CN109523237B

CN109523237B - Crowd-sourced task pushing method and related device based on user preference

Info

Publication number: CN109523237B
Application number: CN201811364711.1A
Authority: CN
Inventors: 黄夕桐; 李佳琳; 王健宗; 肖京
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2018-11-15
Filing date: 2018-11-15
Publication date: 2023-08-04
Anticipated expiration: 2038-11-15
Also published as: WO2020098251A1; CN109523237A

Abstract

The embodiment of the invention discloses a crowdsourcing task pushing method and a related device based on user preference, wherein the method comprises the following steps: determining a first preset number of task response active users aiming at tasks of a target task type; respectively acquiring historical push data sets of each task response active user; establishing an acceptance probability logistic regression model according to the history push data set; estimating historical task acceptance probability according to the active user data and the historical task data by using an acceptance probability logistic regression model; estimating the user likelihood degree of the active user of task response according to the historical task acceptance probability and the response result label data; determining a first high-preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users, and pushing the target pushing task of the target task type to the first high-preference target user. By adopting the scheme of the invention, the delivery efficiency of the crowdsourcing task can be improved.

Description

Crowd-sourced task pushing method and related device based on user preference

Technical Field

The invention relates to the field of computers, in particular to a crowdsourcing task pushing method based on user preference and a related device.

Background

In recent years, more and more enterprises begin to try to delegate certain technical tasks to external individuals or organizations through internet channels to complete, and this emerging open collaboration innovation model based on the internet is called crowdsourcing. Crowd-sourcing modes generally include three principals: the crowdsourcing party distributes crowdsourcing tasks on the crowdsourcing platform, and then the crowdsourcing party receives the tasks from the crowdsourcing platform, finishes the tasks according to the stipulations and obtains corresponding rewards. Common crowdsourcing tasks include design, management consultation, solution planning, movie production, information collection, picture recognition, software development, and the like. When the crowdsourcing task is distributed, the crowdsourcing platform widely spreads task demands of a source, and meanwhile, people with the capacity, interest and the like matched with the corresponding crowdsourcing task are found on the Internet to distribute, so that the smooth and efficient completion of the crowdsourcing task can be ensured.

However, in the current crowdsourcing job scenario, when a task is issued in most cases, the preference of the individual wrapper for the task is not considered, so that after part of the task is dispatched, the user does not accept the task in time or does not accept the task, and the task needs to be dispatched again. The user has low response degree to the task, and the completion degree and delivery efficiency of the task are directly affected.

Disclosure of Invention

The invention provides a crowdsourcing task pushing method and a related device based on user preference, which can improve the delivery efficiency of crowdsourcing tasks.

In a first aspect, the present invention provides a method for pushing crowdsourcing tasks based on user preferences, including:

determining a first preset number of task response active users aiming at tasks of a target task type;

respectively acquiring a history push data set of each task response active user, wherein the history push data set comprises a second preset number of history push data, and the history push data comprises active user data generated by a history push task of a target task type pushed by the task response active user, history task data corresponding to the history push task and response result tag data of whether the history push task is accepted by the task response active user;

establishing a logistic regression model of the acceptance probability of the historical task about the historical task data and the active user data according to the respective historical push data sets of the first preset number of task response active users, wherein the acceptance probability of the historical task is the acceptance probability of the task response active users to each historical push task;

Estimating the historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model;

estimating the user likelihood of the response results corresponding to the response result label data of the history pushing task and the history pushing task about the task response active user according to the history task acceptance probability and the response result label data;

and determining a first high-preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users, and pushing the target pushing task of the target task type to the first high-preference target user.

With reference to the first aspect, in a possible implementation manner, the historical task data includes at least one task attribute feature data of the historical push task, and the active user data includes at least one user attribute feature data of the task responsive active user;

the establishing a logistic regression model of the acceptance probability of the historical task about the historical task data and the active user data according to the respective historical push data sets of the first preset number of task response active users comprises:

If the second preset number is m, m is a positive integer, using event A ₁ Indicating that a task response active user u accepts an ith historical push task in m historical push tasks, wherein i is a positive integer, and i is E [1, m]The historical task acceptance probability of the task response active user u to the ith historical push task is:

wherein the vector x _i A task characteristic value vector formed by task attribute characteristic data corresponding to the ith historical push task; vector w _u A user characteristic weight vector formed by user attribute characteristic data of the ith historical push task for the task response active user u, wherein the user characteristic weight vector is formed by the user attribute characteristic data of the ith historical push taskAnd counting the user attribute feature weights of all the user attribute feature data in the value vector according to the user attribute feature data of all the first preset number of task response active users and the response result tag data of the history pushing data set corresponding to the task response active users.

With reference to the first aspect, in one possible implementation, the estimating, according to the historical task acceptance probability and the response result tag data, the user likelihood of the task response active user with respect to the historical push task and the response result corresponding to the response result tag data of the historical push task includes:

If the second preset number is m, and m is a positive integer, and response results corresponding to m historical pushing tasks pushed by the task response active user u and response result tag data of the m historical pushing tasks form a sampling sample set of the task response active user u, the likelihood degree of the task response active user u about the sampling sample set is as follows:

wherein ,P_u (A ₁ |x _uj ) The historical task acceptance probability of the j-th historical push task in m historical push tasks is represented by the task response active user u; y is _uj The response result label data of the j-th history pushing task in m history pushing tasks is responded to the active user u by the task, j is a positive integer, j is E [1, m]，y _uj ∈{0,1}。

With reference to the first aspect, in one possible implementation manner, the determining, according to the user likelihood degrees corresponding to the first preset number of task response active users, a first high preference target user from the first preset number of task response active users includes:

sorting the first preset number of task response active users from high to low according to the likelihood degrees of the corresponding users;

and determining a third preset number of task response active users with the forefront ordering as first high-preference target users, wherein the third preset number is smaller than or equal to the first preset number and is larger than or equal to the number of target pushing tasks.

With reference to the first aspect, in one possible implementation, the method further includes:

deleting the first high-preference target users from the first preset number of task response active users, and determining the task response active users after deleting the first high-preference target users as secondary screening active users;

when a task rejection instruction of the first high-preference target user for the target pushing task is received, determining a second high-preference target user from the second-level screening active users according to the user likelihood degrees corresponding to the second-level screening active users;

and pushing the target pushing task corresponding to the task rejection instruction to the second high-preference target user.

With reference to the first aspect, in one possible implementation, the pushing the target pushing task of the target task type to the first high preference target user includes:

determining high preference acceptance time data of the first high preference target user according to the historical push data set of the first high preference target user;

and pushing the target pushing task of the target task type to the first high-preference target user at the moment corresponding to the high-preference receiving time data.

In a second aspect, an embodiment of the present invention provides a crowdsourcing task push device based on user preference, including:

an active user determining unit, configured to determine, for a task of a target task type, a first preset number of task response active users;

the data set acquisition unit is used for respectively acquiring historical push data sets of all task response active users, wherein the historical push data sets comprise a second preset number of historical push data, and the historical push data comprise active user data generated by a historical push task of a task response active user being pushed with a target task type, historical task data corresponding to the historical push task and response result tag data of whether the historical push task is accepted by the task response active user;

the model building unit is used for building a logistic regression model of the acceptance probability of the historical task about the historical task data and the active user data according to the first preset number of task response active users' respective historical push data sets, wherein the acceptance probability of the historical task is the acceptance probability of the task response active users to each historical push task;

The estimating unit is used for estimating the historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model;

the estimation unit is further configured to estimate, according to the historical task acceptance probability and the response result tag data, a user likelihood degree of the task response active user with respect to the historical push task and a response result corresponding to the response result tag data of the historical push task;

the task pushing unit is used for determining a first high-preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users, and pushing the target pushing task of the target task type to the first high-preference target user.

With reference to the second aspect, in a possible implementation manner, the apparatus further includes:

the second-level screening unit is used for deleting the first high-preference target users from the first preset number of task response active users, and determining the task response active users after deleting the first high-preference target users as second-level screening active users;

The secondary screening unit is further configured to determine, when a task rejection instruction of the first high-preference target user for a target push task is received, a second high-preference target user from the secondary screening active users according to user likelihood degrees corresponding to the secondary screening active users;

the task pushing unit is further configured to push a target pushing task corresponding to the task rejection instruction to the second high-preference target user.

In a third aspect, an embodiment of the present invention provides another crowdsourcing task push device based on user preference, including a processor, a memory, and a communication interface, where the processor, the memory, and the communication interface are connected to each other, where the communication interface is configured to receive and send data, and the memory is configured to store program code, and the processor is configured to invoke the program code to perform any of the methods in the first aspect and the various possible implementations of the first aspect.

In a fourth aspect, embodiments of the present invention provide a computer storage medium storing a computer program comprising program instructions which, when executed by a computer, cause the computer to perform any one of the methods of the first aspect and the respective possible implementations of the first aspect.

In the embodiment of the invention, according to the historical pushing data set of each task responding active user, a logical regression model of the receiving probability of the historical task receiving probability about the historical task data and the active user data is established, and according to the historical task receiving probability estimated by using the logical regression model of the receiving probability and the response result label data of each task responding active user to each historical pushing task, the user likelihood degree of each task responding active user about each historical pushing task and the response result corresponding to each response result label data is estimated respectively, and further the target pushing task of the target task type is pushed to the first high preference target user determined from the task responding active user according to the user likelihood degree, so that the differentiated pushing of the crowdsourcing task according to the preference of the user can be realized, the response degree of the user to the crowdsourcing task is improved, and the delivery efficiency of the crowdsourcing task is further improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of a crowdsourcing task pushing method based on user preference according to an embodiment of the present invention;

FIG. 2 is a flowchart of another crowd-sourced task push method based on user preferences according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of a crowdsourcing task pushing device based on user preference according to an embodiment of the present invention;

fig. 4 is a schematic structural diagram of another crowdsourcing task pushing device based on user preference according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, fig. 1 is a flow chart of a crowdsourcing task pushing method based on user preference according to an embodiment of the present invention, and as shown in the drawing, the method includes:

s101, determining a first preset number of task response active users aiming at tasks of a target task type.

Specifically, the tasks mainly refer to crowdsourcing tasks appearing on the Internet, and relate to the fields of information retrieval, artificial intelligence, video analysis, knowledge mining, image quality evaluation and the like. The task type of the task may be various, for example, a semantic judgment class, a voice recognition class, an information collection class, etc., and the target task type may be one of them. The first preset number can be adjusted according to different tasks of the target task type, and it can be understood that the larger the first preset number is, that is, the larger the number of active users responded by the sampled tasks is, the more accurate the first high-preference target user for the tasks of the target task type is determined by the crowdsourcing task pushing method based on the user preference.

Optionally, the first preset number of task response active users may be determined by:

11 And respectively acquiring all historical users aiming at the task of the target task type.

12 And respectively calculating the target type task acceptance proportion of each historical user, wherein the target type task acceptance proportion is the ratio of the number of times of accepting the target task type task by each historical user to the number of times of pushing the target task type.

13 And ordering the historical users according to the order of the task acceptance proportion of the respective target type from high to low, and determining a first preset number of historical users with the earlier ordering as the task response active users.

S102, respectively acquiring historical push data sets of each task response active user.

Specifically, for the first number of task response active users determined in step S101, a history push data set of each task response active user is collected respectively, where the history push data set includes a second preset number of history push data, where the history push data includes active user data generated by a history push task of a target task type for the task response active user, history task data corresponding to the history push task, and response result tag data that is whether the history push task is accepted by the task response active user, that is, each time the task response active user is pushed by one history push task, a set of history push data is generated. It can be appreciated that the larger the above second preset number, i.e. the more historical push data is sampled for each task in response to an active user, the more accurate the first high-preference target user for the task of the target task type determined by the user preference-based crowdsourcing task push method.

Optionally, the historical push information sets of the task response active users are respectively obtained, and each historical push information in the historical push information sets is quantized to obtain the historical push data set corresponding to each task response active user. For example, if one history push information in the history push information set of the acquired task response active user a is 17 points of task acceptance time, the history push information may be quantized into history push data 17. For another example, in the obtained historical pushing information set of the task response active user B, one historical pushing information set is a task receiving place which is a home, and in the crowdsourcing task pushing based on the user preference, the current time can be predefined, and the historical pushing information can be quantized into the historical pushing data 1 in the task receiving place which is the home, the company, the commute, the outdoor and other places respectively corresponding to the marks 1, 2, 3, 4 and 5.

S103, establishing a logistic regression model of the acceptance probability of the historical task with respect to the historical task data and the active user data according to the respective historical push data sets of the first preset number of task response active users.

Here, the historical task acceptance probability is the acceptance probability of the task response active user for each historical push task. The acceptance probability logistic regression model is established according to the historical push data sets of all the first preset number of task response active users, and the acceptance probability of any one task response active user to any one historical push task can be estimated by using the acceptance probability logistic regression model.

Optionally, the historical task data includes at least one task attribute feature data of the historical push task, and the active user data includes at least one user attribute feature data of the task responsive active user. If the second preset number is m, m is a positive integer,by event A ₁ Indicating that a task response active user u accepts an ith historical push task in m historical push tasks, wherein i is a positive integer, and i is E [1, m]The historical task acceptance probability of the task response active user u for the ith historical push task is expressed as follows by a formula (1):

wherein the vector x _i A task characteristic value vector formed by task attribute characteristic data corresponding to the ith historical push task; vector w _u And counting user attribute feature data of all the first preset number of task response active users and response result tag data of a history pushing data set corresponding to the task response active users.

S104, estimating the historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model.

Specifically, by using the acceptance probability logistic regression model, according to the active user data and the historical task data contained in the historical pushing data set of each active user of the task response active user of the first preset number, the historical task acceptance probability of each historical active user for the historical pushing task when the historical active user is pushed by the historical active user is estimated.

For example, the history push data set of the user a includes two sets of history push data, the two sets of history push data correspond to history push tasks of the target task type of the user a being pushed twice, the user a generates active user data 1 when being pushed with a first history push task, the history task data of the first history push task is the history task data 1, the user a generates active user data 2 when being pushed with a second history push task, the history task data of the second history push task is the history task data 2, in this step, the acceptance probability logistic regression model is utilized to estimate the history task acceptance probability of the first history push task when the user a is pushed with the first history push task according to the active user data 1 and the history task data 1, and the history task acceptance probability of the second history push task when the user a is pushed with the second history push task is estimated according to the active user data 2 and the history task data 2.

S105, estimating the user likelihood degree of the response results corresponding to the response result label data of the history pushing task and the history pushing task about the task response active user according to the history task acceptance probability and the response result label data.

Specifically, according to the estimated historical task acceptance probability of the task response active user for the historical push task when the task response active user is pushed by the task response active user per se in the step S104, and the response result tag data for the historical push task, the user likelihood degree of the task response active user is estimated by using a likelihood function, wherein the user likelihood degree is the likelihood degree of the task response active user about a sampling sample set, and the sampling sample set comprises the historical push task corresponding to all the historical task data contained in the historical push data set of the task response active user per se and the response result corresponding to all the response result tag data contained in the historical push data set of the task response active user per se. Because the sampling sample set is a more active sampling sample set for the task response active user, that is, the number of historical pushing tasks corresponding to the sampling sample set is larger than the number of historical pushing tasks accepted by the corresponding historical active user, the preference degree of the task response active user for the task of the target task type can be approximately represented by the user likelihood degree of the task response active user about the self sampling sample set.

Optionally, if the second preset number is m, where m is a positive integer, and response results corresponding to m historical pushing tasks pushed by the task response active user u and response result tag data of the m historical pushing tasks form a sample set of the task response active user u, a likelihood degree of the task response active user u about the sample set is expressed as follows by a formula (2):

S106, determining a first high-preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users, and pushing target pushing tasks of target task types to the first high-preference target user.

Specifically, since the user likelihood may represent the preference degree of the task response active user for the task of the target task type, the preference degree of the task response active user with the higher user likelihood estimated in step S105 for the task of the target task type may be higher, so that a certain number or a certain proportion of task response active users with the highest user likelihood may be determined as the first high preference target user, and when the target pushing task of the target task type is to be pushed, the target pushing task of the target task type may be pushed to the first high preference target user.

Optionally, the specific step of determining the first high preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users may be as follows:

21 And ordering the first preset number of task response active users from high to low according to the likelihood of the corresponding users.

22 Determining a third preset number of task response active users with the forefront ranking as first high preference target users, wherein the third preset number is smaller than or equal to the first preset number and is larger than or equal to the number of target pushing tasks.

In an alternative embodiment, the method may further comprise the steps of:

31 Deleting the first high-preference target users from the first preset number of task response active users, and determining the task response active users after deleting the first high-preference target users as secondary screening active users.

32 And when a task rejection instruction of the first high-preference target user for the target pushing task is received, determining a second high-preference target user from the second-level screening active users according to the user likelihood degrees corresponding to the second-level screening active users.

33 And pushing the target pushing task corresponding to the task rejection instruction to the second high-preference target user.

Through the above steps 31), 32) and 33), when the user sending the task rejection instruction is included in the first high-preference target user who is pushed with the target pushing task, a second high-preference target user with higher preference degree can be screened out of the users other than the first high-preference target user in the task response active user, the target pushing task corresponding to the task rejection instruction is pushed to the second high-preference target user, so that the user with higher preference degree matching with the target pushing task corresponding to the task rejection instruction can be pushed, the first high-preference target user can be prevented from being repeatedly pushed with the target pushing task corresponding to the target task type, the preference degree of the first high-preference target user on the task with the target task type can be reduced, the exposure degree of the task with the target task type can be improved, more second high-preference target users other than the first high-preference target user can be pushed with the task with the target task type, and the adhesion degree of the second high-preference target user and the task with the target task type can be improved.

In the embodiment of the invention, according to the historical push data set of each task response active user, an acceptance probability logistic regression model of the historical task acceptance probability with respect to the historical task data and the active user data is established, and according to the historical task acceptance probability estimated by using the acceptance probability logistic regression model and the response result label data of each task response active user to each historical push task, the user likelihood degree of each task response active user with respect to each historical push task and the response result corresponding to each response result label data is estimated respectively, and because the user likelihood degree can represent the preference degree of the task response active user to the task of the target task type, the first high preference target user can be determined according to the user likelihood degree, and then the target push task of the target task type can be pushed to the first high preference target user. The method and the device realize differentiated pushing of the crowdsourcing tasks according to the preference of the user, improve the response degree of the user to the crowdsourcing tasks, and further improve the delivery efficiency of the crowdsourcing tasks.

Referring to fig. 2, fig. 2 is a flow chart of another crowd-sourced task pushing method based on user preference according to an embodiment of the present invention, and as shown in the drawing, the method includes:

S201, all historical users of the tasks aiming at the target task type are respectively obtained.

For example, if the target task type is an information collection class, all historical users pushed through the information collection class task are obtained.

S202, respectively calculating the target type task acceptance proportion of each historical user, sequencing the historical users according to the sequence from high to low of the respective target type task acceptance proportion, and determining a first preset number of historical users with the front sequencing as active task response users.

Here, the target task type acceptance ratio is a ratio of the number of times each history user accepts the task of the target task type to the number of times it is pushed to the target task type. For example, assuming that there are 100 history users determined for the tasks of the information collection class in step S201, the number of times that one user a of the 100 history users has been pushed with the information collection class task is 15, if the number of times that the user a receives the pushed information collection class task is 10, the target type task receiving ratio of the user a is 10/15=2/3, according to the above calculation method, the target type task receiving ratios of the 100 history users are sequentially calculated, and if the first preset number is 50, the 50 users with the highest target type task receiving ratio of the 100 history users are determined as the task responding active users.

S203, historical push information sets of the task response active users are respectively obtained, and each piece of historical push information in the historical push information sets is quantized to obtain a historical push data set corresponding to each task response active user.

Specifically, the historical push information set of each task response active user comprises a second preset number of groups of historical push information, and each group of historical push information comprises active user information generated by the task response active user by a historical push task of a push target task type, historical task information corresponding to the historical push task and a response result of whether the historical push task is accepted by the task response active user. The historical task information comprises at least one task attribute characteristic information of the historical push task, and the active user information comprises at least one user attribute characteristic information of the task responsive active user. And carrying out quantization processing on each task attribute characteristic information and each user attribute characteristic information, thereby completing the quantization processing of the history push information set.

For example, if the target task type is an information collection type, the first preset number is 50, the second preset number is 30, and the history push information set of the user B in the 50 task response active users obtained in step S203 is as shown in table 1:

TABLE 1

The collection time, collection channel and information type in table 1 are 3 task feature attribute information included in historical task information, the age, the place where the collection channel is located when the collection channel is pushed and the proficiency degree are 3 user feature information included in active user information, the task feature attribute information and the user feature information are respectively quantized, the collection time is quantized into numbers corresponding to the time, and the collection channel is quantized into numbers corresponding to the time: telephone acquisition, internet acquisition and field acquisition correspond to numerals 1, 2 and 3 respectively, and information types are quantized into: entertainment type, diet type and medical type correspond to numerals 1, 2 and 3, respectively, age is quantized to numerals corresponding to age, and the place where pushed is located is quantized to: the home, outdoor and company correspond to the numbers 1, 2 and 3, respectively, and the proficiency course is measured as: very skilled, more skilled, less skilled and less skilled correspond to the numbers 5, 4, 3, 2 and 1 respectively, quantifying response outcome acceptance as response outcome tag 1, and quantifying response outcome rejection or omission as response outcome tag 0, resulting in a historical push data set for user B as shown in table 2:

TABLE 2

S204, according to the user attribute feature data and response result label data contained in the historical pushing data sets of all the first preset number of task response active users, counting the user feature weights of the user attribute feature data in the user feature weight vector formed by the user attribute feature data.

Specifically, the user feature weight represents the influence degree of the corresponding user attribute feature data on the task response active user to accept the historical push task, and the user feature weight can be calculated through statistical software such as SPSS (Statistical Product and Service Solutions, statistical product and service solution) or SAS (Statistics Analysis System, statistical analysis system).

Optionally, in order to improve the computing efficiency and reduce the computing cost, the user attribute feature data with the smaller absolute value of the corresponding user feature weight in the user attribute feature data may be omitted, and the user attribute feature data with the larger user feature weight may be screened to participate in the computing. For example, if the user feature weights for gender, age, location and proficiency at the time of being pushed are calculated statistically by using the statistical software SPSS, respectively: 0.002, 0.335, 0.114 and 0.219, the user attribute feature data corresponding to gender may be truncated and not participate in the calculation.

S205, establishing a logistic regression model of the acceptance probability of the historical task with respect to the historical task data and the active user data according to the user characteristic weight.

Based on the example in step S203, if the user feature weights of the age, the place where the user is pushed, and the proficiency level obtained in step S204 are respectively: 0.335, 0.114 and 0.219, the time of acquisition, acquisition channel and acquisition type are respectively represented by variables t, c and k, the age, the place when pushed and the proficiency are respectively represented by variables a, s and l, and the event A is used ₁ Indicating that the ith user in the 50 task response active users receives the ith history pushing task in the 30 history pushing tasks, the history task acceptance probability of the ith user for the ith history pushing task is expressed as shown in a formula (3):

wherein the vector x _i Task attribute characteristic data acquisition time t corresponding to ith historical push task _i Channel c for collecting _i Information type k _i Task eigenvalue vector, vector x _i ＝(t _i ,c _i ,k _i ) The method comprises the steps of carrying out a first treatment on the surface of the Vector w _u User attribute feature data age a for the ith user for the ith historical push task _u QuiltPlace s at the time of pushing _u Proficiency level l _u User characteristic weight vector, vector w _u ＝(0.335*a _u ,0.114*s _u ,0.219*l _u )。

S206, estimating the historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model.

Here, the history task acceptance probability is a probability that the task response active user accepts the history push task corresponding to the history task data when the history push task corresponding to the history task data is pushed.

Based on the example in step S203, if the statistical software SPSS in step S204 calculates the age, the location when pushed, and the user feature weight of the proficiency level as follows: 0.335, 0.114 and 0.219, and the task feature value vector of the history push task corresponding to the reference numeral 3 is x according to the history push data set corresponding to the table 2 ₃ = (12,3,3), user B has a user feature weight vector w for the history push task corresponding to reference number 3 _B = (0.335 x 20,0.114 x 3,0.219 x 4), x ₃ and w_B Substituting into the formula (3) in the step S205 to calculate the history task acceptance probability P of the history task corresponding to the reference number 3 when the user B is pushed the history task corresponding to the reference number 3 _B (A ₁ |x ₃ ). According to the method, the history task acceptance probability P of the history push tasks corresponding to the labels 1, 2,3, … and 30 can be estimated in sequence when the user B is pushed with the history push tasks corresponding to the labels 1, 2,3, … and 30 respectively _B (A ₁ |x ₁ )、P _B (A ₁ |x ₂ )、P _B (A ₁ |x ₃ )、…、P _B (A ₁ |x ₃₀ ). And further, the historical task acceptance probability of each task response active user for the corresponding historical push task when the corresponding historical push task is pushed can be estimated.

S207, estimating the user likelihood degree of the response results corresponding to the response result label data of the history pushing task and the history pushing task about the task response active user according to the history task acceptance probability and the response result label data.

Based on the example in step S203, if step S206 obtains the history task acceptance probability P for the history push tasks corresponding to the reference numerals 1, 2, 3, …, 30 when the user B is pushed the history push tasks corresponding to the reference numerals 1, 2, 3, …, 30, respectively _B (A ₁ |x ₁ )、P _B (A ₁ |x ₂ )、P _B (A ₁ |x ₃ )、…、P _B (A ₁ |x ₃₀ ) The sample set of user B is [ (history push task corresponding to reference numeral 1, accept), (history push task corresponding to reference numeral 2, reject), (history push task corresponding to reference numeral 3, accept), (history push task corresponding to reference numeral 4, ignore) ], … …, (history push task corresponding to reference numeral 30, accept)]The user likelihood of user B for the self-sampled sample set can be calculated using equation (4):

S208, sorting the first preset number of task response active users from high to low according to the likelihood of the corresponding users, and determining a third preset number of task response active users with the forefront sorting as first high preference target users.

Here, the third preset number is the number of the first high preference target users, and the value of the third preset number may be a preset fixed value or a fixed percentage of the value of the set first preset number, where the fixed value and the fixed percentage may be set differently according to different attribute information such as emergency situations of the target push task, but the setting of the fixed value or the fixed percentage is to ensure that the third preset number is smaller than or equal to the first preset number and is greater than or equal to the number of the target push task.

For example, if the 50 task response active users in step S207 are ranked according to their respective user likelihoods from high to low, the resulting sequences are shown in table 3:

ranking labels	User' s	User likelihood
			1	User 20	0.0835
2	User 8	0.0762
			3	User 44	0.0754
4	User 6	0.0733
			5	User 29	0.0689
6	User 12	0.0687
			7	User 3	0.0644
8	User 1	0.0621
			9	User 46	0.0584
……	……	……
			50	User 39	0.0014

TABLE 3 Table 3

If the third preset number is 6, user 20, user 8, user 44, user 6, user 29, user 12 are determined to be the first high preference target user.

S209, determining high-preference receiving time data of the first high-preference target user according to the historical pushing data set of the first high-preference target user, and pushing the target pushing task of the target task type to the first high-preference target user at the moment corresponding to the high-preference receiving time data.

Specifically, the time corresponding to the high-preference receiving time data is the time when the first high-preference target user receives the target pushing task in 24 hours of a day and pushes the target pushing task at the time when the first high-preference target user receives the target pushing task at the maximum possibility, so that the possibility of the first high-preference target user for receiving the target pushing task can be further improved, and the delivery efficiency of the target pushing task is further improved.

Here, the high-preference receiving time data common to the first high-preference target users may be determined, the target pushing task may be pushed to the first high-preference target users in a unified manner at the time corresponding to the high-preference receiving time, the high-preference receiving time data of each first high-preference target user may be determined, the target pushing task may be pushed to the corresponding first high-preference target user at the time corresponding to the high-preference receiving time data of each first high-preference target user, and further, there are various methods for determining the high-preference receiving time data of the first high-preference target user.

In an alternative embodiment, the statistics may be performed on the respective historical push data sets of all the first high-preference target users, to obtain a peak-of-acceptance time period with the greatest number of accepted historical push tasks for pushing at 0-1, 1-2, 2-3, …, 23-24, the high preference receiving time data may be determined as the receiving peak time period, for example, if the number of the historical pushing tasks pushed in the 17-18 point time period is the greatest through statistical calculation, the target pushing tasks may be respectively pushed to the first high preference target user at random time points between 17-18 points.

And respectively carrying out statistics calculation on the historical pushing data sets of the first high-preference target users to obtain the respective receiving peak time periods of the first high-preference target users, and respectively pushing the target pushing tasks to the corresponding first high-preference target users in the respective receiving peak time periods of the first high-preference target users.

In another optional implementation manner, the highest fourth preset number of historical task acceptance probabilities in the historical task acceptance probabilities of all the first high-preference target users are obtained, push time data of the historical push tasks corresponding to the highest fourth preset number of historical task acceptance probabilities are determined to be the high-preference acceptance time data, the target push tasks of the target task type are distributed to fourth preset number of push batches, and the target push tasks of the corresponding push batches are pushed to the first high-preference target users at the time corresponding to the fourth preset number of high-preference acceptance time data. The push time data may be present in active user data contained in the historical push data set or may be present in historical task data contained in the historical push data set.

For example, if the fourth preset number is 3, the highest 3 historical task acceptance probabilities among the historical task acceptance probabilities of all the first high-preference target users are the historical task acceptance probabilities P of the user a for the 3 rd historical push task of the target task type that was pushed by the user a _A (A ₁ |x ₃ ) Historical task acceptance probability P of user M on historical push task of 12 th target task type which is pushed by user M _M (A ₁ |x ₁₂ ) Historical task acceptance probability P of user G for historical push task of 29 th target task type which is pushed by user G _G (A ₁ |x ₂₉ ) Further, it may be determined that the time to when the user a was pushed the 3 rd historical push task is 17 points according to the historical push data set of the user a, the time to when the user M was pushed the 12 th historical push task is 11 points according to the historical push data set of the user M, the time to when the user G was pushed the 29 th historical push task is 15 points according to the historical push data set of the user G, if there are 15 target push tasks in total, the 15 target push tasks are randomly distributed to 3 push batches, for example, 5 target push tasks may be randomly distributed to each push batch, and then the target push tasks of the 3 push batches are pushed to the first high preference target user at 11 points, 15 points and 17 points, respectively.

The highest historical task acceptance probability of the first high-preference target users can be obtained respectively, the pushing time of the historical pushing task corresponding to the highest historical task acceptance probability of the first high-preference target users is further determined, and the target pushing task is pushed to the first high-preference target users at the pushing time of the historical pushing task corresponding to the highest historical task acceptance probability of the first high-preference target users.

Optionally, if a task rejection instruction of the first high-preference target user for the target push task is received, determining a second high-preference target user for the target push task corresponding to the task rejection instruction, further determining high-preference acceptance time data of the second high-preference target user, and pushing the target push task corresponding to the task rejection instruction to the second high-preference target user at a time corresponding to the high-preference acceptance time data of the second high-preference target user.

Based on the example in step S208, if the task rejection instructions of the user 44 and the user 12 are received after the target push tasks of 6 target task types are pushed to the user 20, the user 8, the user 44, the user 6, the user 29, and the user 12, the user 3 and the user 1 may be determined as the second highest preference target users, and then the history task acceptance probabilities of the user 3 and the user 1, which are respectively the history task acceptance probabilities of the user 3 to the 18 th target task type that was pushed by the user 3 and the history task acceptance probability of the user 1 to the 5 th target task type that was pushed by the user 1, are further obtained, the time at which the user 3 was pushed by the 18 th history push task is 3, and the time at which the user 1 was pushed by the 5 th history push task is 10, and the history push tasks corresponding to the task rejection instructions sent by the user 44 and the user 12 are respectively pushed to the user 3 and the user 1 at 3 and 10.

In the embodiment of the invention, firstly, a task response active user is determined from historical users of tasks of the target task type, then, a historical push data set of the task response active user is obtained through quantization processing on a historical push information set of the task response active user, and the user likelihood degree of the task response active user is estimated according to the historical push data set and an established acceptance probability logistic regression model, and further, a first high-preference target user is determined from the task response active user according to the user likelihood degree, and the target push task of the target type is pushed to the first high-preference target user at a moment corresponding to the high-preference acceptance time data of the first high-preference target user. The method and the device not only realize differentiated pushing of the crowdsourcing task according to the preference of the user, but also push the crowdsourcing task at the moment when the user has high possibility of accepting the task, further improve the response degree of the user to the crowdsourcing task and improve the delivery efficiency of the crowdsourcing task.

Referring to fig. 3, fig. 3 is a schematic structural diagram of a crowdsourcing task pushing device based on user preference according to an embodiment of the present invention, as shown in the fig. 3, the crowdsourcing task pushing device 30 based on user preference may include:

An active user determining unit 301, configured to determine, for a task of a target task type, a first preset number of task response active users.

Specifically, the tasks mainly refer to crowdsourcing tasks appearing on the Internet, and relate to the fields of information retrieval, artificial intelligence, video analysis, knowledge mining, image quality evaluation and the like. The task type of the task may be various, for example, a semantic judgment class, a voice recognition class, an information collection class, etc., and the target task type may be one of them. The first preset number can be adjusted according to different tasks of the target task type, and it can be understood that the larger the first preset number is, that is, the larger the number of active users responded by the sampled tasks is, the more accurate the first high-preference target user of the task of the target task type is determined by the crowdsourcing task pushing device based on the user preference.

Optionally, the active user determining unit 301 may specifically be configured to: respectively acquiring all historical users aiming at the task of the target task type; calculating a target type task acceptance ratio of each historical user, wherein the target type task acceptance ratio is a ratio of the number of times each historical user accepts the task of the target task type to the number of times the task of the target task type is pushed; and sequencing the historical users according to the sequence from high to low of the task acceptance proportion of the respective target type, and determining a first preset number of historical users with the earlier sequencing as the active users for task response.

The data set obtaining unit 302 is configured to obtain a history push data set of each task response active user, where the history push data set includes a second preset number of history push data, and the history push data includes active user data generated by a history push task of a task response active user being pushed with a target task type, history task data corresponding to the history push task, and response result tag data that whether the history push task is accepted by the task response active user.

Specifically, for the first number of task response active users determined by the active user determining unit 301, a history push data set of each task response active user is collected respectively, where the history push data set includes a second preset number of history push data, and the history push data includes active user data generated by a history push task of a task response active user in a push target task type, history task data corresponding to the history push task, and response result tag data that is received by the task response active user, that is, a set of history push data is generated by each time the task response active user is pushed by one history push task. It can be appreciated that the greater the above second preset number, i.e. the more historical push data is sampled for each task in response to an active user, the more accurate the crowd-sourced task push device determines the first highly-favored target user for the task of the target task type based on the user preferences.

Optionally, the data set obtaining unit 302 may specifically obtain a history push information set of each task responsive to the active user, and perform quantization processing on each history push information in the history push information set to obtain a history push data set corresponding to each task responsive to the active user.

The model building unit 303 is configured to build a logistic regression model of the acceptance probability of the historical task with respect to the historical task data and the active user data according to the respective historical push data sets of the first preset number of task response active users.

Here, the historical task acceptance probability is the acceptance probability of the task response active user for each historical push task. The logistic regression model of acceptance probability is built by the model building unit 303 according to the historical pushing data sets of all the first preset number of task response active users, and by using the logistic regression model of acceptance probability, the historical task acceptance probability of any one task response active user to any one historical pushing task can be estimated.

Optionally, the historical task data includes at least one task attribute feature data of the historical push task, and the active user data includes at least one user attribute feature data of the task responsive active user. If the second preset number is m, m is a positive integer, using event A ₁ Indicating that a task response active user u accepts an ith historical push task in m historical push tasks, wherein i is a positive integer, and i is E [1, m]The model building unit 303 builds an acceptance probability logistic regression model, and the historical task acceptance probability of the task response active user u for the i-th historical push task is expressed as formula (5):

wherein the vector x _i A task characteristic value vector formed by task attribute characteristic data corresponding to the ith historical push task; vector w _u For the task response active user u, a user attribute weight vector is formed by the user attribute feature data of the ith historical push task, the user attribute weights of all the user attribute feature data in the user attribute weight vector, and the model building unit 303 builds the user attribute feature numbers of all the user response active users according to all the first preset number of tasksAnd according to the response result label data statistics of the historical push data set corresponding to the task response active user.

And an estimating unit 304, configured to estimate the historical task acceptance probability according to the active user data and the historical task data by using the acceptance probability logistic regression model.

Specifically, the estimating unit 304 estimates, according to the active user data and the historical task data included in the historical pushing data set of each active user in response to the first preset number of tasks, the historical task acceptance probability of each historical active user for the historical pushing task when the historical pushing task has been pushed by the active user by using the acceptance probability logistic regression model.

The estimating unit 304 is further configured to estimate, according to the historical task acceptance probability and the response result tag data, a user likelihood of the task responding active user with respect to the historical push task and a response result corresponding to the response result tag data of the historical push task.

Specifically, the estimation unit 304 estimates, according to the estimated historical task acceptance probability of the task response active user for the historical push task when the task response active user has been pushed by the task response active user itself, and the response result tag data for the historical push task, the user likelihood of the task response active user by using a likelihood function, where the user likelihood is the likelihood of the task response active user about a sample set, where the sample set includes the historical push task corresponding to all the historical task data included in the historical push data set of the task response active user and the response result corresponding to all the response result tag data included in the historical push data set of the task response active user. Because the sampling sample set is a more active sampling sample set for the task response active user, that is, the number of historical pushing tasks corresponding to the sampling sample set is larger than the number of historical pushing tasks accepted by the corresponding historical active user, the preference degree of the task response active user for the task of the target task type can be approximately represented by the user likelihood degree of the task response active user about the self sampling sample set.

Optionally, if the second preset number is m, where m is a positive integer, and response results corresponding to m historical push tasks pushed by the task response active user u and response result tag data of the m historical push tasks form a sample set of samples of the task response active user u, the estimation unit 304 represents likelihood of the task response active user u with respect to the sample set as shown in formula (6):

The task pushing unit 305 is configured to determine a first high-preference target user from the first preset number of task response active users according to the user likelihood degrees corresponding to the first preset number of task response active users, and push a target pushing task of a target task type to the first high-preference target user.

Specifically, since the user likelihood may represent the preference degree of the task response active user for the task of the target task type, the preference degree of the task response active user with higher user likelihood estimated by the estimation unit 304 for the task of the target task type may be higher, so that a certain number or a certain proportion of task response active users with highest user likelihood may be determined as first high preference target users, and when a target pushing task of the target task type is to be pushed, the target pushing task of the target task type may be pushed to the first high preference target users.

Optionally, the task pushing unit 305 may be specifically configured to: sorting the first preset number of task response active users from high to low according to the likelihood degrees of the corresponding users; and determining a third preset number of task response active users with the forefront ordering as first high-preference target users, wherein the third preset number is smaller than or equal to the first preset number and is larger than or equal to the number of target pushing tasks.

Further optionally, the crowdsourcing task pushing device 30 based on user preference may further include:

and the secondary filtering unit 306 is configured to delete the first high-preference target user from the first preset number of task response active users, and determine the task response active user after deleting the first high-preference target user as a secondary filtering active user.

The secondary screening unit 306 is further configured to determine, when a task rejection instruction of the first high-preference target user for a target push task is received, a second high-preference target user from the secondary screening active users according to user likelihood degrees corresponding to the secondary screening active users.

The task pushing unit 305 is further configured to push a target pushing task corresponding to the task rejection instruction to the second high preference target user.

When there is a user sending a task rejection instruction in the first high-preference target users that are pushed with the target pushing task, the second screening unit 306 may screen out a second high-preference target user with a higher preference degree from users other than the first high-preference target users in the task response active users, and the task pushing unit 305 may push the target pushing task corresponding to the task rejection instruction to the second high-preference target user, so as to ensure that the user with a higher preference degree matches the target pushing task corresponding to the task rejection instruction to push, and avoid that the first high-preference target user is repeatedly pushed with the target pushing task corresponding to the target task type, so as to reduce the preference degree of the first high-preference target user on the task with the target task type, and also improve the exposure degree of the task with the target task type, so that more second high-preference target users other than the first high-preference target user are pushed with the task with the target task type, and improve the adhesion degree of the second high-preference target user and the task with the target task type.

Further optionally, the task pushing unit 305 may specifically be configured to: determining high preference acceptance time data of the first high preference target user according to the historical push data set of the first high preference target user; and pushing the target pushing task of the target task type to the first high-preference target user at the moment corresponding to the high-preference receiving time data.

Specifically, the time corresponding to the high preference receiving time data is the time when the probability that the first high preference target user receives the target pushing task in 24 hours of a day is the maximum, and the task pushing unit 305 performs pushing at the time when the probability that the first high preference target user receives the target pushing task is the maximum, so that the probability that the first high preference target user receives the target pushing task can be further improved, and further the delivery efficiency of the target pushing task is improved. Here, the task pushing unit 305 may determine high preference acceptance time data common to the first high preference target users, and push the target pushing task to the first high preference target users at a time corresponding to the high preference acceptance time, or may determine high preference acceptance time data of each first high preference target user, and push the target pushing task to the corresponding first high preference target user at a time corresponding to the high preference acceptance time data of each first high preference target user.

In the embodiment of the invention, a model building unit builds a logistic regression model of the acceptance probability of the historical task about the historical task data and the acceptance probability of the active user data according to the historical push data set of each task response active user, and an estimation unit respectively estimates the user likelihood degree of the response result of each task response active user about each historical push task and each response result label data corresponding to each response result label data according to the historical task acceptance probability estimated by using the acceptance probability logistic regression model and the response result label data of each task response active user to each historical push task. The method and the device realize differentiated pushing of the crowdsourcing tasks according to the preference of the user, improve the response degree of the user to the crowdsourcing tasks, and further improve the delivery efficiency of the crowdsourcing tasks.

Referring to fig. 4, fig. 4 is a schematic structural diagram of another crowdsourcing task pushing device based on user preference according to an embodiment of the present invention, and as shown in the drawing, the crowdsourcing task pushing device 40 based on user preference includes a processor 401, a memory 402, and a communication interface 403. The processor 401 is connected to the memory 402 and the communication interface 403, for example, the processor 401 may be connected to the memory 402 and the communication interface 403 through a bus.

The processor 401 is configured to support the user preference based crowdsourcing task pushing device to perform the corresponding functions in the user preference based crowdsourcing task pushing method described in fig. 1-2. The processor 401 may be a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a hardware chip or any combination thereof. The hardware chip may be an Application-specific integrated circuit (ASIC), a programmable logic device (Programmable Logic Device, PLD), or a combination thereof. The PLD may be a complex programmable logic device (Complex Programmable Logic Device, CPLD), a Field programmable gate array (Field-Programmable Gate Array, FPGA), general array logic (Generic Array Logic, GAL), or any combination thereof.

The memory 402 is used for storing program codes and the like. Memory 402 comprises an internal memory that may include at least one of: volatile memory (e.g., dynamic Random Access Memory (DRAM), static RAM (SRAM), synchronous Dynamic RAM (SDRAM), etc.) and nonvolatile memory (e.g., one-time programmable read-only memory (OTPROM), programmable ROM (PROM), erasable Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM)), memory 402 may also include external memory that may include at least one of a Hard Disk (HDD) or Solid State Drive (SSD), flash Drive, e.g., high density flash memory (CF), secure Digital (SD), microsD, mini SD, extreme digital (xD), memory stick, etc.

The communication interface 403 is used for receiving or transmitting data.

The processor 401 may call the program code to perform the following operations:

It should be noted that implementation of each operation may also correspond to the corresponding description of the method embodiment shown with reference to fig. 1-2; the processor 401 may also be used to perform other operations in the method embodiments described above.

Embodiments of the present invention also provide a computer storage medium storing a computer program comprising program instructions which, when executed by a computer, cause the computer to perform a method as described in the previous embodiments, which may be part of a crowdsourcing task pushing device based on user preferences as mentioned above.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.

The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.

Claims

1. The crowdsourcing task pushing method based on the user preference is characterized by comprising the following steps of:

respectively acquiring a history push data set of each task response active user, wherein the history push data set comprises a second preset number of history push data, the history push data comprises active user data generated by a history push task of a target task type of the task response active user, history task data corresponding to the history push task and response result tag data of whether the history push task is accepted by the task response active user, the history task data comprises at least one task attribute characteristic data of the history push task, and the active user data comprises at least one user attribute characteristic data of the task response active user;

establishing a logistic regression model of the reception probability of the historical task with respect to the historical task data and the active user data according to the respective historical push data sets of the first preset number of task response active users, wherein the reception probability of the historical task is the reception probability of the task response active users on each historical push task, and if the second preset number is m, m is a positive integer, an event A is used ₁ Indicating that the task response active user u accepts the ith historical push task in m historical push tasks, i is a positive integer,the historical task acceptance probability of the task response active user u to the ith historical push task is:

wherein the vector x _i A task characteristic value vector formed by task attribute characteristic data corresponding to the ith historical push task; vector w _u A user attribute weight vector formed by user attribute feature data of the ith historical push task for the task response active user u, wherein the user attribute weight of each user attribute feature data in the user attribute weight vector is according to all the first preset number of task response active users uCounting the attribute characteristic data of the users and the response result tag data of the history pushing data set corresponding to the task response active user;

2. The method of claim 1, wherein estimating the user likelihood of the task responding active user with respect to the historical push task and the response result corresponding to the response result tag data of the historical push task based on the historical task acceptance probability and the response result tag data comprises:

，

wherein ,representing a task response active user u versus m history pushesThe history task acceptance probability of the j-th history pushing task in the sending task; y is _uj Responding response result tag data of the active user u to the j-th history pushing task in m history pushing tasks for the task, wherein j is a positive integer,/-is a positive integer>，/>。

3. The method of claim 1, wherein the determining a first high preference target user from the first preset number of task response active users based on respective user likelihoods of the first preset number of task response active users comprises:

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

5. The method of claim 1, wherein pushing the target push task of the target task type to the first high preference target user comprises:

6. A crowdsourcing task pushing device based on user preferences, comprising:

A model building unit, configured to build a logistic regression model of a historical task acceptance probability with respect to the historical task data and the active user data according to the historical push data sets of the first preset number of task response active users, where the historical task acceptance probability is an acceptance probability of the task response active users for each historical push task, and if the second preset number is m, m is a positive integer, event a is used ₁ Indicating that the task response active user u accepts the ith historical push task in m historical push tasks, i is a positive integer,the historical task acceptance probability of the task response active user u to the ith historical push task is:

wherein the vector x _i A task characteristic value vector formed by task attribute characteristic data corresponding to the ith historical push task; vector w _u A user attribute weight vector formed by the user attribute feature data of the i-th historical pushing task for the task response active user u is obtained by statistics according to the user attribute feature data of all the first preset number of task response active users and response result tag data of a corresponding historical pushing data set of the task response active users;

7. A crowdsourcing task pushing device based on user preferences, as recited in claim 6, further comprising:

8. A crowdsourcing task push device based on user preferences, comprising a processor, a memory and a communication interface, the processor, memory and communication interface being interconnected, wherein the communication interface is for receiving and transmitting data, the memory is for storing program code, the processor is for invoking the program code to perform the method of any of claims 1-5.

9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1-5.