CN111209478A

CN111209478A - Task pushing method and device, storage medium and electronic equipment

Info

Publication number: CN111209478A
Application number: CN202010006758.1A
Authority: CN
Inventors: 邓江; 高玮
Original assignee: JD Digital Technology Holdings Co Ltd
Current assignee: JD Digital Technology Holdings Co Ltd
Priority date: 2020-01-03
Filing date: 2020-01-03
Publication date: 2020-05-29

Abstract

The utility model relates to the technical field of artificial intelligence, in particular to a task pushing method and a device, a computer readable storage medium and an electronic device, wherein the method comprises the steps of obtaining the characteristic information of a plurality of users within the preset time, and clustering the users according to the characteristic information to obtain a plurality of reference user types and a plurality of clustering centers; taking the reference user type to which the target user belongs as the target user type according to the characteristic information of the target user and the clustering center; acquiring a plurality of candidate tasks, and calculating the probability of the candidate tasks to be distributed to the target user type; and judging whether to push the candidate task to the target user according to the probability. The technical scheme of the embodiment of the disclosure improves the accuracy of task pushing, reduces the waste of computing resources, can reduce a lot of unnecessary dispatching and reduces certain cost.

Description

Task pushing method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the technical field of artificial intelligence, and in particular, to a task pushing method and apparatus, a computer-readable storage medium, and an electronic device.

Background

With the rapid development of the computer industry, the user task system is used more and more, and therefore, the requirement for the intellectualization of the user task system is higher and higher.

However, in the process of implementing the present invention, the inventor finds that, when a user task system in the prior art pushes a task, the precision of task distribution is insufficient, which causes many unnecessary task distribution and waste of computing resources.

Therefore, it is necessary to design a new task pushing method and apparatus, a computer readable storage medium and an electronic device

It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.

Disclosure of Invention

The present disclosure aims to provide a task pushing method and apparatus, a computer-readable storage medium, and an electronic device, so as to overcome, at least to a certain extent, the problem that in the related art, when a user task system pushes a task, the precision of task promotion is insufficient, many unnecessary promotions are performed on the task, and the waste of computing resources is caused.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.

According to a first aspect of the present disclosure, a task pushing method includes:

acquiring characteristic information of a plurality of users within preset time, and clustering the users according to the characteristic information to obtain a plurality of reference user types and a plurality of clustering centers;

taking the reference user type to which the target user belongs as a target user type according to the characteristic information of the target user and the clustering center;

acquiring a plurality of candidate tasks, and calculating the probability of the candidate tasks distributed to the target user type;

and judging whether the candidate task is pushed to the target user or not according to the probability.

In an exemplary embodiment of the present disclosure, obtaining feature information of a plurality of users within a preset time, and clustering the users according to the feature information to obtain a plurality of reference user types and a plurality of clustering centers includes:

acquiring characteristic information of a plurality of users from a database;

determining a feature vector according to the feature information;

and clustering the plurality of users according to the characteristic vectors and the clustering centers to obtain a plurality of reference user types.

In an exemplary embodiment of the present disclosure, clustering the plurality of users according to the feature vector and the clustering center to obtain a plurality of reference user types includes:

clustering the plurality of feature vectors by using the plurality of clustering centers to obtain feature vector types;

and dividing the plurality of users into a plurality of reference user types according to the feature vector types.

In an exemplary embodiment of the present disclosure, selecting a reference user type to which a target user belongs as a target task type according to the feature information of the target user includes:

acquiring characteristic information of the target user;

determining a feature vector of the target user according to the feature information;

and according to the feature vector, taking the reference user type corresponding to the clustering center closest to the feature vector as a target user type.

In an exemplary embodiment of the present disclosure, obtaining a plurality of candidate tasks and calculating a probability that the candidate tasks are allocated to the target user type includes:

obtaining a plurality of candidate tasks from a database, wherein each candidate task comprises a plurality of characteristic attributes;

and calculating the probability of the candidate task to be distributed to the target user type by utilizing a deep learning model according to the characteristic attribute.

In an exemplary embodiment of the present disclosure, the method further comprises;

acquiring training data, wherein the training data comprises a plurality of characteristic attributes of sample candidate tasks and a judgment result of whether the sample candidate tasks are distributed to the target user type;

and training a machine learning model based on the training data to obtain the deep learning model.

In an exemplary embodiment of the present disclosure, determining whether to push the candidate task to the target user according to the probability includes:

judging the probability and the preset value;

and if the probability is larger than the preset value, pushing the candidate task corresponding to the probability to the target user as a tippy task.

According to an aspect of the present disclosure, there is provided a task pushing apparatus including:

the acquisition module is used for acquiring the characteristic information of a plurality of users within preset time and clustering the users according to the characteristic information to obtain a plurality of reference user types;

the selection module selects a reference user type to which the target user belongs as a target user type according to the characteristic information of the target user;

the calculation module is used for acquiring a plurality of candidate tasks and calculating the probability of the candidate tasks distributed to the target user type;

and the judging module is used for judging whether the candidate task is pushed to the target user according to the probability.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a task pushing method as in any one of the above.

According to an aspect of the present disclosure, there is provided an electronic device including:

a processor; and

a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the task push method as in any above.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

in the task pushing method provided by the embodiment of the disclosure, users are clustered by analyzing user characteristic information to obtain a reference user type and a plurality of clustering centers, a target user type of a target user is determined, and the probability of the target user type for receiving tasks is calculated to further determine the probability of the target user for receiving the tasks; on the other hand, whether the task is allocated to the target user is determined by calculating the probability that the user type to which the target user belongs receives the task, the task is allocated by comparing more data, and the information of whether the user receives the task is quantized, so that a lot of unnecessary recommendations can be reduced, and the waste of computing resources is reduced. The pushed task can meet the completion intention of the user, and the participation rate of the user is increased.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty. In the drawings:

FIG. 1 is a flow chart of a task pushing method in an embodiment of the disclosure;

FIG. 2 is a flow chart of clustering users in an embodiment of the present disclosure;

FIG. 3 is a flow chart of clustering users according to feature vectors in an embodiment of the present disclosure;

FIG. 4 is a flow chart of calculating probabilities using a deep learning model in an embodiment of the disclosure;

FIG. 5 is a flow diagram of training a machine learning model in an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of data acquisition and data flow in an embodiment of the present disclosure;

FIG. 7 is a block diagram of input data and output data when task assignments are made according to different user types in an embodiment of the disclosure;

FIG. 8 is a schematic diagram illustrating components of a task pushing device according to an exemplary embodiment of the present disclosure;

FIG. 9 schematically illustrates a structural diagram of a computer system suitable for use with an electronic device that implements an exemplary embodiment of the present disclosure;

fig. 10 schematically illustrates a schematic diagram of a computer-readable storage medium, according to some embodiments of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

In the exemplary embodiment, a task pushing method is first provided, which can push tasks more accurately. Referring to fig. 1, the task pushing method may include the following steps:

s110, acquiring characteristic information of a plurality of users within preset time, and clustering the users according to the characteristic information to obtain a plurality of reference user types and a plurality of clustering centers;

s120, taking the reference user type to which the target user belongs as the target user type according to the feature information of the target user and the clustering center;

s130, obtaining a plurality of candidate tasks and calculating the probability of the candidate tasks distributed to the target user type;

and S140, judging whether to push the candidate task to the target user according to the probability.

In the task pushing method provided by the embodiment of the disclosure, users are clustered by analyzing user characteristic information to obtain a reference user type and a plurality of clustering centers, a target user type of a target user is determined, and the probability of the target user type for receiving tasks is calculated to further determine the probability of the target user for receiving the tasks; on the other hand, whether the task is allocated to the target user is determined by calculating the probability that the user type to which the target user belongs receives the task, the task is allocated by comparing more data, and the information of whether the user receives the task is quantized, so that a lot of unnecessary recommendations can be reduced, and the waste of computing resources is reduced. The pushed task can meet the completion intention of the user and increase the participation rate of the user.

Hereinafter, each step of the task pushing method in the present exemplary embodiment will be described in more detail with reference to the drawings and the embodiments.

Step S110, obtaining characteristic information of a plurality of users within preset time, and clustering the users according to the characteristic information to obtain a plurality of reference user types and a plurality of clustering centers.

In an example embodiment of the present disclosure, the server may obtain feature information of the user within a preset time from the database, where the feature information may include a tag of the user and behavior information such as a task receiving rate completion rate of the user, and the tag of the user may represent an identity, an age, and the like of the user, for example, "student", "white collar", "youth", and the like, which are not specifically limited in this example embodiment.

In the present exemplary embodiment, the behavior information of the user may include, in addition to the above-mentioned percentage completion rate of the user to the task, prize information of the user, and the like, and the type of the behavior information of the user is not specifically limited in the present exemplary embodiment; the reward received by the user may include a cash red envelope, a purchase ticket, a payment ticket, a membership voucher, a point reward, and the like, and of course, the reward may also include other types, which is not specifically limited in this exemplary embodiment.

The task receiving rate of the user can be expressed as the ratio of the task received by the user in the same task appearing in a plurality of different time periods to the total task; the completion rate of the user to the task can be expressed as a ratio of the task completed in the same task appearing in a plurality of different time periods of the user to the total task.

Note that, in the present exemplary embodiment, the preset time may be five days, seven days, one month, or the like, and is not particularly limited in the present exemplary embodiment.

In an example embodiment of the present disclosure, clustering the users according to the feature information to obtain a plurality of reference user types and a plurality of cluster centers, as shown in fig. 2, may include steps S210 to S230, which are explained in detail below:

in step S210, feature information of a plurality of users is acquired from a database.

In the present exemplary embodiment, the server determines the feature vector of the feature information obtained from the database, and the content of the feature information has already been described above, and therefore, the description thereof is omitted here. Here, the feature information of one user is taken as an example for explanation, for example, in the present exemplary embodiment, the ages in the tag information may be represented by 1, 2, 3, and the like, for example, a teenager may be represented by 1, a youth may be represented by 2, and the like. The same may be said for the identity of the user by a, b, c, etc., e.g. a may represent a student, b may represent a white collar, etc. The label information may be of various types, and the above description is simply made, and the label information is not specifically limited in the present exemplary embodiment. The user's task acquisition rate can be expressed in a decimal, for example, 0.7, 0.5, etc., and the user's task completion rate can also be expressed in a decimal, for example, 0.8, 0.5, etc.

In step S220, a feature vector is determined according to the feature information.

In this exemplary embodiment, assuming that the feature information of one of the users includes youth, a student, a task obtaining rate of 0.6, and a task completing rate of 0.3, the feature data corresponding to the feature information of the user may be represented as [2, a, 0.6, 0.3], and then the feature data may be converted and normalized to obtain a feature vector, of course, the labels in the feature information of the user and the task obtaining rate and task completing rate of the user may be various, and the feature vector may be obtained in various manners.

In step S230, the users are clustered according to the feature vectors and the clustering centers to obtain multiple reference user types.

In an example embodiment of the present disclosure, a reference user type to which a target user belongs is selected as a target task type according to the feature information of the target user, and as shown in fig. 3, the method may include steps S310 to S320, which are explained in detail as follows:

in step S310, a plurality of feature vectors are clustered by using a plurality of clustering centers to obtain a feature vector type.

In this exemplary embodiment, a k-means clustering algorithm may be adopted to complete clustering of multiple users, and specifically, multiple clustering centers are determined according to points represented by the feature vectors in the multidimensional coordinate system, and the multiple feature vectors are clustered according to distances between the multiple feature vectors and the multiple clustering centers, so as to obtain a feature vector type.

In step S320, the users are classified into a plurality of reference user types according to the feature vector types.

Each feature vector may correspond to one user, and the reference user type may be determined according to the feature vector type, that is, the number of the reference user types is determined by the number of the clustering centers, for example, the number of the clustering centers obtained by using the k-means clustering algorithm is 5, and the number of the reference user types is also 5, and the number of the clustering centers is not specifically limited in the present exemplary embodiment.

Specifically, firstly, the feature vectors are clustered according to points of the feature vectors in a multi-dimensional coordinate system to obtain types of the feature vectors, then the feature vectors are mapped to feature information, and then clustering of multiple users is completed to obtain multiple user types.

In step S120, a reference user type to which the target user belongs is used as the target user type according to the feature information of the target user and the clustering center.

First, feature information of a target user can be obtained from a database, and a feature vector of the target user, content of the feature information, and how to obtain the feature vector are determined according to the feature information of the target user.

In this exemplary embodiment, the server may put the feature vector of the target user into a multidimensional coordinate system, calculate distances between points represented by the feature vector in the multidimensional coordinate system and a plurality of clustering centers, select a clustering center closest to the point represented by the target feature vector in the multidimensional coordinate system as the target clustering center, and determine a reference user type corresponding to the target clustering center as the target user type of the target user.

In step S130, a plurality of candidate tasks are obtained, and the probability of the candidate tasks being assigned to the target user type is calculated.

In an example embodiment of the present disclosure, obtaining a plurality of candidate tasks and calculating a probability that the candidate tasks are allocated to the target user type may include, as shown in fig. 4, the following steps:

s410, acquiring a plurality of candidate tasks from a database, wherein each candidate task comprises a plurality of characteristic attributes;

in this exemplary embodiment, the server may obtain a plurality of candidate tasks from the database, where the candidate tasks may include a personal insurance task, an automobile insurance task, a child education task, an investment and financing task, a finishing industry task, a shopping task, a payment task, a loan task, a game play task, a game recharge task, a content reading task, and the like, and the candidate tasks may be of a wider variety and are not specifically limited in this exemplary embodiment.

The characteristic attributes of the task may include a received rate, a completed rate, a type of reward to the user, and other characteristic attributes, such as a release time of the task, an effective date of the task, an address of the completed task, description information of the task, a state of the task, a type of the set task, a pipeline display information of the task, a service line of the task, and the like, which are not specifically limited in this exemplary embodiment.

And S420, calculating the probability of the candidate task to be distributed to the target user type by using a deep learning model according to the characteristic attribute.

In the present exemplary embodiment, the probability of the candidate task being assigned to the target user type may be calculated using a deep learning model according to the feature attributes in the candidate task described above.

The deep learning model may be obtained by training a naive bayes model, or may be obtained by training other machine learning models, for example, by training a decision tree model, which is not specifically limited in this exemplary embodiment.

In the present exemplary embodiment, as shown with reference to fig. 5, the above method may further include the steps of:

step S510, obtaining training data, wherein the training data comprises a plurality of characteristic attributes of sample candidate tasks and a judgment result of whether the sample candidate tasks are distributed to the target user type;

step S520, training a machine learning model based on the training data to obtain the deep learning model.

Steps S510 to S520 described in detail below.

In this example embodiment, training data may be first obtained from a database, and the training data may include a plurality of feature attributes of the sample candidate task and a determination result of whether the sample candidate task is assigned to the target user type.

In the following, the probability of allocating candidate tasks to a target user through calculation using the foregoing bayesian model is explained in detail through a specific implementation manner, and assuming that feature attributes of the candidate tasks include A, B, C, the probability of allocating a sample candidate task including an a feature attribute to a target user type may be obtained from training data, and similarly, the probability of allocating a sample candidate task including a B feature attribute to a target user type and the probability of allocating a sample candidate task including a C feature attribute to a target user type may also be obtained from training data. Of course, the probability of allocating the sample candidate task to the target user task type may also be calculated according to the training data. When the deep learning model is used for calculation, the correlation probability with respect to the above feature attribute A, B, C can be directly obtained from the deep learning model.

And secondly, calculating the probability of the candidate task comprising A, B, C three characteristic attributes to be allocated to the target user type according to the Bayesian rule.

P (is | a × B × C) may be employed in the present exemplary embodiment to identify the probability of assigning a candidate task including A, B, C three feature attributes to the target user type, and the probability of assigning a candidate task including A, B, C three feature attributes to the target user type may be calculated using a first calculation formula, which may be:

p (is | A X B C) ═ P (A X B C | is) × P (is)/P (A X B C)

Then, bayesian may be used to convert the first calculation formula into a second calculation formula assuming that the feature attributes A, B, C are all independent from each other, where the second calculation formula is:

p (is | a × B × C) ═ P (a | is) × P (B | is) × P (C | is) × P (is)/(P)

(A)*P(B)*P(C))

Wherein P (a | is) represents a probability that a sample candidate task including a feature attribute is assigned to a target user type, and P (B | is) represents a probability that a sample candidate task including a B feature attribute is assigned to a target user type; p (C | is) represents the probability that a sample candidate task including the C feature attribute is assigned to the target user type; p (YES) represents the probability of sample candidate tasks being assigned to the target user in the training data. P (a) represents the probability that a feature attribute is included in the sample candidate task in the training set, p (B) represents the probability that B feature attribute is included, and p (C) represents the probability that C feature attribute is included. In the present exemplary embodiment, "+" may represent the meaning of a multiplication operation.

In training the machine learning model, the server may calculate P (a | is), P (B | is), P (C | is), P (y), P (a), and P from the training data

(B) And p (c) and calculating the probability of the candidate task being assigned to the target user according to an expression about the probability of the candidate task being assigned to the target user type obtained by the characteristic attribute, the expression may be an expression similar to the second calculation formula.

It should be noted that the deep learning model includes the correlation probabilities of all feature attributes included in the candidate task and the expression of the probability that the candidate task is allocated to the target user type obtained through the feature attributes.

The characteristic attribute A, B, C may be a range value, and the characteristic attribute a may indicate that the extraction rate is 40% or more and 50% or less, for example. A specific value may be expressed, and is not particularly limited in the present exemplary embodiment.

The number of feature attributes of the candidate tasks may be different, so that different candidate tasks are included in the training data to cover feature attributes in all candidate tasks.

When the deep learning model is used, the probability of the candidate task being allocated to the target user type can be obtained only by inputting the characteristic attribute of the candidate task.

It should be noted that, in the present exemplary embodiment, there may be a plurality of types of deep learning models, that is, different machine learning models may be used for training to obtain a deep training model, and there may also be a plurality of types of training processes.

In step S140, it is determined whether to push the candidate task to the target user according to the probability.

In the present exemplary embodiment, the probability of the candidate task being assigned to the target user type is calculated by the deep learning model, and then whether to push the task to the target user may be determined according to the probability.

In an example embodiment, a preset value may be set, and whether to push the candidate task to the target user may be determined according to a magnitude relationship between the probability and the preset value; the candidate tasks with the probability greater than the preset value can be pushed to the target user. The target user has high possibility of receiving the candidate task with high probability, so that unnecessary pushing operation can be avoided, and certain pushing cost is reduced.

In another exemplary embodiment, the probabilities corresponding to the candidate tasks may be sorted according to a size order, and a preset number of candidate tasks with a higher probability may be pushed to the target user, where the preset number may be 10 or 20, and the preset number may also be customized according to a requirement, and is not specifically limited in this exemplary embodiment.

The task pushing method is described below with reference to a specific embodiment. Referring to fig. 6, the characteristic information 620 of the user may be obtained from the database 610, the characteristic information includes user behavior information and user tag information, and the task related information 630 may also be obtained from the database, the task related information 630 may include basic task information 631 and task reward information 632, the characteristic information 620 and the task related information 630 are input into the server, and the recommended task list 650 is finally obtained through calculation of the server 640.

When the server 640 processes the feature information 620 and the task related information 630, as shown in fig. 7, the users may be clustered to obtain a plurality of user types, for example, user type one 710, user type two 712, user type three 714, and the like. Then, according to the feature attributes of the acquired candidate tasks, the feature attributes may include the above-mentioned rate of getting, rate of being completed, and the like of the candidate tasks.

For example, assuming that the user type of the target user is user type one 710, that is, user type one 710 is the target user type, the feature attributes of the candidate tasks are obtained, and the feature attributes may include a first candidate task getting rate 720, a first candidate task completing rate 722, a second candidate task getting rate 724, a second candidate task completing rate 726, and the like, the feature attributes of all the candidate tasks are obtained, and the feature attributes are input into the deep learning model to obtain the probability that the candidate tasks are allocated to the target user type, so as to obtain the task recommendation list 730.

It should be noted that the feature attributes of one candidate task may include multiple types, in this exemplary embodiment, a simple description is made only by taking the completed rate and the received rate as an example, and in this exemplary embodiment, the number and the type of the feature attributes are not specifically limited.

It is noted that the above-mentioned figures are merely schematic illustrations of processes involved in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

The following describes an embodiment of an apparatus of the present disclosure, which may be used to perform the task pushing method described above in the present disclosure. In addition, in the exemplary embodiment of the disclosure, a task pushing device is also provided. Referring to fig. 8, the task pushing apparatus 800 includes: an obtaining module 810, a selecting module 820, a calculating module 830, and a determining module 840.

The obtaining module 810 may be configured to obtain feature information of a plurality of users within a preset time, and cluster the users according to the feature information to obtain a plurality of reference user types; the selecting module 820 may be configured to select a reference user type to which a target user belongs as a target user type according to the feature information of the target user, and the calculating module 830 is configured to obtain a plurality of candidate tasks and calculate a probability that the candidate tasks are allocated to the target user type; the judging module 840 is configured to judge whether to push the candidate task to the target user according to the probability.

For details that are not disclosed in the embodiment of the present disclosure, please refer to the embodiment of the task pushing method described above for the details that are not disclosed in the embodiment of the present disclosure.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the task pushing method is also provided.

As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

An electronic device 900 according to such an embodiment of the disclosure is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is only an example and should not bring any limitations to the functionality or scope of use of the embodiments of the present disclosure.

As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

Wherein the storage unit stores program code that is executable by the processing unit 910 to cause the processing unit 910 to perform steps according to various exemplary embodiments of the present disclosure described in the above section "exemplary method" of the present specification. For example, the processing unit 910 may execute step S110 as shown in fig. 1: acquiring characteristic information of a plurality of users within preset time, and clustering the users according to the characteristic information to obtain a plurality of reference user types; s120: selecting a reference user type to which the target user belongs as a target user type according to the characteristic information of the target user; s130: acquiring a plurality of candidate tasks, and calculating the probability of the candidate tasks distributed to the target user type; s140: and judging whether the candidate task is pushed to the target user or not according to the probability.

As another example, the electronic device may implement the steps shown in fig. 1 to 5.

The storage unit 920 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)921 and/or a cache memory unit 922, and may further include a read only memory unit (ROM) 923.

Storage unit 920 may also include a program/utility 924 having a set (at least one) of program modules 925, such program modules 925 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.

Bus 930 can be any of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 900, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interface 950. Also, the electronic device 900 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) via the network adapter 960. As shown, the network adapter 960 communicates with the other modules of the electronic device 900 via the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, aspects of the present disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present disclosure described in the "exemplary methods" section above of this specification, when the program product is run on the terminal device.

Referring to fig. 10, a program product 1000 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a 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.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A 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 (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.

A computer readable signal medium may include a propagated data signal with 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 readable signal medium may also be any readable medium that is not a 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 readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.

Claims

1. A task pushing method is characterized by comprising the following steps:

2. The method of claim 1, wherein obtaining feature information of a plurality of users within a preset time, and clustering the users according to the feature information to obtain a plurality of reference user types and a plurality of clustering centers comprises:

acquiring characteristic information of a plurality of users from a database;

determining a feature vector according to the feature information;

3. The method of claim 2, wherein clustering the plurality of users according to the feature vector and the clustering center to obtain a plurality of reference user types comprises:

4. The method according to claim 2, wherein selecting a reference user type to which the target user belongs as a target task type according to the feature information of the target user comprises:

acquiring characteristic information of the target user;

and according to the feature vector of the target user, taking the reference user type corresponding to the clustering center closest to the feature vector of the target user as the target user type.

5. The method of claim 1, wherein obtaining a plurality of candidate tasks and calculating the probability of the candidate tasks being assigned to the target user type comprises:

6. The method of claim 5, further comprising;

7. The method of claim 1, wherein determining whether to push the candidate task to the target user according to the probability comprises:

judging the probability and the preset value;

8. A task pushing apparatus, comprising:

the computing module is used for acquiring a plurality of candidate tasks and computing the probability of the candidate tasks distributed to the target user type;

9. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing a task pushing method according to any one of claims 1 to 7.

10. An electronic device, comprising:

a processor; and

a memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the task pushing method of any of claims 1 to 7.