CN117499537A - Data processing method and device, electronic equipment and storage medium - Google Patents

Abstract

The present disclosure provides a data processing method and apparatus thereof, an electronic device, and a storage medium, the method including: acquiring a plurality of pushed lists; generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same; packaging the plurality of activities to generate an outbound task; and ordering lists in the outbound tasks based on the target ordering strategy and the target ordering algorithm to obtain target outbound tasks, wherein at least part of lists included in the target outbound tasks are irregular in ordering. The embodiment of the disclosure improves the user conversion rate.

Description

Data processing method and device, electronic equipment and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a data processing method and device, electronic equipment and a storage medium.

Background

The electric pin system generally distributes a new daily list to the outbound system to predict outbound (namely, outbound mode of switching on to the seat after switching on the user) so as to improve the seat utilization rate. However, in the process of using the predictive outbound, since a plurality of activities (refer to a list set of the same type) are packaged into a predictive outbound task and sent to the outbound system, the outbound system makes calls according to the list order in the predictive outbound task.

Because the activity information and the user information contained in the list can be used for evaluating the user, when the user is connected to the agent, the agent can estimate whether the subsequent connected list belongs to the user with lower quality. Therefore, after the users with lower quality are connected, some agents close the predicted outgoing calls, and when the list calls are finished, the predicted outgoing calls are restarted, so that the conversion rate of the users can be influenced.

Disclosure of Invention

The embodiment of the disclosure provides a data processing method, a device thereof, electronic equipment and a storage medium, so as to improve the conversion rate of a user.

In a first aspect, the present disclosure provides a data processing method, which may include:

acquiring a plurality of pushed lists;

generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same;

generating outbound tasks for the plurality of activities;

and ordering the lists in the outbound tasks based on a target ordering strategy and a target ordering algorithm to obtain target outbound tasks, wherein at least part of lists included in the target outbound tasks are irregular in ordering.

In a second aspect, the present disclosure provides a data processing apparatus, which may include:

The acquisition module is used for acquiring a plurality of pushed lists;

the first generation module is used for generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same;

the second generation module is used for generating outbound tasks from the activities;

the ordering module is used for ordering the lists in the outbound tasks based on a target ordering strategy and a target ordering algorithm to obtain target outbound tasks, and at least part of lists included in the target outbound tasks are irregular in ordering.

In a third aspect, the present disclosure provides an electronic device, which may include:

at least one processor;

at least one memory; the method comprises the steps of,

one or more input/output I/O interfaces coupled between the processor and the memory;

wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executable by the at least one processor to enable the at least one processor to perform the data processing method.

In a fourth aspect, the present disclosure provides a computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the data processing method described above.

According to the embodiment provided by the disclosure, the target outbound task is obtained by sequencing the lists in the outbound task, so that at least part of lists in the target outbound task are not sequenced regularly, and the user quality of the lists in the target outbound task sent to the agent is not circulated regularly, so that the agent cannot reduce the user quality in the next list and expect, the condition that the agent closes the answer because the agent predicts that the subsequent user quality is lower is avoided, the agent utilization rate is improved, and the user conversion rate is correspondingly increased.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings are included to provide a further understanding of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, without limitation to the disclosure. The above and other features and advantages will become more readily apparent to those skilled in the art by describing in detail exemplary embodiments with reference to the attached drawings, in which:

FIG. 1 is a flow chart of a data processing method provided in an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of the workflow of an upstream system, an electrical pinning system, and an outbound system provided by embodiments of the present disclosure;

FIG. 3 is a schematic diagram of a data processing method according to an embodiment of the disclosure;

FIG. 4 is a block diagram of a data processing apparatus according to an embodiment of the present disclosure;

fig. 5 is a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

For a better understanding of the technical solutions of the present disclosure, exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Embodiments of the disclosure and features of embodiments may be combined with each other without conflict.

As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

It should be noted that, all user data related in the embodiments of the present application are data input by the user, and the data acquisition needs to be confirmed by the authorization of the user. Therefore, in the technical scheme of the disclosure, the related processes of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user accord with the regulations of related laws and regulations, and the public welfare is not violated.

The current outbound scheme is: after the list arrives at the electric pin system from the upstream system, packing and distributing a plurality of active lists to the outbound system to predict outbound; the seat starts the function of answering the predicted outbound, waits for the outbound system to switch on the list, predicts the outbound according to the list sequence in the predicted outbound task, switches on the seat after switching on the list, and reenters the predicted outbound queue for waiting for the next round of predicted outbound.

Some technical terms are first described below:

upstream system: means a system that transmits the listing information to the electrical pinning system;

electric pin system: refers to a system responsible for handling specific flow logic for telemarketing;

seat: refers to telemarketing representatives or specialists;

list: means marketing data containing user information and campaign information;

Activity: a list set with the same name list marketing type;

predicting outbound calls: the method is that a received list sent by an upstream system is pushed to an outbound system for calling, and the outbound mode of the idle seat is switched on after the list is switched on;

skill set: refers to a collection of agents that are dedicated to dialing certain activities.

The current outbound mode is: after the list arrives at the electric pin system from the upstream system, packing and distributing a plurality of active lists to the outbound system to predict outbound; the seat starts the function of answering the predicted outbound, waits for the outbound system to switch on the list, predicts the outbound according to the list sequence in the predicted outbound task, switches on the seat after switching on the list, and reenters the predicted outbound queue for waiting for the next round of predicted outbound. Because the list order is ordered according to the quality of the users, the activity information and the user information contained in the list can be used for evaluating the users, and when the users are connected to the agents, the agents can estimate whether the subsequent connected list belongs to the users with lower quality. Therefore, after the users with low quality are connected, some agents can close the predicted outgoing call, and after the list calls are finished, the predicted outgoing call is restarted, so that the conversion rate of the users can be influenced.

According to the embodiment of the disclosure, the outbound lists are ordered through the call ordering strategy, and under the condition of maximally utilizing the seat resources, the acquired list resources are wasted through avoiding the seat utilization rule holes by the technical means, so that the list conversion rate of the electric pin system is maximized, and a technical basis is provided for improving the overall performance. The embodiments of the present disclosure are described in detail below.

The embodiment of the disclosure provides a data processing method, which can be applied to an electric pin system, as shown in fig. 1, 2 and 3, and the method can comprise the steps of S11-S14:

s11, acquiring a plurality of pushed lists.

S12, generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same.

S13, generating outbound tasks from the plurality of activities.

S14, ordering lists in the outbound tasks based on the target ordering strategy and the target ordering algorithm to obtain target outbound tasks, wherein at least part of lists included in the target outbound tasks are irregular in ordering.

In the embodiment of the disclosure, each list pushed by the upstream system corresponds to a corresponding user quality (or user evaluation index), and can be used for indicating the marketing value of the user. The higher the user quality, the higher the marketing value; the lower the user quality, the lower the marketing value.

In the disclosed embodiments, user quality may be expressed in terms of user scoring.

In embodiments of the present disclosure, each list may include, but is not limited to, user information and activity information; the user information may include, but is not limited to, a user number, a user last name and/or first name, a user income bracket, a user occupation (where the user income bracket and the user occupation may be used to indicate user quality), and the like. The campaign information refers to information of a type of marketing required to be performed on the user; the activity information may include, but is not limited to: activity codes, activity names, activity content, etc.

In the embodiment of the disclosure, the ranking strategy of the list can be pre-created, the ranking strategy can be used as the ranking basis of the list, the ranking strategy can comprise a plurality of types, so that the list can be ranked by selecting a proper ranking strategy from the ranking strategy according to different activities and different demands when business adjustment occurs, and a new ranking strategy can be created at any time according to the demands and added into the ranking strategy of the list, so that the flexibility of the ranking strategy is improved, and the flexibility and convenience of the electric marketing system in the processing process of the list are correspondingly improved.

In the embodiments of the present disclosure, the ranking policy of the list may include, but is not limited to, one of the following:

the first ordering strategy is used for indicating that all lists in outbound tasks are randomly ordered;

the second ordering strategy is used for indicating to randomly order the activities and respectively prioritize the lists included in the activities;

the third sorting strategy is used for indicating that the active lists are distributed to a plurality of skill groups according to proportion, and the lists corresponding to each skill group are sorted in priority;

the fourth ranking policy is used to instruct to prioritize the activities and to prioritize the list comprised by each activity separately.

In the presently disclosed embodiments, the ranking strategy described above is explained below by way of example.

For the first ordering policy: for example, if there are 5000 lists in the outbound task, the 5000 lists are randomly ordered.

For the second ranking strategy: for example, if there are 3 activities, the 3 activities are randomly ordered first, then the list included by the respective activities is prioritized.

For the third ranking strategy: for example, if there are 2 activities (activity 1 and activity 2), 2 skill sets (skill set 1 and skill set 2), a list of one half of activity 1 is assigned to skill set 1, a list of the remaining half of activity 1 is assigned to skill set 2, a list of one half of activity 2 is assigned to skill set 1, a list of the remaining half of activity 2 is assigned to skill set 2, and then the lists corresponding to the respective skill sets are prioritized.

For the fourth ranking strategy: for example, if there are 3 activities, the 3 activities are first ranked according to the priority of the 3 activities, and then the list included in each activity is further prioritized.

The sorting strategy is various in form, and various choices are provided for list sorting.

In the embodiment of the disclosure, the sorting strategy can reserve an adjustment mechanism, modify one or more sorting strategies contained in the sorting strategy at any time, and add or delete the contained sorting strategy at any time, so that the sorting strategy can flexibly cope with various service requirements.

Based on the adjustment mechanism, the business adjustment is flexibly handled by adjusting the sorting strategy and the sorting algorithm, the change of the calling book sequence of the active list is realized, and a business user can freely select the combination of the sorting strategy and the sorting algorithm of the activity according to different requirements to explore and realize the improvement of the performance.

In practical application, the above-mentioned multiple sorting strategies can be displayed for related personnel to manually select, so as to select the most suitable sorting strategy of the current period or scene as the target sorting strategy to sort the list.

In the embodiment of the present disclosure, the ranking policy of the list may also be automatically selected, and first, the standby ranking policy to be selected needs to be added to a preset database, for example, the first database. The alternate ordering strategy may include, but is not limited to: configuring a sequencing strategy and a sequencing strategy corresponding to at least one target activity; configuring a sequencing strategy refers to a sequencing strategy designated for activities; the target activity may refer to an activity meeting certain preset conditions, for example, a higher priority activity.

In the embodiment of the disclosure, based on the standby ranking policy recorded in the first database, the following ranking policy configuration scheme may be adopted to automatically configure the ranking policy.

The data processing method further comprises the following steps:

if the first database includes a configuration ordering policy for at least one activity of the plurality of activities, determining a target ordering policy based on the configuration ordering policy for the at least one activity;

and if the first database does not comprise a plurality of active configuration ordering strategies, taking the ordering strategy with the highest priority coefficient in the standby ordering strategies recorded in the first database as a target ordering strategy.

In the embodiment of the present disclosure, the first database is used to store the active standby ranking policy, which may be at least one of the four ranking policies (the first ranking policy, the second ranking policy, the third ranking policy, and the fourth ranking policy) described above. The standby ordering policy may include an ordering policy specified for some activities, or may be an ordering policy corresponding to some target activities meeting a preset condition. When selecting a ranking strategy for outbound campaigns, one ranking strategy may be automatically selected from the standby ranking strategies. The first choice can use the designated sorting strategy (i.e. configuration sorting strategy) for a certain activity as the target sorting strategy of the outbound activity, and if a plurality of configuration sorting strategies exist, the configuration sorting strategy corresponding to the activity with the highest priority coefficient can be selected; in addition, if no sequencing strategy is configured in the alternative sequencing strategies, a sequencing strategy corresponding to the activity with the highest priority coefficient can be selected from the multiple alternative sequencing strategies and used as the target sequencing strategy of the outbound activity.

By the scheme, the system can automatically select the proper sorting strategy without relying on manpower, and the alternative sorting strategy comprises the designated configuration sorting strategy and the sorting strategy corresponding to the selected target activity, so that the alternative sorting strategy is ensured to be the sorting strategy which is optimized according to experience, and the reasonable sorting of the list is facilitated.

In the embodiment of the present disclosure, the foregoing preset conditions may include, but are not limited to, the priority coefficient being higher than a set priority threshold; the data processing method further comprises the following steps:

and searching an activity record corresponding to the target activity from a second database based on the identifiers of the activities, wherein the second database records at least one activity record of the activities, and the activity record comprises the identifiers of the activities, the priority coefficient and the corresponding ordering strategy.

And adding the sorting strategy included in the activity record corresponding to the target activity into the standby sorting strategy in the first database.

The priorities of different activities can be preset, the priority of each activity can be preset by manual work and stored in the second database, certain activities can be selected from the second database as target activities, and the ranking strategy corresponding to the target activities is added into the first database as an alternative ranking strategy.

The target activity may be the activity with the highest priority coefficient.

The high-priority activity is an important activity, the sorting strategy corresponding to the important activity is a sorting strategy path which is optimally selected and is most matched with the activity, and the sorting strategy corresponding to the high-priority activity is used as an alternative sorting strategy, so that when the high-priority activity is sorted, the target sorting strategy automatically selected from the alternative sorting strategy can be used as the sorting strategy which is optimally matched with the high-priority activity, and the optimal sorting requirement of the important activity can be preferentially met.

The second database may be a task dynamic priority seed library for holding activity priority records.

Based on the second database, the same management of the activity priority is realized, and the query of the activity priority is facilitated.

The storage field information of the second database may: activity id (identity, which may be name), sorting strategy, sorting algorithm, priority coefficient, list level, dynamic priority seed;

wherein, activity id: id of the same type of list;

ordering strategy: a ranking strategy for activity use;

priority coefficient: priority coefficients calculated according to the list distribution process data and the marketing result data;

List magnitude: the order of the list of the active seed records;

dynamic priority seed: and a random number seed, each list is allocated to generate a new seed value, so that the random value of the task dimension is more random.

When a list is allocated to the task allocation, inquiring records in a second database according to the activity id corresponding to the list, the task allocation ordering strategy and the ordering algorithm, and if the records are not inquired, adding a record and inserting the record into the second database; if the existing record is inquired, the list level +1 is carried out on the record, the random value of the dynamic priority seed is updated, and then the record is updated.

And (3) marketing a list by the agent, and inquiring records in a second database according to the activity id corresponding to the list, the task allocation ordering strategy and the ordering algorithm when the marketing result is stored. Updating the priority coefficient of the corresponding activity of the list through the marketing result: the method comprises the steps of firstly, solving the variance of the task conversion rate (task total conversion list amount/task total list amount) to which a name list belongs and the activity conversion rate (activity total conversion list amount/activity total list amount) to which a list belongs, secondly, taking out the priority coefficient of the activity corresponding to the list in a record, and calculating a correlation coefficient (a statistical index for reflecting the correlation degree between variables when the correlation coefficient is calculated according to the existing calculation method) with the variance result calculated in the first step to serve as a new priority coefficient.

In the embodiment of the disclosure, the data of the list distribution process and the data of the list marketing result can be used as basic data for calculating the performance trend after processing. After the conversion rate of the activities and the lists is processed, the conversion rate can be updated to a dynamic priority seed library table, data support is provided for dynamic adjustment priority of the subsequent allocation tasks, and effective gain is generated for marketing conversion rate.

In an embodiment of the present disclosure, the data processing method further includes:

searching a target activity configuration record from activity configuration records of a third database based on the identifiers of the plurality of activities, wherein the third database records at least one activity configuration record, the activity configuration record comprises the identifiers of the activities and a configuration ordering strategy corresponding to the activities, and the target activity configuration record comprises the activity configuration record of at least one activity in the plurality of activities;

and adding the configuration ordering strategy included in the target active configuration record into the standby ordering strategy in the first database.

The specified ordering policies for the activities may be stored in a third database, which may be an activity ordering policy configuration table, for recording activities with specified ordering policies and their corresponding specified ordering policies (i.e., configuring ordering policies).

Based on the third database, the method and the system realize that the appointed ordering strategy can be recorded in time when related personnel have a wish to appointed ordering strategy for a certain activity, and expand the sources of the standby ordering strategy.

The target ordering policy may be determined based on priorities of the plurality of activities.

For example, if the first mapping relationship between the activity priority and the aforementioned four sorting strategies is set in advance, it includes: the activities of priorities 0-200 correspond to a first ranking policy, the activities of priorities 201-300 correspond to a second ranking policy, the activities of priorities 301-600 correspond to a third ranking policy, and the activities of priorities 601-1000 correspond to a fourth ranking policy, then determining a target ranking policy based on the priorities of the plurality of activities may include: determining a target priority based on the priorities of the plurality of activities (for example, the largest priority in the priorities corresponding to the plurality of activities may be taken as the target priority, the priority obtained by weighting and summing the priorities of the plurality of activities may be taken as the target priority, the smallest priority in the priorities corresponding to the plurality of activities may be taken as the target priority, etc.), and determining the target ranking policy based on the target priority and the first mapping relationship (that is, the ranking policy corresponding to the target priority in the first mapping relationship is taken as the target ranking policy).

The target sorting strategy scheme is simple based on the priorities of the activities, and related personnel can map the activities with different priorities and the most matched sorting strategy according to experience in advance, so that the activities with different priorities can be matched to the most suitable sorting strategy, and a technical basis is provided for improving the conversion rate of users.

In an embodiment of the present disclosure, the random ranking algorithm specifically adopted in the ranking of the activities and/or lists in the ranking policy may include, but is not limited to:

bubbling ordering algorithm, hill ordering algorithm, selection ordering algorithm, insertion ordering algorithm, and random number ordering algorithm.

In practical application, the plurality of random ranking algorithms can be displayed for related personnel to manually select, so that the random ranking algorithm with the most proper current time period or scene is selected as the target ranking algorithm for ranking.

The target ordering algorithm is one of a plurality of random ordering algorithms, and the ordering efficiency corresponding to each random ordering algorithm in the plurality of random ordering algorithms is different.

The random ordering algorithm is various in form and meets different demands of list ordering.

The random number ranking algorithm may refer to a method for ranking the list according to a random number (or random generated number) provided by a preset predictive outbound task seed.

In an embodiment of the present disclosure, sorting the list according to a random number provided by a preset predictive outbound task seed may include:

acquiring a plurality of random numbers provided by a predicted outbound task seed;

correspondingly distributing a plurality of random numbers to a plurality of lists needing to be arranged randomly;

sorting the random numbers according to the numerical values to obtain a first sorting order;

and ordering the lists to be randomly arranged according to the first ordering order to realize ordering the lists according to the randomly generated numbers.

In an embodiment of the present disclosure, before ranking the lists according to the target ranking policy, the method may further include:

and acquiring a pre-selected ordering strategy, generating a corresponding random number according to the selected ordering strategy, and caching the random number.

The random number may be cached to redis [ Remote Dictionary Server, a remote dictionary service, a key-value storage system, a cross-platform non-relational database, to be directly fetched from redis when ordering is required.

The target ordering algorithm may be determined based on priorities of the plurality of activities.

For example, if the second mapping relationship between the activity priority and the aforementioned bubbling ordering algorithm, hil ordering algorithm, selection ordering algorithm, insertion ordering algorithm, and random number ordering algorithm is set in advance, it includes: the activities of priorities 0-200 correspond to the bubble ordering algorithm, the activities of priorities 201-400 correspond to the hil ordering algorithm, the activities of priorities 401-600 correspond to the selection ordering algorithm, the activities of priorities 601-800 correspond to the insert ordering algorithm, the activities of priorities 801-1000 correspond to the random number ordering algorithm, and determining the target ordering algorithm based on the priorities of the plurality of activities may include: a target priority is determined based on the priorities of the plurality of activities (e.g., a maximum priority among priorities corresponding to the plurality of activities may be taken as a target priority, a priority obtained by weighted summation of priorities of the plurality of activities may be taken as a target priority, a minimum priority among priorities corresponding to the plurality of activities may be taken as a target priority, etc.), and a target ranking algorithm is determined based on the target priority and the second mapping relationship (i.e., a ranking algorithm corresponding to the target priority in the second mapping relationship is taken as a target ranking algorithm).

The target sorting algorithm scheme based on the priorities of the activities is simple, and related personnel can map the activities with different priorities and the sorting algorithm which is most matched according to experience in advance, so that the activities with different priorities can be matched to the most suitable sorting algorithm, and a technical basis is provided for improving the conversion rate of users.

In the embodiment of the disclosure, after the target ranking policy and the target ranking algorithm selected for the above scheme are ranked, a ranking result is obtained, because for different batches of lists, the number of users with low quality is different, and the user quality in a batch of lists possibly obtained is low, that is, the marketing value is low, in this case, the user lists with low marketing value are continuously ranked no matter what the ranking is, so that the agent has a chance to predict from the user quality in the continuous list that the next list with low user quality is likely to be, so in order to avoid the problem of failure of the embodiment of the disclosure caused by low user quality (such probability is small) in the whole batch of lists, the following processes may be performed: further detecting whether each of a plurality of adjacent first lists in the sequencing result meets a preset sequencing condition or not; the first list is a list with user quality lower than a set quality threshold; the preset ordering condition is used for maintaining or improving the expected value of the agent for the subsequent call list.

In the embodiment of the present disclosure, the preset sorting condition may include, but is not limited to:

the number of the plurality of first lists is smaller than a preset number threshold; and/or the number of the groups of groups,

the plurality of first lists are arranged in order of increasing customer quality.

In an embodiment of the present disclosure, in order to avoid occurrence of a situation that the sorting result does not meet a preset sorting condition, the data processing method may further include:

detecting the user quality of a plurality of lists in advance, and inserting a preset standby list into the plurality of lists when the acquired plurality of lists correspond to the same activity and the user quality contained in the plurality of lists is lower than a set level, wherein the activity corresponding to the standby list is the same as the activity corresponding to the plurality of lists and the user quality contained in the standby list is higher than a set quality threshold; and/or adjusting the user quality of at least a portion of the plurality of lists above a set quality threshold.

In the embodiment of the disclosure, some lists with higher user quality may be reserved in advance for different activities, and inserted into a whole batch of lists with generally lower user instructions, and then the lists are sorted according to the sorting strategy, or the lists with higher user quality are inserted into the sorting result, so that the agent cannot predict whether the subsequent lists are all lists with low marketing value through the inserted lists with higher user quality.

In the embodiment of the disclosure, the user quality may be adjusted for a part of the lists or all the lists in the whole batch of lists, so that the user quality of at least a part of the lists is higher, for example, higher than the set quality threshold, so that the whole batch of lists does not only contain the lists with lower user quality, and after the lists are randomly ordered, the prediction difficulty of the agent on the subsequent lists is improved, so that the agent cannot accurately predict whether the subsequent lists are all low marketing value lists.

After the electric pin system obtains a pushed batch of lists, a dispatcher selects a plurality of lists of a plurality of activities to be distributed to a plurality of skill groups and creates a distribution task. When the allocation task is created, the system determines a target ordering strategy according to the ordering strategy selection method, and determines a target ordering algorithm according to the random ordering algorithm selection method. After the dispatcher confirms to establish the allocation task, the system stores an outbound task record, updates the outbound task when the outbound task is in the dynamic priority seed library of the task, and adds an outbound task record when the outbound task is not in the dynamic priority seed library of the task. Each outbound task record is used for recording the related information of the assigned outbound task.

In an embodiment of the present disclosure, the storage field information of the outbound task record may include, but is not limited to: task id, task name, activity priority configuration, ordering policy id, and ordering algorithm id.

Wherein, task id: a unique code of the assigned outbound task;

task name: the outbound task name is displayed by the outbound system;

activity priority configuration id: and allocating priority coefficients corresponding to the activities in the tasks.

Ordering strategy: the tasks are distributed and ordered according to which ordering strategy;

sorting algorithm: the task list is ordered according to which ordering algorithm.

For example, an outbound task record may contain: task id: "1234", task name: "20230228 high value T0YC", activity priority configuration id: "1", ordering policy: "first ranking strategy", ranking algorithm: "bubble ordering algorithm".

In the embodiment of the disclosure, the random value generated by the outbound task seed can be cached in the redis when the outbound task record is created.

After the allocation task is successfully created, the electric pin system creates a list allocation record for the list to be allocated according to the list activity attribute and the attribute of the outbound task record. At this time, the record of the dynamic priority seed library of the allocation task is inquired according to the ordering strategy and the ordering algorithm of the outbound task record and the list activity id, a call priority is randomly obtained through the dynamic priority seed, the dynamic priority seed is updated, and then the allocation record of the list is saved.

The list allocation record may be used to store task information, activity information, ordering policy information, ordering algorithm information, allocation status, call priority information, etc. corresponding to each list.

For example, the stored field information of the roster allocation record may include: task id, activity id, list id, ranking policy, ranking algorithm, call priority, allocation status, marketing results.

Wherein, task id: the list belongs to the assigned task id;

activity id: the list belongs to an activity id;

list id: a unique code of the list allocation record;

ordering strategy: a corresponding ordering strategy;

sorting algorithm: a corresponding ranking algorithm;

list allocation status: recording list allocation status (e.g. to be allocated, allocated; no outbound call, outbound call completed);

call priority: recording list calling sequence;

marketing results: and recording a list marketing result.

For example, a list allocation record may contain: task id is "1", activity id is: "123", the name of the corresponding activity of the list is "repayment high value", the ranking policy is "second ranking policy", and the ranking algorithm is: "Hill ordering algorithm", allocation status "to be allocated", list call priority: "12319383127".

One outbound task record may correspond to one or more of the shortlist allocation records.

When the system starts to distribute the list, the system can inquire the list distribution record, obtain the memory location (for example, list) of the list according to the task id and the activity id, place the list in the memory location, and update the state of the list distribution record to be distributed.

After the outbound task list is distributed, the list of the distributed task list is ordered and packed according to the target ordering strategy and the target ordering algorithm.

After the packed task allocation list is ordered by using a target ordering strategy and a target ordering algorithm, the list of the outbound system calls is an outbound sequence obtained by dynamically adjusting according to the expected sequence of the business or the actual outbound conversion rate of the list, so that the name list allocation (calling) is more reasonable, and the user conversion rate can be improved.

The system pushes the outbound task to the outbound system to start outbound.

And the outbound system calls the list according to the list sequence in the task, and then the outbound system is connected to the seat for telemarketing after the list is connected.

After the list marketing is completed, the conversion rate of the list and the activity is calculated according to the list marketing result, the corresponding distribution task dynamic priority seed library record is inquired, the priority coefficient in the record is updated, and the state in the list distribution record is updated to be marketing.

By the scheme, after the agent starts the call prediction function, the marketing value of the users in the list of the subsequent multi-way call cannot be predicted through the information in the list, so that the situation that the agent stops answering the list with lower marketing value and the lists miss marketing opportunities to waste the loopholes of the marketing opportunities is avoided, and the overall user conversion rate is correspondingly improved.

The disclosed embodiment also provides a data processing apparatus 100, as shown in fig. 4, which may include:

an obtaining module 101, configured to obtain a plurality of pushed lists;

a first generating module 102, configured to generate a plurality of activities based on the plurality of lists, where the activities are a list set, and the types of lists included in the same activity are the same;

a second generating module 103, configured to generate outbound tasks from a plurality of activities;

the ordering module 104 is configured to order the lists in the outbound tasks based on the target ordering policy and the target ordering algorithm, so as to obtain a target outbound task, where at least a part of lists included in the target outbound task are ordered irregularly.

The embodiment of the present disclosure further provides an electronic device 200, as shown in fig. 5, may include:

at least one processor 201;

at least one memory 202; the method comprises the steps of,

One or more input/output I/O interfaces 203 connected between the processor 201 and the memory 202;

wherein the memory 202 stores one or more computer programs executable by the at least one processor 201, the one or more computer programs being executable by the at least one processor 201 to enable the at least one processor 201 to perform the described data processing method.

The disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the described data processing method.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer-readable storage media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).

The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable program instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), erasable Programmable Read Only Memory (EPROM), static Random Access Memory (SRAM), flash memory or other memory technology, portable compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical disc storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable program instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and may include any information delivery media.

The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.

Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.

The computer program product described herein may be embodied in hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.

Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, 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/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

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

Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted in a generic and descriptive sense only and not for purpose of limitation. In some instances, it will be apparent to one skilled in the art that features, characteristics, and/or elements described in connection with a particular embodiment may be used alone or in combination with other embodiments unless explicitly stated otherwise. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the disclosure as set forth in the appended claims.

Claims (10)

1. A method of data processing, the method comprising:

acquiring a plurality of pushed lists;

generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same;

generating outbound tasks for the plurality of activities;

and ordering the lists in the outbound tasks based on a target ordering strategy and a target ordering algorithm to obtain target outbound tasks, wherein at least part of lists included in the target outbound tasks are irregular in ordering.

2. The method of claim 1, wherein the target ordering policy comprises one of the following ordering policies:

the first ordering strategy is used for indicating that all lists in outbound tasks are randomly ordered;

the second ordering strategy is used for indicating to randomly order the activities and respectively prioritize the lists included in the activities;

the third sorting strategy is used for indicating that the active lists are distributed to a plurality of skill groups according to proportion, and the lists corresponding to each skill group are sorted in priority;

the fourth ranking policy is used to instruct to prioritize the activities and to prioritize the list comprised by each activity separately.

3. The method of claim 1, wherein the target ranking algorithm is one of a plurality of random ranking algorithms, each of the plurality of random ranking algorithms having a different ranking efficiency.

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

if the first database includes a configuration ordering policy for at least one activity of the plurality of activities, determining the target ordering policy based on the configuration ordering policy for the at least one activity; the first database is used for recording an active standby ordering strategy; the standby ordering strategy comprises the configuration ordering strategy and an ordering strategy corresponding to at least one target activity; the configuration ordering strategy refers to an ordering strategy designated for activities; the target activity is an activity meeting preset conditions;

And if the first database does not comprise the configuration ordering strategies of the activities, taking the ordering strategy with the highest priority coefficient in the standby ordering strategies recorded in the first database as the target ordering strategy.

5. The method of claim 4, wherein the preset condition includes a priority coefficient being higher than a set priority threshold; the method further comprises the steps of:

searching an activity record corresponding to the target activity from a second database based on the identifiers of the activities, wherein the second database records at least one activity record of the activity, and the activity record comprises the identifiers of the activities, the priority coefficient and a corresponding sorting strategy;

and adding the sorting strategy included in the activity record corresponding to the target activity into the standby sorting strategy in the first database.

6. The method according to claim 4, wherein the method further comprises:

searching a target activity configuration record from activity configuration records of a third database based on the identifiers of the plurality of activities, wherein the third database records at least one activity configuration record, the activity configuration record comprises the identifiers of the activities and a configuration ordering strategy corresponding to the activities, and the target activity configuration record comprises the activity configuration record of at least one activity in the plurality of activities;

And adding the configuration ordering strategy included in the target active configuration record into the standby ordering strategy in the first database.

7. The method of claim 1, wherein the step of determining the position of the substrate comprises,

the target ordering policy is determined based on priorities of the plurality of activities; and/or the number of the groups of groups,

the target ordering algorithm is determined based on priorities of the plurality of activities.

8. A data processing apparatus, comprising:

the acquisition module is used for acquiring a plurality of pushed lists;

the first generation module is used for generating a plurality of activities based on the plurality of lists, wherein the activities are list sets, and the types of lists included in the same activity are the same;

the second generation module is used for generating outbound tasks from the activities;

the ordering module is used for ordering the lists in the outbound tasks based on a target ordering strategy and a target ordering algorithm to obtain target outbound tasks, and at least part of lists included in the target outbound tasks are irregular in ordering.

9. An electronic device, comprising:

at least one processor;

at least one memory; the method comprises the steps of,

one or more input/output I/O interfaces coupled between the processor and the memory;

Wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executable by the at least one processor to enable the at least one processor to perform the data processing method of any one of claims 1-7.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the data processing method according to any of claims 1-7.