database 302. Then, according to the purchasing behavior of the users stored in the database 302, the conversion rate of each sub-user group is determined by the ratio of the number of users having purchasing behavior in the sub-user group to the total number of users included in the sub-user group. And then, calculating the difference degrees corresponding to the classification marks (7,14) according to the conversion rates respectively corresponding to the first sub-user group, the second sub-user group and the third sub-user group.

And selecting the classification mark (3,10) corresponding to the larger difference degree from the classification marks (3,10) and the classification marks (7,14) according to the difference degrees corresponding to the classification marks (3,10) and the classification marks respectively. Then, different push information is set for the first sub-user group, the second sub-user group and the third sub-user group respectively, the first push information is pushed to the users in the first sub-user group, the second push information is pushed to the users in the second sub-user group, and the third push information is pushed to the users in the third sub-user group.

In the prior art, a corresponding user tag is generally assigned to each user, users with the same user tag form a corresponding user group, and then a new user group is generated through operations such as intersection, union and difference of the user group so as to correspond to intersection, union and difference of the user tags, and then information is pushed to the new user group.

In the method provided by the above embodiment of the present disclosure, the classification identifier whose corresponding difference meets the requirement is selected, and the user group can be divided into a plurality of sub-user groups according to the classification manner corresponding to the classification identifier, so that the user group can be flexibly classified, and users with larger behavioral data difference in the user group can be distinguished. Based on the above, information can be further pushed to each divided sub-user group, so that personalized information pushing for users in the user group is realized.

After the classification mode indicated by the target classification identifier is shown for the classification result information of the user group, the target classification identifier can be further updated according to requirements. Referring specifically to FIG. 4, a flow 400 of one embodiment for updating a target class identifier is shown. The flow 400 of the method for pushing information comprises the following steps:

step 401, in response to receiving a modification request for a target class identifier, receiving a modified class identifier.

In this embodiment, after browsing the classification result information corresponding to the target classification identifier, the user may send a modification request for requesting to modify the target classification identifier to the execution main body according to the requirement. At the same time, the user may send the execution principal the classification identification that he desires to modify.

And 402, determining and displaying classification result information corresponding to the modified classification identifier.

In this embodiment, the executing entity may determine the classification result information corresponding to the modified classification identifier by using the method disclosed in fig. 2 for the embodiment. For details, reference may be made to the related description in the corresponding embodiment of fig. 2, which is not repeated herein.

Optionally, the execution subject or other electronic device may determine and store the classification result information corresponding to the modified classification identifier in advance by using the method disclosed in fig. 2 for the corresponding embodiment. At this time, the execution main body can directly acquire and display the classification result information corresponding to the pre-stored and modified classification identifier.

In response to receiving an update request for the target class identifier, the target class identifier is updated with the modified class identifier, step 403.

In this embodiment, the user may compare the classification result information corresponding to the original target classification identifier and the modified classification identifier, and if the classification result information corresponding to the modified classification identifier is more desirable, may send a request for requesting to update the target classification identifier to the execution main body. The executing agent may then update the original target class identifier to the user-modified class identifier.

Optionally, if the classification result system information corresponding to the modified classification identifier is not satisfactory, the original target classification identifier may be kept unchanged. Alternatively, the steps 401 and 403 may be continued until the target user identifier is updated to a classification identifier that is more desirable.

Optionally, after the target classification identifier is updated, information may be further pushed to each sub-user group in the sub-user group corresponding to the target classification identifier. The specific pushing method may refer to the related description in the embodiment corresponding to fig. 2, and is not described herein again.

It should be noted that, for the content not specifically described in this embodiment, reference may be made to the related description in the embodiment corresponding to fig. 2, and details are not described herein again.

The method for pushing information provided by the above embodiment of the present disclosure may select, from the set of classification identifiers, a classification identifier having a better classification result, and display the classification result information of the selected classification identifier to a user, meanwhile, the user may modify the classification identifier according to a requirement, and view the classification result information corresponding to the modified classification identifier, and then may select, by comparing the classification result information corresponding to different classification identifiers, a classification identifier whose corresponding classification result information is more in line with an expected classification identifier as a target classification identifier, and implement more accurate information pushing based on the target classification identifier.

With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present disclosure provides an embodiment of an apparatus for pushing information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.

As shown in fig. 5, the apparatus 500 for pushing information provided by the present embodiment includes an obtaining unit 501, a determining unit 502, a selecting unit 503, and a pushing unit 504. The obtaining unit 501 is configured to obtain behavior data of users in a user group, and determine a classification identifier set for the user group, where a classification identifier in the classification identifier set is used to indicate a classification manner of classifying the user group to obtain a sub-user cluster; the determining unit 502 is configured to determine, for a class identifier in the class identifier set, a degree of difference between behavior data of a sub-user group in the sub-user group corresponding to the class identifier according to behavior data of users in the user group; the selecting unit 503 is configured to select a classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree; the pushing unit 504 is configured to push information to each sub-user group in the sub-user group corresponding to the target classification identification.

In the present embodiment, in the apparatus 500 for pushing information: the specific processing of the obtaining unit 501, the determining unit 502, the selecting unit 503 and the pushing unit 504 and the technical effects thereof can refer to the related descriptions of step 201, step 202, step 203 and step 204 in the corresponding embodiment of fig. 2, which are not described herein again.

In some optional implementations of the present embodiment, the determining unit 502 is further configured to: for the sub-user group in the sub-user group corresponding to the classification identifier, determining a behavior index value of the sub-user group according to the behavior data of the users in the sub-user group; and determining the difference degree corresponding to the classification identifier according to the behavior index values corresponding to the sub-user groups corresponding to the classification identifier.

In some optional implementations of the present embodiment, the determining unit 502 is further configured to: sequentially arranging the behavior index values corresponding to the sub-user groups corresponding to the classification identification to obtain a behavior index value sequence; determining a difference value of adjacent behavior index values in the behavior index value sequence; and determining the difference degree corresponding to the classification identification according to the determined difference value.

In some optional implementations of this embodiment, the classification manner indicated by the classification identifier in the classification identifier set is used to classify the user group according to a time characteristic or a frequency characteristic of the target behavior of the user.

In some optional implementations of the embodiment, the time characteristic is used to characterize a time difference between a latest occurrence time of the target behavior of the user and the target time, and the frequency characteristic is used to characterize an occurrence frequency of the target behavior of the user in the target time period.

In some optional implementations of the present embodiment, the apparatus 500 for pushing information further includes a receiving unit (not shown in the figure) configured to receive an information pushing request for a target object; and the above-mentioned obtaining unit 501 is further configured to obtain behavior data of users in the user group with respect to the target object.

In some optional implementation manners of this embodiment, the users in the user group belong to the same user category, where the user category is determined according to the behavior data of the users in the user group; and the classification identifiers in the classification identifier set are used for indicating the classification of the user group so as to determine the user sub-category to which the users in the user group belong.

In some optional implementations of the embodiment, the apparatus 500 for pushing information further includes a presentation unit (not shown in the figure) configured to present classification result information of the user group for a classification manner indicated by the target classification identifier, where the classification result information includes attribute information of a sub-user cluster corresponding to the target classification identifier.

In some optional implementations of the present embodiment, the apparatus 500 for pushing information further includes an updating unit (not shown in the figure) configured to: receiving a modified classification identifier in response to receiving a modification request for the target classification identifier; determining and displaying classification result information corresponding to the modified classification identification; in response to receiving an update request for the target class identifier, the target class identifier is updated with the modified class identifier.

The apparatus provided in the foregoing embodiment of the present disclosure acquires, by an acquiring unit, behavior data of users in a user group, and determines a classification identifier set for the user group, where a classification identifier in the classification identifier set is used to indicate a classification manner in which a sub-user cluster is obtained by classifying the user group; the determining unit determines the difference degree between the behavior data of the sub-user groups in the sub-user groups corresponding to the classification identifiers according to the behavior data of the users in the user groups for the classification identifiers in the classification identifier set; the selecting unit selects the classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree; the pushing unit pushes information to each sub-user group in the sub-user group corresponding to the target classification identifier, so that the classification identifier with the difference degree meeting the requirement can be selected, the user group is divided into a plurality of sub-user groups according to the classification mode corresponding to the classification identifier, and the user group is flexibly classified. Meanwhile, information can be respectively pushed to each sub-user group obtained by division, and different information pushing of users in the user groups is achieved.

Referring now to FIG. 6, a schematic diagram of an electronic device (e.g., the server of FIG. 1) 600 suitable for use in implementing embodiments of the present disclosure is shown. The server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure.

It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer readable medium may be embodied in the server; or may exist separately and not be assembled into the server. The computer readable medium carries one or more programs which, when executed by the server, cause the server to: acquiring behavior data of users in a user group, and determining a classification identifier set aiming at the user group, wherein the classification identifier in the classification identifier set is used for indicating a classification mode of classifying the user group to obtain a sub-user cluster; for the classification marks in the classification mark set, determining the difference degree between the behavior data of the sub-user groups in the sub-user groups corresponding to the classification marks according to the behavior data; selecting a classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree; and pushing information to each sub-user group in the sub-user group corresponding to the target classification identification.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor comprises an acquisition unit, a determination unit, a selection unit and a pushing unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, a push unit may also be described as a "unit that pushes information to each sub-user group in the corresponding sub-user group identified by the target classification".

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims (12)

1. A method for pushing information, comprising:

acquiring behavior data of users in a user group, and determining a classification identifier set aiming at the user group, wherein the classification identifier in the classification identifier set is used for indicating a classification mode of classifying the user group to obtain a sub-user group;

for the classification marks in the classification mark set, determining the difference degree between the behavior data of the sub-user groups in the sub-user groups corresponding to the classification marks according to the behavior data;

selecting a classification identifier from the classification identifier set as a target classification identifier according to the corresponding difference degree;

and pushing information to each sub-user group in the sub-user group corresponding to the target classification identification.

2. The method of claim 1, wherein determining the degree of difference between the behavior data of the sub-user groups in the sub-user group corresponding to the classification identifier according to the behavior data comprises:

for the sub-user group in the sub-user group corresponding to the classification identifier, determining a behavior index value of the sub-user group according to the behavior data of the users in the sub-user group;

and determining the difference degree corresponding to the classification identifier according to the behavior index values corresponding to the sub-user groups corresponding to the classification identifier.

3. The method according to claim 2, wherein the determining the degree of difference corresponding to the classification identifier according to the behavior index value corresponding to each sub-user group in the sub-user group corresponding to the classification identifier comprises:

sequentially arranging the behavior index values corresponding to the sub-user groups corresponding to the classification identification to obtain a behavior index value sequence;

determining a difference value of adjacent behavior index values in the behavior index value sequence;

and determining the corresponding difference degree of the classification identification according to the difference value.

4. The method of claim 1, wherein the classification indicated by the classifiers in the set of classifiers is used to classify the user group according to a temporal characteristic or a frequency characteristic of a target behavior of the user.

5. The method of claim 4, wherein the time characteristic is used to characterize a time difference between a most recent occurrence of the target behavior of the user and a target time, and the frequency characteristic is used to characterize a frequency with which the user performs the target behavior within a target time period.

6. The method of claim 1, wherein the method further comprises:

receiving an information push request aiming at a target object; and

the acquiring of the behavior data of the users in the user group includes:

and acquiring the behavior data of the users in the user group aiming at the target object.

7. The method according to one of claims 1 to 6, wherein the users in the user group belong to the same user category, wherein the user category is determined from the behavior data of the users in the user group; and

the classification identifiers in the classification identifier set are used for indicating the user groups to be classified finely so as to determine the user sub-categories to which the users in the user groups belong.

8. The method according to one of claims 1-6, wherein the method further comprises:

and displaying classification result information of the classification mode indicated by the target classification identifier aiming at the user group, wherein the classification result information comprises attribute information of a sub-user cluster corresponding to the target classification identifier.

9. The method of claim 8, wherein after presenting the classification result information of the classification manner indicated by the target classification identifier for the user group, the method further comprises:

receiving a modified class identifier in response to receiving a modification request for the target class identifier;

determining and displaying classification result information corresponding to the modified classification identification;

in response to receiving an update request for the target class identifier, updating the target class identifier with the modified class identifier.

10. An apparatus for pushing information, wherein the apparatus comprises:

the device comprises an acquisition unit, a judgment unit and a processing unit, wherein the acquisition unit is configured to acquire behavior data of users in a user group and determine a classification identifier set aiming at the user group, and classification identifiers in the classification identifier set are used for indicating classification modes of classifying the user group to obtain sub-user clusters;

a determining unit configured to determine, for a class identifier in the class identifier set, a degree of difference between behavior data of a sub-user group in a sub-user group corresponding to the class identifier according to the behavior data;

a selecting unit configured to select a classification identifier from the classification identifier set as a target classification identifier according to the corresponding degree of difference;

and the pushing unit is configured to push information to each sub-user group in the sub-user group corresponding to the target classification identifier.

11. A server, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.

12. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-9.

Images