CN114154830A

CN114154830A - Activity quota allocation method, apparatus, device and medium

Info

Publication number: CN114154830A
Application number: CN202111419328.3A
Authority: CN
Inventors: 张晓文
Original assignee: Taikang Life Insurance Co ltd; Taikang Insurance Group Co Ltd
Current assignee: Taikang Life Insurance Co ltd; Taikang Insurance Group Co Ltd
Priority date: 2021-11-26
Filing date: 2021-11-26
Publication date: 2022-03-08

Abstract

An activity denomination assignment method, apparatus, device, and medium are disclosed to enable activity resources to be efficiently utilized to the maximum extent. According to the method and the device, when a request for participation of a currently logged account in activities is received, the target sales potential identification corresponding to the target identification information can be determined according to the target identification information of the currently logged account and the corresponding relation between each piece of identification information and the sales potential identification which is stored in advance; determining a target distribution denomination corresponding to the target sales potential identification according to each pre-stored sales potential identification, the corresponding relation between the activity identification information and the distribution denomination and the first activity identification information of the activity to be participated carried in the participation request; and according to the target allocation name, allocating the activity name of the activity of the first activity identification information to the currently logged account, thereby allocating the activity name suitable for the sales potential of the account to the currently logged account and enabling the activity resources to be effectively utilized to the maximum extent.

Description

Activity quota allocation method, apparatus, device and medium

Technical Field

The present application relates to the field of resource allocation technologies, and in particular, to a method, an apparatus, a device, and a medium for allocating activity denominations.

Background

Currently, for various activities including marketing customer acquisition activities, when allocating the denominations of customers who can participate in the activities to accounts of sales agents and the like, each sales agent (account) is allocated the denominations indiscriminately. For example, for a limited-denomination activity, each account is typically assigned an activity denomination in a first-come, first-serve manner until the activity denomination is assigned.

However, when an activity denomination is indiscriminately assigned to each sales agent (account) on a first-come first-serve basis, etc., the sales agent who receives the activity denomination may not be able to sufficiently and effectively utilize the activity denomination, which may result in waste of the activity denomination and a low utilization rate of the activity denomination (resource).

Therefore, how to allocate the activity denomination to each account so that the activity resources can be utilized to the maximum extent is a technical problem to be solved.

Disclosure of Invention

The application provides an activity denomination assignment method, device, equipment and medium, which are used for enabling activity resources to be effectively utilized to the maximum extent.

In a first aspect, the present application provides a method for activity denomination assignment, the method comprising:

if a request for participating in the activity by a currently logged account is received, determining a target sales potential identifier corresponding to target identification information according to the target identification information of the account and a pre-stored corresponding relationship between each piece of identification information and the sales potential identifier;

determining a target distribution quota corresponding to the target sales potentiality identification according to each pre-stored sales potentiality identification, the corresponding relation between the activity identification information and the distribution quota and the first activity identification information of the activity to be participated carried in the participation request;

and allocating the activity denomination of the activity of the first activity identification information to the account according to the target allocation denomination.

In a second aspect, the present application provides an activity denomination dispensing apparatus, the apparatus comprising:

the receiving module is used for receiving a participation request of a currently logged account to an activity;

the first determining module is used for determining a target sales potential identifier corresponding to the target identification information according to the target identification information of the account and the corresponding relationship between each piece of pre-stored identification information and the sales potential identifier;

a second determining module, configured to determine, according to each pre-stored sales potential identifier, a corresponding relationship between the activity identifier information and the allocation quota, and the first activity identifier information of the activity to be participated in the participation request, a target allocation quota corresponding to the target sales potential identifier;

and the allocation module is used for allocating the activity denomination of the activity of the first activity identification information to the account according to the target allocation denomination.

In a third aspect, the present application provides an electronic device comprising at least a processor and a memory, the processor being configured to implement the steps of an activity denomination allocation method as described in any one of the above when executing a computer program stored in the memory.

In a fourth aspect, the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of a method of activity denomination allocation as described in any one of the above.

According to the method and the device, when a request for participation of a currently logged account in activities is received, the target sales potential identification corresponding to the target identification information can be determined according to the target identification information of the currently logged account and the corresponding relation between each piece of identification information and the sales potential identification which is stored in advance; determining a target distribution denomination corresponding to the target sales potential identification according to each pre-stored sales potential identification, the corresponding relation between the activity identification information and the distribution denomination and the first activity identification information of the activity to be participated carried in the participation request; and according to the target allocation name, allocating the activity name of the activity of the first activity identification information to the currently logged account, so that the activity name suitable for the sales potential of the account can be allocated to the currently logged account.

Drawings

In order to more clearly illustrate the embodiments of the present application or the implementation manner in the related art, a brief description will be given below of the drawings required for the description of the embodiments or the related art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art according to the drawings.

FIG. 1 illustrates a first activity denomination assignment process schematic provided by some embodiments;

FIG. 2 illustrates a first schematic diagram provided by some embodiments for assigning an activity denomination to an account;

FIG. 3 illustrates a second exemplary allocation of an activity denomination to an account provided by some embodiments;

FIG. 4 illustrates a third schematic diagram provided by some embodiments for assigning an activity denomination to an account;

FIG. 5 illustrates a second activity denomination assignment process schematic provided by some embodiments;

FIG. 6 illustrates a diagram of a build account representation provided by some embodiments;

FIG. 7 illustrates an activity quota allocation architecture provided by some embodiments;

FIG. 8 illustrates an activity denomination assignment flow diagram provided by some embodiments;

FIG. 9 illustrates a schematic diagram of an activity denomination dispensing device, according to some embodiments;

fig. 10 is a schematic structural diagram of an electronic device according to some embodiments.

Detailed Description

In order to make the active resources available to the maximum extent, the present application provides an active quota allocation method, apparatus, device and medium.

To make the purpose and embodiments of the present application clearer, the following will clearly and completely describe the exemplary embodiments of the present application with reference to the attached drawings in the exemplary embodiments of the present application, and it is obvious that the described exemplary embodiments are only a part of the embodiments of the present application, and not all of the embodiments.

The terms "first," "second," "third," and the like in the description and claims of this application and in the above-described drawings are used for distinguishing between similar or analogous objects or entities and not necessarily for describing a particular sequential or chronological order, unless otherwise indicated. It is to be understood that the terms so used are interchangeable under appropriate circumstances.

The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and/or software code that is capable of performing the functionality associated with that element.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Example 1:

fig. 1 shows a schematic diagram of a first activity denomination assignment process provided by some embodiments, which, as shown in fig. 1, includes the following steps:

s101: and if a request for participating in the activity by the currently logged account is received, determining a target sales potential identifier corresponding to the target identifier information according to the target identifier information of the account and the corresponding relationship between each piece of identifier information and the sales potential identifier, which is pre-stored.

The activity quota allocation method provided by the embodiment of the application is applied to electronic equipment, and the electronic equipment can be equipment such as a PC (personal computer) and a mobile terminal, and can also be a server.

In one possible implementation manner, when the sales agent clicks a certain activity in an activity list of an activity area, such as a customer activity area, or when the sales agent (for convenience of description, referred to as an agent) clicks a button, such as "participate in an activity" of a certain activity, the electronic device may receive a participation request of a currently logged-in account for the activity, where the participation request may carry activity identification information (for convenience of description, referred to as first activity identification information) of an activity (to be participated in by the sales agent) to participate in the activity.

In a possible implementation manner, the electronic device may pre-store a corresponding relationship between the identification information of each account and the sales potential identifier, where the identification information of the account and the corresponding sales potential identifier may be flexibly set according to a requirement, and this application is not particularly limited thereto. Illustratively, the sales potential identification may include high sales potential, medium sales potential, low sales potential, and the like.

After receiving a request for participating in a campaign from a currently logged-in account, the electronic device may determine, according to identification information (referred to as target identification information for convenience of description) of the currently logged-in account and a correspondence between each piece of identification information and a sales potential identification, a sales potential identification (referred to as a target sales potential identification for convenience of description) corresponding to the target identification information.

S102: and determining a target distribution quota corresponding to the target sales potentiality identification according to each pre-stored sales potentiality identification, the corresponding relation between the activity identification information and the distribution quota and the first activity identification information of the activity to be participated carried in the participation request.

In a possible implementation manner, in order to quickly and intelligently allocate the activity denomination to the account, so that the activity resource can be effectively utilized to the maximum extent, the electronic device may pre-store the corresponding relationship between each sales potential identifier, the activity identifier information and the allocation denomination. Each sales potential identifier, the activity identifier information and the corresponding allocation quota can be flexibly set according to the requirement, and the application is not particularly limited to this.

After the target sales potential identifier corresponding to the target identifier information is determined, the electronic device may determine the target distribution denomination corresponding to the target sales potential identifier according to each pre-stored sales potential identifier, the corresponding relationship between the activity identifier information and the distribution denomination, and the first activity identifier information of the activity to be participated in, which is carried in the participation request.

Illustratively, if the pre-stored corresponding relationship between the sales potential identifier, the activity identifier information and the allocation denomination includes a corresponding relationship between high sales potential and 3 lottery activities and allocation denomination, a corresponding relationship between the lottery activities and the allocation denomination 1 in the sales potential, and a corresponding relationship between low sales potential and 0 lottery activities and allocation denomination; the first activity identification information of the activity to be participated in carried in the participation request is lottery activity; when the target sales potential identifier is high in sales potential, it can be determined that the target allocation denomination corresponding to the target sales potential identifier is 3. When the target sales potential identifier is in the sales potential, it can be determined that the target allocation amount corresponding to the target sales potential identifier is 1. When the target sales potential identifier is low in sales potential, it may be determined that the target allocation quota corresponding to the target sales potential identifier is 0.

S103: and allocating the activity denomination of the activity of the first activity identification information to the account according to the target allocation denomination.

After the target allocation denomination is determined, the activity denomination of the activity (activity to be participated in) of the first activity identification information can be allocated to the currently logged-in account according to the target allocation denomination. Typically, the target may be assigned an active denomination assigned to the currently logged-in account. Still taking the above embodiment as an example, referring to fig. 2, fig. 2 shows a schematic diagram of allocating an active denomination to an account according to a first method provided by some embodiments, as shown in fig. 2, if the target allocation denomination is 3, the active denomination allocated to the currently logged-in account may be 3. In one possible implementation, the account may be assigned an activity denomination, and information such as an activation code may be assigned in an amount equal to the target assignment denomination, and the agent may send the activation code or the like to the customer, and may determine whether the customer has picked up the activity resource based on whether the activation code or the like is used. Referring to fig. 2, if the agent assigns the activity denominations to three agents, vie three, lie four, and wang two, respectively, wherein the zhe three activates (uses) the corresponding activation code, the state corresponding to the zhe three may be updated to "picked", and the lie four and wang two temporarily do not use the activation code, the state corresponding to the lie four and wang two may be "not picked". In addition, the picking rate may also be determined based on the total number of target allocation denominations (total number of co-acquirements) and the number of clients that have picked up active resources, and for example, if the total number of target allocation denominations is 3 and 1 client currently picks up active resources, the picking rate may be 33%.

Referring to fig. 3, fig. 3 is a diagram illustrating a second example of allocating an active denomination to an account according to some embodiments, and as shown in fig. 3, if the target allocation denomination is 1, the active denomination allocated to the currently logged-in account may be 1. Referring to fig. 4, fig. 4 shows a schematic diagram of allocating an active denomination to an account according to a third method provided by some embodiments, as shown in fig. 4, if the target allocation denomination is 0, the active denomination allocated to the currently logged-in account may be 0.

Meanwhile, the method and the system can allocate the activity denominations suitable for the sales potential of the account for the currently logged-in account, for example, more activity denominations can be allocated for sales agents with higher sales potential, so that the activity resources can be inclined to the sales agents with higher sales potential in a targeted manner.

Example 2:

in order to make the active resource maximally utilized, in the embodiment of the present application, before receiving the request for participation of the currently logged-in account in the activity, the method further includes:

if an access activity list request of the currently logged account is received, determining a target preference activity type corresponding to target identification information according to the target identification information of the account and a corresponding relation between each piece of identification information and a preference activity type which is stored in advance;

determining second activity identification information corresponding to the target preference activity type according to the corresponding relation between each pre-stored activity identification information and the activity type;

and displaying the activity of the second activity identification information in the activity list.

In the related art, when each activity is displayed in an activity list (activity section), each activity is usually sequentially displayed in the activity list according to the sequence of the online time of each activity (such as a sales acquisition activity). The activity information displayed in the activity list is indifferent to each sales agent, namely, each sales agent sees the same activity information, whether the sales agent clicks to check the activity or not, and the subjective activity of the sales agent is mainly used.

In one possible implementation, in order to improve the click rate of the sales agent on the activities shown in the activity list and further promote that the activity resources can be utilized to the maximum extent, the electronic device may pre-store the correspondence between the identification information of each sales agent's account and the preferred activity type, and when receiving an access request (access activity list request) from the currently logged-in account to the activity list, may determine the preferred activity type (referred to as a target preferred activity type for convenience of description) corresponding to the target identification information according to the target identification information of the currently logged-in account and the pre-stored correspondence between each identification information and the preferred activity type; then, according to the corresponding relation between each piece of pre-stored activity identification information and the activity type, determining the activity identification information (called as second activity identification information for convenient description) corresponding to the target preference activity type; and then, in the activity list, the activity of the second activity identification information is shown. In a possible implementation manner, only the activities of the second activity identification information may be displayed in the activity list, or the activities of the second activity identification information may be preferentially displayed in the activity list, which may be flexibly set according to the requirements.

In one possible implementation, when the campaign of the second campaign identification information is preferentially shown in the campaign list, each campaign may be shown according to the display priority of each campaign included in the campaign list, where the display priority of the campaign of the second campaign identification information may be the highest. For example, the activity of the second activity identification information may be presented at the head of the activity list, and other activities than the activity of the second activity identification information may be presented after the activity of the second identification information, so that the sales agent may view the activity of the second activity identification information preferentially.

Since the activity type of the activity of the second activity identification information is the activity type preferred by the sales agent, the activity of the second activity identification information is preferentially displayed in the activity list, so that the click rate of the sales agent on the activity displayed in the activity list can be improved, and further, the activity resources can be promoted to be utilized to the maximum extent.

For ease of understanding, the activity denomination assignment process provided herein is explained below with a specific embodiment. Fig. 5 is a schematic diagram of a second activity denomination assignment process provided by some embodiments, as shown in fig. 5, which includes the steps of:

s501: and if an access activity list request of the currently logged account is received, determining a target preference activity type corresponding to the target identification information according to the target identification information of the currently logged account and the corresponding relationship between each piece of identification information and the preference activity type, which is stored in advance.

S502: and determining second activity identification information corresponding to the target preference activity type according to the corresponding relation between each pre-stored activity identification information and the activity type.

S503: and displaying each activity according to the display priority of each activity contained in the activity list, wherein the display priority of the activity of the second activity identification information is the highest.

S504: and if a request for participating in the activity by the currently logged account is received, determining a target sales potential identifier corresponding to the target identifier information according to the target identifier information of the currently logged account and the corresponding relationship between each piece of identifier information and the sales potential identifier, which is pre-stored.

S505: and determining a target distribution denomination corresponding to the target sales potential identification according to each pre-stored sales potential identification, the corresponding relation between the activity identification information and the distribution denomination and the first activity identification information of the activity to be participated carried in the participation request.

S506: and allocating the activity denomination of the activity of the first activity identification information to the currently logged account according to the target allocation denomination.

Example 3:

in order to accurately determine the corresponding relationship between the identification information of each account and the sales potential identification, on the basis of the above embodiments, in the embodiment of the present application, the process of determining the corresponding relationship between each identification information and the sales potential identification includes:

aiming at each account with identification information, inputting first attribute information of the account with the identification information into a sales potential determination model trained in advance; determining the sales potential identification of the account of the identification information according to the output result of the sales potential determination model; and storing the corresponding relation between the identification information of the account and the sales potential identification of the account.

In a possible implementation manner, when determining the corresponding relationship between the identification information of each account and the sales potential identification, for each account of the identification information, the attribute information (referred to as first attribute information for convenience of description) of the historical activity participation rate, the customer-obtaining conversion rate, the activity, and the like of the account of the identification information may be input into the sales potential determination model trained in advance. Then, according to the output result of the sales potential determination model, the sales potential identification of the account of the identification information is determined. After the sales potential identifier of the account with the identification information is determined, the corresponding relationship between the identification information of the account and the sales potential identifier of the account can be stored.

Example 4:

in order to train the sales potential determination model, on the basis of the above embodiments, in an embodiment of the present application, the training process of the sales potential determination model includes:

acquiring first sample attribute information of any account in a sample set, wherein the first sample attribute information corresponds to a sample sales potential identification label;

determining an identification sales potential identification tag of the first sample attribute information through an original sales potential determination model;

and training an original sales potential determination model according to the sample sales potential identification label and the recognition sales potential identification label.

In the embodiment of the application, the sales potential identification of the account can be determined through a sales potential determination model which is trained in advance. Specifically, in training the sales potential determination model, the sample set may contain attribute information (referred to as first sample attribute information for convenience of description) of a plurality of accounts. In one possible implementation, the first sample attribute information of any account included in the sample set corresponds to a sample sales potential identification tag, and the sample sales potential identification tag can be used for identifying the sales potential identification of the account.

When the original sales potential determination model is trained, first sample attribute information of any account in a sample set can be obtained, and the first sample attribute information corresponds to a sample sales potential identification label. Inputting the acquired first sample attribute information of any account into an original sales potential determining model, and acquiring an identification sales potential identification label corresponding to the first sample attribute information through the original sales potential determining model.

In specific implementation, after the identification sales potential identification tag of the input first sample attribute information is determined, because the sample sales potential identification tag of the first sample attribute information is pre-stored, whether the identification result of the sales potential determination model is accurate can be determined according to whether the sample sales potential identification tag of each pixel point is consistent with the identification sales potential identification tag. In specific implementation, if the results of the recognition of the sales potential determination model are not accurate, parameters of the sales potential determination model need to be adjusted, so that the sales potential determination model is trained.

In a specific implementation, when parameters in the sales potential determination model are adjusted, a gradient descent algorithm may be adopted to perform back propagation on the gradient of the parameters of the sales potential determination model, so as to train the sales potential determination model.

In a possible implementation manner, the above operation may be performed on the first sample attribute information of each account in the sample set, and when a preset convergence condition is met, it is determined that the sales potential determination model is trained completely.

The first sample attribute information of the account in the sample set can pass through the original sales potential determination model when the preset convergence condition is met, the number of the correctly identified first sample attribute information is larger than the set number, or the iteration number of training the sales potential determination model reaches the set maximum iteration number, and the like. The specific implementation can be flexibly set, and is not particularly limited herein.

In a possible implementation manner, when training the original sales potential determination model, the first sample attribute information in the sample set may be divided into first training sample attribute information and first test sample attribute information, the original sales potential determination model is trained based on the first training sample attribute information, and then the reliability of the trained sales potential determination model is verified based on the first test sample attribute information.

Example 5:

in order to determine the correspondence between the identification information of each account and the preferred activity type, on the basis of the foregoing embodiments, in an embodiment of the present application, the process of determining the correspondence between each identification information and the preferred activity type includes:

for each account of the identification information, inputting second attribute information of the account of the identification information into a preference activity type determination model which is trained in advance; determining the preference activity type of the account of the identification information according to the output result of the preference activity type determination model; and storing the corresponding relation between the identification information of the account and the preference activity type of the account.

In one possible implementation, when determining the correspondence between the identification information of each account and the preferred activity type, the account base information of each account including gender, age, and the like of the identification information may be determined for each account of the identification information; work performance information such as activity participation rate, participation activity type and the like; attribute information (called as second attribute information for convenience of description) including at least one item of current behavior data information such as a current browsing activity type and current search information is input into a preference activity type determination model which is trained in advance, and a preference activity type of an account of the identification information is determined according to an output result of the preference activity type determination model. For example, the preferred activity type of the account may be a game type activity type, a lottery type activity type, or the like, and the preferred activity type of the account is not particularly limited in this application. After the preferred activity type of the account is determined, the correspondence between the identification information of the account and the preferred activity type of the account may be saved.

Example 6:

in order to train the preference activity type determination model, on the basis of the above embodiments, in an embodiment of the present application, a training process of the preference activity type determination model includes:

acquiring second sample attribute information of any account in a sample set, wherein the second sample attribute information corresponds to a sample preference activity type label;

determining a recognition preference activity type label of the second sample attribute information through an original preference activity type determination model;

and training an original preference activity type determination model according to the sample preference activity type label and the identification preference activity type label.

In the embodiment of the application, the preference activity type of the account can be determined through a pre-trained preference activity type determination model. Specifically, in training the preference activity type determination model, the sample set may contain attribute information (referred to as second sample attribute information for convenience of description) of a plurality of accounts. In one possible implementation, the second sample attribute information of any account included in the sample set corresponds to a sample preferred activity type tag, and the sample preferred activity type tag can be used for identifying a preferred activity type of the account.

When the original preference activity type determination model is trained, second sample attribute information of any account in the sample set can be obtained, and the second sample attribute information corresponds to a sample preference activity type label. Inputting the obtained second sample attribute information of any account into an original preference activity type determination model, and obtaining an identification preference activity type label corresponding to the second sample attribute information through the original preference activity type determination model.

In specific implementation, after the identification preference activity type tag of the input second sample attribute information is determined, because the sample preference activity type tag of the second sample attribute information is pre-stored, whether the identification result of the preference activity type determination model is accurate can be determined according to whether the sample preference activity type tag of the second sample attribute information of each account is consistent with the identification preference activity type tag. In specific implementation, if the difference indicates that the recognition result of the preference activity type determination model is inaccurate, parameters of the preference activity type determination model need to be adjusted, so that the preference activity type determination model is trained.

In specific implementation, when parameters in the preference activity type determination model are adjusted, a gradient descent algorithm can be adopted to perform back propagation on the gradient of the parameters of the preference activity type determination model, so that the preference activity type determination model is trained.

In one possible implementation, the above operations may be performed on the second sample attribute information of each account in the sample set, and when a preset convergence condition is satisfied, it is determined that the training of the preference activity type determination model is completed.

The second sample attribute information of the account in the sample set can pass through the original preference activity type determination model when the preset convergence condition is met, the number of the second sample attribute information which is correctly identified is larger than the set number, or the iteration number of training the preference activity type determination model reaches the set maximum iteration number, and the like. The specific implementation can be flexibly set, and is not particularly limited herein.

In a possible implementation manner, when training the original preference activity type determination model, the second sample attribute information in the sample set may be divided into second training sample attribute information and second test sample attribute information, the original preference activity type determination model is trained based on the second training sample attribute information, and then the reliability of the trained preference activity type determination model is verified based on the second test sample attribute information.

In one possible implementation, account information such as sales potential identification of the account, preferred activity type, etc. may be built into the picture of the account. FIG. 6 illustrates a schematic diagram of an account representation built according to some embodiments, and as shown in FIG. 6, when building a representation of an account, attribute information of the account may be first obtained from basic databases in an electronic device based on a data acquisition layer in the electronic device. For example, the acquired attribute information may include account basic data (referred to as cold data for convenience of description) that may reflect the basic situation of the agent and that may not easily change over time, such as the sex, age, location, job level, and working time of the account. The acquired attribute information may further include work performance data of the account in the last period of time (current statistical period), such as the amount of deals, the number of new customers, the number of old customers, the type of policy, the conversion rate of customers, the participation rate of activities, the activity level, and other data that can reflect the recent situation of the agent (for convenience of description, referred to as temperature data). In addition, the obtained attribute information may also include current behavior data of the account, for example, data (referred to as hot data for convenience of description) that may reflect what the agent is doing, such as current search content, click content, filter content, whether to share activities, and the like of the account.

In one possible implementation, the cold data, the temperature data, the hot data, and the like of the account may be used as second attribute information (for convenience of description, referred to as a fact tag), and the second attribute information is input into a pre-trained preference activity type determination model to determine the preference activity type of the account.

In a possible implementation mode, the access time of the agent (account) access activity and the like can be counted, and the active time interval and the like of account preference are determined based on the access time of the account. The attribute information and information such as preference activity type and preference active time interval of the account obtained based on the attribute information can be used as first sample attribute information (for convenience of description, called as a model label), the first attribute information of the account is input into a sales potential determination model which is trained in advance, and then a sales potential identification (for convenience of description, called as an advanced label) of the account is determined.

In one possible implementation, a representation of the account may be constructed based on fact tags, model tags, advanced tags, and the like. For example, the existing technologies such as text mining, natural language processing, machine learning (clustering), deep learning, etc. may be used to construct the portrait of the account, which is not described herein again.

In one possible implementation, after a representation is constructed for each account, the representation quality may be evaluated prior to performing any of the above steps of the activity denomination assignment method using information in the representation, such as sales potential identification, preferred activity type, etc. If the portrait quality evaluation result shows that the portrait quality is qualified, the portrait quality of each account can be considered to be higher, and any step of the activity denomination assignment method can be carried out based on the constructed account portrait. And if the image quality evaluation result shows that the image quality is unqualified, the image quality of each account is considered to be low, the image needs to be reconstructed until the image quality evaluation result shows that the image quality is qualified, and then the step of the activity denomination allocation method is carried out based on the image with qualified quality.

In one possible embodiment, the image quality may be evaluated by a/B testing based on a small portion of the account (small volume). Illustratively, the following steps may be taken in evaluating the portrait quality based on the A/B test:

first, a part of accounts are extracted from all accounts, and the step of the activity denomination assignment method described in any one of the above embodiments of the present application (for convenience of description, referred to as the account portrait-based manner of the present application) is performed based on the extracted account portrait of the part of accounts, that is, a process in S101-S103 described above may be performed to assign an activity denomination suitable for the sales potential of the account to the currently registered account based on the sales potential identifier in the account portrait, and a process in S501-S503 described above may be performed to preferentially present activities of activity types preferred by the sales agent (activities of the second activity identification information) in the activity list. Meanwhile, when the extracted part of accounts are in the account portrait-based mode, activity participation parameters (called group A account activity participation parameters for convenience of description) such as the click rate of activity, the reading time and the like can be counted.

In addition, the activity name can be allocated to the extracted part of accounts in a mode of allocating activity names to each sales agent (account) indiscriminately based on first-come first-serve and the like in the related technology, the activity information displayed in the activity list in the related technology is used for displaying the activity information (for convenience of description, the mode of not being based on account portrait in the related technology) for each sales agent in a mode of no difference, and meanwhile, when the part of accounts are used in the mode of not being based on account portrait in the related technology, activity participation parameters (for convenience of description, called B group account activity participation parameters) such as click rate, reading time and the like of activities are counted.

Then, comparing whether the value of the group A account activity participation parameter exceeds the value of the group B account activity participation parameter; if the value of the group A account activity participation parameter exceeds (is larger than) the value of the group B account activity participation parameter, the account portrait quality can be considered to be qualified. And if the value of the group A account activity participation parameter does not exceed (is less than or equal to) the value of the group B account activity participation parameter, the account portrait quality is not qualified.

Fig. 7 is a schematic diagram of an activity rating allocation architecture according to some embodiments, as shown in fig. 7, attribute information of an account may be collected from each basic database based on a data collection layer in an electronic device, where the attribute information of the account may include account basic data that may reflect basic conditions of an agent, work performance data (such as agent customer data, agent transaction data, policy data, and the like), and agent behavior data (agent App behavior data) that may reflect what the agent is doing (what is doing in an Application program (App)).

Then, the data analysis and mining layer in the electronic device may determine account identifiers of the same account (user) in each basic database, unify the account identifiers of the same account in different basic databases (unify user identifiers), perform cleaning, clustering and analysis on the attribute information of the account collected from each basic database based on the unified account identifiers, and determine (define) different levels of tags (tag system definition) such as fact tags, model tags and advanced tags of the account.

Then, based on the labels of different layers, the portrait of the account (portrait characteristic construction) can be constructed, and the portrait quality is evaluated. The data analysis and mining layer can be based on text mining, natural language processing, machine learning (clustering), deep learning and other modes when the account portrait is constructed.

Service layers in electronic devices may contain both business services and system services. The service can have functions such as a portrait billboard (an agent and the like can view own portrait based on the portrait billboard), label management and the like; the system service is mainly an API interface service, and the service layer can interact with other levels such as an application layer, a data analysis and mining layer and the like based on the API interface.

The activity denomination assignment method described in any of the above embodiments in this application may be stored in an application layer in the electronic device, and the application layer may assign activity denominations to agents (classify agents, assign different activity denominations to agents with different sales potential identifications), display activities in an activity list (personalized push activities), and the like based on any of the above activity denomination assignment methods.

Fig. 8 shows a schematic flow chart of activity denomination assignment provided by some embodiments, and as shown in fig. 8, the process includes the following steps:

firstly, a data acquisition layer can acquire attribute information such as basic data of an account in each basic database; the data analysis and mining layer can unify account identifications of the same account in all databases, perform data fusion on attribute information of the same account in different basic databases, and then perform label system definition to define labels of different levels such as fact labels, model labels and advanced labels. Then, based on labels of different layers, an account portrait is constructed (portrait characteristics are constructed); after the portrait is constructed, A/B testing can be carried out, the quality of the portrait is evaluated, if the quality of the portrait is qualified, the portrait can be displayed through a portrait billboard in the service layer, the service layer can manage all labels contained in the portrait, and meanwhile, the service layer can send the portrait to the application layer through an API (application programming interface). After the agent logs in the relevant App in the electronic device, the application layer in the electronic device may perform operations such as allocating activity denominations for the agent (classifying the agents, allocating different activity denominations for agents with different sales potential identifications) and displaying activities (personalized push activities) in an activity list based on the account representation.

Example 7:

based on the same technical concept, the present application provides an activity denomination dispensing device, fig. 9 shows a schematic view of an activity denomination dispensing device provided by some embodiments, as shown in fig. 9, the device includes:

a receiving module 91, configured to receive a request for participation in an activity from a currently logged account;

a first determining module 92, configured to determine, according to the target identification information of the account and a correspondence between each piece of pre-stored identification information and a sales potential identification, a target sales potential identification corresponding to the target identification information;

a second determining module 93, configured to determine, according to each pre-stored sales potential identifier, a corresponding relationship between the activity identifier information and the allocation quota, and the first activity identifier information of the activity to be participated in the participation request, a target allocation quota corresponding to the target sales potential identifier;

an allocating module 94, configured to allocate an activity denomination of an activity of the first activity identification information to the account according to the target allocation denomination.

In a possible embodiment, the apparatus further comprises:

the display module is used for determining a target preference activity type corresponding to the target identification information according to the target identification information of the account and the corresponding relation between each piece of identification information and the preference activity type which is stored in advance if the access activity list request of the currently logged account is received; determining second activity identification information corresponding to the target preference activity type according to the corresponding relation between each pre-stored activity identification information and the activity type; and displaying the activity of the second activity identification information in the activity list.

In a possible implementation manner, the presentation module is specifically configured to present each activity according to a presentation priority of each activity included in the activity list, where the presentation priority of the activity of the second activity identification information is the highest.

In a possible embodiment, the first determining module 92 is specifically configured to, for each account with identification information, input first attribute information of the account with identification information into a sales potential determining model trained in advance; determining the sales potential identification of the account of the identification information according to the output result of the sales potential determination model; and storing the corresponding relation between the identification information of the account and the sales potential identification of the account.

In a possible implementation manner, the presentation module is specifically configured to, for each account of identification information, input second attribute information of the account of the identification information into a preference activity type determination model trained in advance; determining the preference activity type of the account of the identification information according to the output result of the preference activity type determination model; and storing the corresponding relation between the identification information of the account and the preference activity type of the account.

Example 8:

based on the same technical concept, the present application provides an electronic device, and fig. 10 shows that some embodiments provide a structural schematic diagram of an electronic device, as shown in fig. 10, the electronic device includes: the system comprises a processor 101, a communication interface 102, a memory 103 and a communication bus 104, wherein the processor 101, the communication interface 102 and the memory 103 are communicated with each other through the communication bus 104;

the memory 103 has stored therein a computer program which, when executed by the processor 101, causes the processor 101 to perform the steps of:

In a possible implementation manner, the processor 101 is further configured to, before the request for participation of the currently logged-in account in the activity is received, determine, if a request for accessing the activity list of the currently logged-in account is received, a target preference activity type corresponding to the target identification information according to the target identification information of the account and a correspondence between each piece of identification information and a preference activity type that is pre-stored;

In a possible implementation manner, the processor 101 is specifically configured to present each campaign according to a presentation priority of each campaign included in the campaign list, where the presentation priority of the campaign of the second campaign identification information is the highest.

In a possible embodiment, the processor 101 is specifically configured to, for each account of identification information, input first attribute information of the account of identification information into a sales potential determination model trained in advance; determining the sales potential identification of the account of the identification information according to the output result of the sales potential determination model; and storing the corresponding relation between the identification information of the account and the sales potential identification of the account.

In a possible implementation manner, the processor 101 is specifically configured to obtain first sample attribute information of any account in a sample set, where the first sample attribute information corresponds to a sample sales potential identification tag;

In a possible implementation manner, the processor 101 is specifically configured to, for each account of identification information, input second attribute information of the account of identification information into a pre-trained preference activity type determination model; determining the preference activity type of the account of the identification information according to the output result of the preference activity type determination model; and storing the corresponding relation between the identification information of the account and the preference activity type of the account.

In a possible implementation manner, the processor 101 is specifically configured to obtain second sample attribute information of any account in a sample set, where the second sample attribute information corresponds to a sample preference activity type tag;

Because the principle of the electronic device for solving the problem is similar to the activity quota allocation method, the implementation of the electronic device can be referred to the implementation of the method, and repeated details are not repeated.

The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

The communication interface 102 is used for communication between the above-described electronic device and other devices.

The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Alternatively, the memory may be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a central processing unit, a Network Processor (NP), and the like; but may also be a Digital instruction processor (DSP), an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like.

Example 9:

based on the same technical concept, the present application provides a computer-readable storage medium having stored therein a computer program executable by an electronic device, the program, when executed on the electronic device, causing the electronic device to perform the following steps:

In one possible embodiment, before receiving the request for participation in the activity from the currently logged-in account, the method further includes:

In a possible embodiment, the activity of presenting the second activity identification information in the activity list includes:

and displaying each activity according to the display priority of each activity contained in the activity list, wherein the display priority of the activity of the second activity identification information is the highest.

In one possible embodiment, the process of determining the corresponding relationship between each identification information and the sales potential identification includes:

In one possible embodiment, the training process of the sales potential determination model includes:

In one possible embodiment, the process of determining the correspondence of each identification information to the preferred activity type includes:

In one possible embodiment, the training process of the preference activity type determination model includes:

The computer readable storage medium may be any available medium or data storage device that can be accessed by a processor in an electronic device, including but not limited to magnetic memory such as floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc., optical memory such as CDs, DVDs, BDs, HVDs, etc., and semiconductor memory such as ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs), etc.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A method for activity denomination assignment, the method comprising:

2. The method of claim 1, wherein prior to receiving a request for participation in an activity by a currently logged-in account, the method further comprises:

3. The method according to claim 2, wherein the activity of presenting the second activity identification information in the activity list comprises:

4. The method of claim 1, wherein the step of determining the correspondence between each identification information and the sales potential identification comprises:

5. The method of claim 4, wherein the training process of the sales potential determination model comprises:

6. The method of claim 2, wherein determining the correspondence of each identification information to a preferred activity type comprises:

7. The method of claim 6, wherein the training process of the preference activity type determination model comprises:

8. An activity denomination assignment device, characterized in that the device comprises:

9. An electronic device, characterized in that the electronic device comprises at least a processor and a memory, the processor being adapted to carry out the steps of an activity denomination allocation method according to any one of claims 1 to 7, when executing a computer program stored in the memory.

10. A computer-readable storage medium, characterized in that it stores a computer program which, when being executed by a processor, carries out the steps of an activity denomination allocation method according to any one of claims 1 to 7.