Outbound call method and device

Abstract

The invention discloses an outbound method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: calculating an initial outbound call volume according to an initial outbound call parameter, and screening an initial outbound call user according to the initial outbound call volume, so that a robot executes an outbound call task on the initial outbound call user and transfers the outbound call task to a manual service agent when receiving a transfer instruction; real-time outbound parameters are calculated according to outbound tasks executed by the robot and the manual seat, and the real-time outbound parameters comprise robot behavior parameters and manual seat behavior parameters; and calculating an outbound call volume according to the real-time outbound call parameter, and screening an outbound call user according to the outbound call volume, so that the robot executes an outbound call task to the outbound call user and transfers the outbound call task to a manual service agent when receiving a transfer instruction. According to the embodiment, the outbound call is carried out based on the outbound call volume calculated based on dynamic and fine granularity, the robot behavior and the manual seat behavior are added into the outbound call volume calculation, and the accuracy of the outbound call volume is ensured.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an outbound calling method and device. Background Art

[0002] With the maturity of call centers and AI technology, the human-machine collaborative outbound calling method is gradually becoming popular. First, robots are used for outbound calls, and then human agents are connected according to the communication instructions of the outbound users to achieve the purpose of improving outbound call efficiency. In human-machine collaborative outbound calls, the outbound call system allocates the corresponding user list for outbound calls based on the outbound call volume. Among them, how the outbound call system allocates the appropriate number of outbound call users to the robot, that is, the outbound call volume, determines whether the capabilities of human agents and robots can be fully utilized. Existing methods for determining outbound call volume are mostly based on predictions based on call connection rates.

[0003] In the process of realizing the present invention, the inventors found that the following problems exist in the prior art: the existing method for determining the outbound call volume is too extensive, the accuracy of the outbound call volume is insufficient, and the capabilities of manual seats and robots are not maximized, which affects the outbound call efficiency and thus causes the outbound call effect to fail to meet expectations. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides an outbound calling method and device, which realizes outbound calling based on dynamic and fine-grained calculation of outbound calling volume, adds robot behavior and manual agent behavior to the calculation of outbound calling volume, performs fine-grained calculation of outbound calling volume, and ensures the accuracy of outbound calling volume, so as to fully utilize the business capabilities of robots and manual agents, improve outbound calling efficiency, and ensure outbound calling effect.

[0005] To achieve the objective, according to one aspect of an embodiment of the present invention, a method for making an outbound call is provided, comprising:

[0006] Calculate the initial outbound call volume according to the initial outbound call parameters, and screen the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call users and transfers the outbound call task to the manual seat when the robot receives the transfer instruction;

[0007] Calculate real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters;

[0008] The outbound call volume is calculated according to the real-time outbound call parameters, and outbound call users are screened according to the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to manual agents when the robot receives a transfer instruction.

[0009] Optionally, the robot behavior parameters include the robot connection rate and the transfer-to-human rate; the manual agent behavior parameters include the length of time after the manual agent call; the outbound call volume is calculated based on the real-time outbound call parameters, including: calculating the number of manual agent receptions within a specified time period based on the length of time after the manual agent call, the robot connection rate and the transfer-to-human rate; calculating the number of transferred calls based on the robot connection rate and the transfer-to-human rate; and obtaining the outbound call volume by removing the transferred calls and the number of ongoing calls from the number of manual agent receptions.

[0010] Optionally, the number of calls received by manual agents within a specified time period is calculated based on the post-call time of the manual agents, the robot connection rate and the transfer-to-manual rate, including: taking the number of manual agents whose outbound calls have ended and who have not made a new round of outbound calls as the post-call volume; calculating the number of released manual agents based on the post-call time of the manual agents and the post-call volume; calculating the number of calls received by manual agents based on the number of idle manual agents and the number of released manual agents, as well as the robot connection rate and the transfer-to-manual rate.

[0011] Optionally, after removing the transferred manual volume and the ongoing call volume from the manual seat reception volume, the method further includes: determining an interference coefficient based on the monitored waiting time of idle manual seats and the call loss rate of robot-to-manual transfer; and adding the interference coefficient to the calculation of the outbound call volume.

[0012] Optionally, calculating the initial outbound call volume according to the initial outbound call parameters includes: calculating the initial outbound call volume within a specified time period according to the number of idle manual agents and the initial outbound call connection rate in the initial outbound call parameters.

[0013] Optionally, screening initial outbound users according to the initial outbound call volume includes: according to the initial outbound call volume, reading a target list that meets the initial outbound call volume from a pre-prepared outbound call list, and using the target list as initial outbound users; wherein the outbound call list is obtained by shuffling a regularly sorted source list.

[0014] Optionally, before calculating the outbound call volume according to the real-time outbound call parameters, the method also includes: judging and confirming that the total number of manual agents exceeds the number threshold; when the total number of manual agents does not exceed the number threshold, calculating the outbound call volume according to the number of idle manual agents and the outbound call connection rate in the real-time outbound call parameters.

[0015] According to a second aspect of an embodiment of the present invention, there is provided an outbound call device, including:

[0016] A first outbound call module, configured to calculate an initial outbound call volume according to initial outbound call parameters, and screen initial outbound call users according to the initial outbound call volume, so that the robot performs an outbound call task for the initial outbound call users and transfers the outbound call task to a manual agent when the robot receives a transfer instruction;

[0017] A parameter calculation module, used to calculate real-time outbound call parameters based on the outbound call tasks being performed by the robot and the outbound call tasks being performed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters;

[0018] The second outbound call module is used to calculate the outbound call volume according to the real-time outbound call parameters, and screen outbound call users according to the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to manual seats when the robot receives a transfer instruction.

[0019] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for outbound calls, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method provided by the first aspect of the embodiment of the present invention.

[0020] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0021] An embodiment of the invention has the following advantages or beneficial effects: by calculating the initial outbound call volume according to the initial outbound call parameters, screening the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction; calculating the real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the manual agent, the real-time outbound call parameters include the robot behavior parameters and the manual agent behavior parameters; calculating the outbound call volume according to the real-time outbound call parameters, screening the outbound call users according to the outbound call volume, so that the robot performs the outbound call task for the outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction. The technical solution realizes a method for making outbound calls based on the outbound call volume calculated dynamically and finely granularly, adds the robot behavior and the manual agent behavior to the calculation of the outbound call volume, ensures the accuracy of the outbound call volume, so as to give full play to the business capabilities of the robot and the manual agent, improve the outbound call efficiency, and ensure the outbound call effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0023] Figure 1 is a schematic diagram of the main process of the outbound calling method according to an embodiment of the present invention;

[0024] Figure 2 Detailed flowchart of the outbound calling method according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of main modules of an outbound calling device according to an embodiment of the present invention;

[0026] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0027] Figure 5 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0028] It should be noted that in the technical solution of the present invention, the collection / collection, update, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken for user personal information to selectively block the use or access to personal information data to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. In addition, once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0029] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0030] The existing method for determining the outbound call volume is too extensive, the accuracy of the outbound call volume is insufficient, and the capabilities of human agents and robots are not maximized, which affects the efficiency of outbound calls, resulting in the outbound call effect failing to meet expectations and failing to meet practical applications.

[0031] In order to solve the above problems existing in the prior art, the present invention proposes an outbound calling method. While initially executing the outbound calling task, the real-time outbound calling parameters including the robot behavior parameters and the human agent behavior parameters are calculated according to the outbound calling tasks being executed by the robot and the outbound calling tasks being executed by the human agent. Then, the outbound calling volume is calculated according to the real-time outbound calling parameters, and the outbound calling users who meet the outbound calling volume are screened to execute the outbound calling tasks. The method of making outbound calls based on the outbound calling volume calculated dynamically and fine-grained is realized, and the robot behavior and the human agent behavior are added to the calculation of the outbound calling volume, thereby ensuring the accuracy of the outbound calling volume, so as to give full play to the business capabilities of the robot and the human agent, improve the outbound calling efficiency, and ensure the outbound calling effect.

[0032] Figure 1 FIG. 1 is a schematic diagram of the main flow of the outbound calling method according to an embodiment of the present invention. Figure 1 As shown, the outbound calling method of the embodiment of the present invention includes the following steps S101 to S103.

[0033] Step S101, calculating the initial outbound call volume according to the initial outbound call parameters, and screening the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call users and transfers the outbound call task to the manual seat when the robot receives the transfer instruction.

[0034] Specifically, before the outbound call system starts to execute the outbound call task, it will send out a list of outbound call users. The embodiment of the present invention adopts human-machine collaborative outbound calling, in which the robot initiates the outbound call and communicates with the user first. During the communication process, it determines whether to transfer to a manual seat according to the user's intention. For example, the robot can first guide the user to clarify the business direction corresponding to the user, and then transfer the call to the manual seat of the corresponding business direction; or it can transfer to the manual seat according to the user's transfer instruction to manual communication. This human-machine collaborative outbound calling method can use the robot to preliminarily screen out users with communication intentions, and then the manual seat will provide personalized services, which can effectively save human resources. From the above, it can be seen that whether each robot and manual seat can be fully utilized to achieve efficient outbound calls mainly depends on the determination of the number of outbound users, that is, the determination of the outbound call volume.

[0035] The present invention is based on the scenario of human-machine collaborative outbound calls, and calculates the outbound call volume in a fine-grained manner according to the actual outbound call execution situation. In the initial startup stage of the outbound call task, considering that there is no basic data for determining the main calculation parameters, the initial outbound call parameters are set according to the historical outbound call data. Of course, the initial outbound call parameters can also be calculated based on the current time characteristics and the specific business characteristics of the outbound call, combined with historical experience. The initial outbound call volume at the initial moment is calculated based on the initial outbound call parameters, and then the initial outbound call user is selected from the user list prepared in advance in the background according to the initial outbound call volume. Specifically, the initial outbound call user can be selected in sequence, or according to a preset selection rule.

[0036] The outbound call system sends the initial outbound call user to each robot so that the robot can perform the outbound call task, and if a transfer instruction is received during the outbound call process, the outbound call task is transferred to the manual seat to perform the outbound call task in collaboration. It can be understood that the outbound call system can also directly initiate an outbound call to the initial outbound call user, and then assign each outbound call user to the robot to answer. In addition, the transfer instruction of the embodiment of the present invention can be initiated by the user, or by the call system after determining the business direction of the user's interest, and the embodiment of the present invention does not make specific limitations.

[0037] According to an embodiment of the present invention, calculating the initial outbound call volume according to the initial outbound call parameters includes: calculating the initial outbound call volume within a specified time period according to the number of idle manual agents and the initial outbound call connection rate in the initial outbound call parameters.

[0038] Specifically, the determination of the initial outbound call volume in the embodiment of the present invention is mainly based on the calculation of idle manual seats, and the ratio of the number of idle manual seats to the initial outbound call connection rate is calculated, wherein the initial outbound call connection rate belongs to the initial outbound call parameter, which can be set in advance or calculated based on current characteristics and historical experience. It can be understood that when making the first outbound call, the number of idle manual seats is the number of all current manual seats.

[0039] It should be noted that the outbound call task in the embodiment of the present invention is periodic. The outbound call is started at a preset time every day, and the outbound call task is executed in rounds according to the specified time period until the set end time. For example, it is started at 9:00 am every day and ends at 17:00 pm. The outbound call time period is 20 seconds. Therefore, a round of outbound call tasks will be initiated every 20 seconds between 9:00 and 17:00, that is, the outbound call volume is calculated every 20 seconds. It can be understood that the outbound call volume calculated each time is the outbound call volume corresponding to the execution of the next round of outbound call tasks.

[0040] According to another embodiment of the present invention, screening initial outbound users according to the initial outbound call volume includes: according to the initial outbound call volume, reading a target list that meets the initial outbound call volume from a pre-prepared outbound call list, and using the target list as initial outbound users; wherein the outbound call list is obtained by shuffling a regularly sorted source list.

[0041] Specifically, the user list in the embodiment of the present invention is mainly derived from the source list extracted by other systems according to user characteristics. The users in the source list are often sorted according to the characteristic rules, and users with the same characteristics are arranged together. In order to ensure the stability of the real-time outbound call parameter values ​​calculated subsequently and avoid the fluctuation of the parameter values, the source list needs to be shuffled first. Specifically, the source list can be processed using a shuffle algorithm, or the source list can be randomly sorted multiple times. The embodiment of the present invention does not limit the specific shuffle method. Based on the outbound call list obtained after the shuffle processing, according to the calculated initial outbound call volume, the target list that meets the initial outbound call volume is read from the outbound call list, and the target list is sent to the robot as the initial outbound call user.

[0042] Step S102: Calculate real-time outbound call parameters according to the outbound call tasks being executed by the robot and the outbound call tasks being executed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters.

[0043] Specifically, the embodiment of the present invention uses the real-time data of the outbound call task being executed to calculate and update the outbound call parameters. The outbound call system monitors the outbound call-related data of the entire process of the outbound call task, and the outbound call task executed by the robot or transferred to the manual agent. The relevant data generated by the outbound call task being executed by the manual agent, and considering that this case is a human-machine collaborative outbound call, the robot's behavior in the process of human-machine collaborative outbound calls is mainly monitored, such as whether it is connected, the specific call duration, etc., and the behavior of the manual agent, such as the call duration, the state after the call, etc., based on these data, the robot behavior parameters, the manual agent behavior parameters, and the current actual outbound call volume and other real-time outbound call parameters are calculated. It should be noted that for the state of the manual agent after the call mentioned above, in the actual outbound call business, after the manual agent has completed the communication with the outbound call user, although the outbound call action is completed, it is still necessary to perform the recording work of this outbound call, so the state of the manual agent after the call is the last link of the outbound call task, which is also within the calculation scope.

[0044] Step S103: Calculate the outbound call volume according to the real-time outbound call parameters, and screen outbound call users according to the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to manual agents when the robot receives a transfer instruction.

[0045] Specifically, based on the current real-time outbound call parameters calculated above, the outbound call volume is calculated in a more refined manner from the robot granularity and the manual agent granularity, and then the outbound call users who meet the outbound call volume are screened from the outbound call list after random processing according to the method of screening users similar to the above, and then the determined outbound call users are sent to the robot, so that the robot initiates an outbound call to the outbound call user, performs the outbound call task, and transfers to the manual agent when receiving the transfer instruction. It can be understood that at this stage, the outbound call system will also update and calculate the real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the manual agent to improve the accuracy of the real-time outbound call parameters.

[0046] In addition, in order to ensure that the outbound call-related data for calculating the real-time outbound call parameters can be as close as possible to the actual situation of the users in the outbound call list, the calculation conditions for calculating the outbound call volume are usually set. Only when the calculation conditions are met, the real-time calculation stage is entered to start calculating the outbound call volume. If the conditions are not met, it is considered that the real-time outbound call parameters calculated at this time are not reasonable enough and cannot participate in the calculation of the outbound call volume. It can be seen that the outbound call task execution of the embodiment of the present invention is divided into two stages, the first stage is the initial stage, and the second stage is the real-time calculation stage. The calculation conditions of the embodiment of the present invention are comprehensively considered from the two dimensions of the cumulative execution time of the outbound call task and the accumulated actual outbound call volume, and the time threshold and the quantity threshold are set. In view of the fact that the outbound call task is executed periodically, when the execution time of the outbound call task reaches the time threshold, or the cumulative number of the initial outbound call volume reaches the quantity threshold, the outbound call volume is calculated according to the current real-time outbound call parameters. Of course, other conditions can also be added, such as manual intervention to open the calculation conditions, etc., to meet the needs of different scenarios.

[0047] Exemplarily, the duration threshold is 15 minutes, the quantity threshold is 100, and the 20 seconds mentioned above is used as the cycle of the outbound call task. Then, during the execution of the first round of outbound call tasks, the real-time outbound call parameters will be calculated, and the execution duration of this round of outbound call tasks and the initial outbound call volume of this round will be counted. If the execution duration does not reach 15 minutes, and the initial outbound call volume does not reach 100, the initial outbound call volume of the second round will still be calculated according to the initial outbound call parameters, and then the second round of outbound call tasks will be executed, and the real-time outbound call parameters will be calculated and updated synchronously until the cumulative execution time of multiple rounds of outbound call tasks reaches 15 minutes, or the cumulative number of initial outbound call volumes of multiple rounds of outbound call tasks reaches 100. At this time, it will jump to the real-time calculation stage, that is, the outbound call volume is calculated according to the real-time outbound call parameters.

[0048] According to one embodiment of the present invention, the robot behavior parameters include the robot connection rate and the transfer-to-human rate; the manual agent behavior parameters include the length of time after the manual agent call; the outbound call volume is calculated based on the real-time outbound call parameters, including: calculating the number of manual agent receptions within a specified time period based on the length of time after the manual agent call, the robot connection rate and the transfer-to-human rate; calculating the number of transferred calls based on the robot connection rate and the transfer-to-human rate; and obtaining the outbound call volume by removing the transferred calls and the number of ongoing calls from the number of manual agent receptions.

[0049] Specifically, the embodiment of the present invention mainly calculates the outbound call volume from the robot behavior parameters and the manual agent behavior parameters. For the manual agent behavior parameters, the post-call status plays an important role in accurately calculating the next round of outbound call volume. If the manual agent can quickly complete the post-call record, then it is able to access a new round of outbound call tasks. Therefore, the outbound call system will calculate the ratio of the sum of the post-call duration of all manual agents to the sum of the number of post-calls of the manual agents, and define this ratio as the post-call duration of the manual agent. For the robot behavior parameters, the robot connection rate and the transfer rate to manual are calculated mainly based on the number of outbound calls, the number of connections, and the number of transfers of the robot.

[0050] According to the above-calculated post-call time of the manual seat, the robot connection rate and the transfer rate to manual, the manual seat reception volume is calculated for the time period of the next outbound call task, and then the product of the outbound call volume connected by the robot and the transfer rate is calculated to obtain the transfer volume that needs to be transferred to the manual agent during the robot outbound call process. The number of calls in progress is obtained by calculating the difference between the current outbound call volume and the number of calls currently in progress. Finally, the number of calls received by the manual seat, the number of transfers to manual agents and the number of calls in progress are subtracted to calculate the accurate outbound call volume.

[0051] According to another embodiment of the present invention, the number of calls received by manual agents within a specified time period is calculated based on the post-call time of the manual agents, the robot connection rate and the transfer-to-manual rate, including: taking the number of manual agents whose outbound calls have ended and have not made a new round of outbound calls as the post-call volume; calculating the number of released manual agents based on the post-call time of the manual agents and the post-call volume; calculating the number of manual agents received based on the number of idle manual agents and the released manual agents, as well as the robot connection rate and the transfer-to-manual rate.

[0052] Specifically, for the calculation of the number of calls received by manual agents, the outbound call system of the embodiment of the present invention will count the status of the manual agents. When the manual agent ends the outbound call and does not make a new round of outbound calls, the status is the post-call status. It can be understood that the manual agent can indicate the end of the post-call record by clicking the end of the outbound call task, and can enter a new round of outbound calls. Then the state between the end of the call by the manual agent and the end of the outbound call task is the post-call status. The outbound call system counts the number of manual agents in the post-call state to obtain the post-call volume. Then calculate the ratio of the time period of the outbound call and the post-call duration of the manual agent, multiply the calculated post-call volume by the ratio, and calculate how many manual agents can be released from the manual agents in the post-call state to perform a new round of outbound call tasks, which is expressed by the formula: post-call volume × (time period / post-call duration of the manual agent). Finally, the number of currently idle human seats and the number of released human seats are summed up, and the impact of the robot connection rate and the transfer rate to human is taken into account to obtain the specific calculation formula for the number of human seat receptions: [number of idle human seats + number of post-calls × (time period / length of post-calls for human seats)] / (robot connection rate × transfer rate to human).

[0053] Furthermore, based on the determined number of calls received by manual seats, combined with the number of calls in progress and the number of calls transferred to manual services, the calculation formula for the outbound call volume is: Outbound call volume = [number of idle manual seats + number of calls after calls × (time period / length of time after calls for manual seats)] / (robot connection rate × transfer to manual service rate) - (outbound call volume - number of calls currently in progress) - number of robot connection rates × transfer to manual service rate.

[0054] According to another embodiment of the present invention, after deducting the transferred manual volume and the ongoing call volume from the manual seat reception volume, the method further includes: determining an interference coefficient based on the monitored waiting time of idle manual seats and the call loss rate of robot-to-manual transfer; and adding the interference coefficient to the calculation of the outbound call volume.

[0055] Specifically, in order to more accurately and flexibly adjust the outbound call volume, the embodiment of the present invention sets the idle waiting time of the manual seat and the call loss rate of the robot to the manual, and introduces the interference coefficient, so as to dynamically and flexibly adjust the outbound call volume according to the specific situation of the outbound call task to be executed. Specifically, when the waiting time of the manual seat counted in real time is higher than the set idle time and the call loss rate of the robot to the manual is lower than the set value, it means that the outbound call volume of the manual seat is not saturated, and the interference coefficient is increased to increase the concurrency. When the call loss rate is greater than the set value, it means that the load of the manual seat is large. At this time, the interference system can be reduced, and the concurrency can be reduced to reduce the loss of outbound users. Accordingly, after the interference coefficient is added to the calculation of the outbound call volume, the final calculation formula of the outbound call volume is: outbound call volume = { [manual seat idle volume + post-call volume × (time period / manual seat post-call time)] / (robot connection rate × transfer rate to manual) - (outbound call volume - the number of calls currently in progress) - robot connection volume × transfer rate to manual} × interference coefficient.

[0056] The embodiment of the present invention can effectively ensure the rationality of the outbound call volume and further improve the accuracy of the outbound call volume by dynamically adjusting the outbound call volume through the interference coefficient.

[0057] According to another embodiment of the present invention, before calculating the outbound call volume according to the real-time outbound call parameters, the method also includes: judging and confirming that the total number of manual agents exceeds the number threshold; when the total number of manual agents does not exceed the number threshold, calculating the outbound call volume according to the number of idle manual agents and the outbound call connection rate in the real-time outbound call parameters.

[0058] Specifically, in order to better adapt to more outbound call scenarios, an embodiment of the present invention also provides a simple method for calculating the outbound call volume. Before calculating the outbound call volume based on real-time outbound call parameters, it is necessary to determine whether the total number of manual seats exceeds the number threshold. If the current total number of manual seats is very small, for example, the number threshold is 6, which is less than 6 people, then there is no need to calculate the outbound call volume in a fine-grained manner. The ratio between the number of idle manual seats and the outbound call connection rate in the real-time outbound call parameters is directly calculated to obtain the outbound call volume.

[0059] Figure 2 The detailed flow chart of the outbound calling method of the embodiment of the present invention is as follows. First, the regularly sorted source list of the same user characteristics is processed in a random order. Specifically, the source list can be processed by a random order algorithm, or the source list can be randomly sorted according to a set number of times to achieve the purpose of random order, and the initial outbound calling parameters of the human-machine collaborative outbound calling are set according to the historical outbound calling data.

[0060] When the outbound call system receives an outbound call task start instruction, or when the outbound call system detects that the current system time reaches the time point for starting the outbound call task, the outbound call task is started and enters the initial outbound call stage.

[0061] (1) The first round of outbound calls in the initial outbound call phase calculates the initial outbound call volume based on the initial outbound call parameters, selects the initial outbound call users from the outbound call list after random processing based on the initial outbound call volume, and sends the initial outbound call users to the robot. The robot executes the outbound call task according to the received initial outbound call users, and transfers the outbound call task to the manual seat when the robot receives the transfer instruction from the initial outbound call user. At the same time, the outbound call system calculates the real-time outbound call parameters and determines whether one of the execution time of the current outbound call task and the initial outbound call volume has reached the time threshold and quantity threshold set in the calculation conditions.

[0062] (2) If neither of the above conditions is met, the initial outbound call parameters are used to calculate the initial outbound call volume of the second round of outbound calls, and then the initial outbound call users of the second round of outbound calls are selected from the outbound call list after random processing, excluding the initial outbound call users who have already made outbound calls, according to the initial outbound call volume. Then, outbound call tasks are performed on these initial outbound call users, and the real-time outbound call parameters are calculated and updated at the same time to determine whether the cumulative execution time of the current second round of outbound call tasks and the cumulative execution time of the first round of outbound call tasks, as well as the cumulative number of the second round of initial outbound call volumes and the first round of initial outbound call volumes have reached the time threshold and number threshold set in the calculation conditions.

[0063] If none of the calculation conditions are met, the third round of outbound calls will be continued according to the above method. If at least one of the calculation conditions is met, the initial outbound call stage will enter the real-time calculation stage.

[0064] (1) In the first round of outbound calls in the real-time calculation stage, we first determine whether the total number of human agents exceeds the threshold. If not, we use a simple calculation method to calculate the outbound call volume based on the number of idle human agents and the outbound call connection rate in the real-time outbound call parameters. If it exceeds the threshold, we calculate the outbound call volume in a fine-grained manner based on the robot connection rate, transfer rate to human agents, and the length of time after the human agent call is finished, as well as the interference coefficient in the calculated real-time outbound call parameters. Finally, based on the outbound call volume, we select outbound call users from the outbound call list after random processing, excluding the initial outbound call users who have been called out, and send the outbound call users to the robot so that the robot can perform the outbound call task. When the robot receives the transfer instruction, it transfers the outbound call task to the human agent. At the same time, the outbound call system will also calculate and update the real-time outbound call parameters and start the second round of outbound calls in the real-time calculation stage.

[0065] (2) The second round of outbound calls in the real-time calculation stage is similar to the first round of outbound calls in this stage. It also first determines whether the total number of current manual seats exceeds the number threshold. If not, a simple calculation method is used to calculate the outbound call volume based on the number of idle manual seats and the outbound call connection rate in the real-time outbound call parameters. If it exceeds the number threshold, the outbound call volume is calculated in a fine-grained manner based on the robot connection rate, transfer rate to manual, and the length of time after the manual seat call, as well as the interference coefficient in the calculated real-time outbound call parameters. Finally, based on the outbound call volume, the outbound call users are selected from the outbound call list after the out-of-order processing except for the users who have been called out before, and the outbound call users are sent to the robot so that the robot can perform the outbound call task. When the robot receives the transfer instruction, the outbound call task is transferred to the manual seat. At the same time, the outbound call system will also calculate and update the real-time outbound call parameters and start the third round of outbound calls in the real-time calculation stage.

[0066] According to the above method, it is periodically determined whether the total number of manual seats exceeds the number threshold, and the outbound call volume is calculated according to the real-time outbound call parameters until a signal indicating the termination of the outbound call task is received, or the system time of the outbound call system reaches the preset outbound call termination time point, the outbound call system ends the outbound call work.

[0067] In the human-machine collaborative outbound call scenario, the embodiment of the present invention calculates the outbound call volume accurately and finely through the number of human agent receptions, the number of human transfers and the number of calls in progress based on the robot connection rate, the transfer rate to human and the length of time after the human agent call in the real-time outbound call parameters calculated during the execution of the outbound call task, and supports dynamic adjustment of the outbound call volume according to the waiting time of idle human agents and the call loss rate of robot-to-human transfers, so as to obtain an outbound call volume that is more in line with the current execution status of the outbound call task, thereby ensuring the rationality of the calculated outbound call volume, thereby improving the outbound call efficiency and ensuring the outbound call effect.

[0068] Figure 3 1 is a schematic diagram of the main modules of the device for outbound calling according to an embodiment of the present invention. Figure 3 As shown, the outbound calling device 300 mainly includes a first outbound calling module 301 , a parameter calculation module 302 and a second outbound calling module 303 .

[0069] The first outbound calling module 301 is used to calculate the initial outbound calling volume according to the initial outbound calling parameters, and screen the initial outbound calling users according to the initial outbound calling volume, so that the robot performs the outbound calling task for the initial outbound calling users and transfers the outbound calling task to the manual seat when the robot receives the transfer instruction;

[0070] A parameter calculation module 302 is used to calculate real-time outbound call parameters based on the outbound call tasks being performed by the robot and the outbound call tasks being performed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters;

[0071] The second outbound calling module 303 is used to calculate the outbound calling volume according to the real-time outbound calling parameters, and screen outbound calling users according to the outbound calling volume, so that the robot performs outbound calling tasks for the outbound calling users and transfers the outbound calling tasks to manual agents when the robot receives a transfer instruction.

[0072] According to one embodiment of the present invention, the robot behavior parameters include the robot connection rate and the transfer-to-human rate; the human agent behavior parameters include the length of time after the human agent call; the second outbound call module 303 is further used to: calculate the number of human agent receptions within a specified time period based on the length of time after the human agent call, the robot connection rate and the transfer-to-human rate; calculate the number of transferred human calls based on the robot connection rate and the transfer-to-human rate; and obtain the outbound call volume by removing the transferred human call volume and the number of calls in progress from the number of human agent receptions.

[0073] According to another embodiment of the present invention, the second outbound call module 303 is further used to: take the number of manual agents whose outbound calls have ended and have not made a new round of outbound calls as the post-call volume; calculate the number of released manual agents based on the post-call duration of the manual agents and the post-call volume; calculate the number of manual agents received based on the number of idle manual agents and the number of released manual agents, as well as the robot connection rate and the transfer to manual rate.

[0074] According to another embodiment of the present invention, the outbound calling device 300 further includes a coefficient adjustment module (not shown in the figure), which is used to: after deducting the transferred manual volume and the ongoing call volume from the manual seat reception volume, determine the interference coefficient according to the monitored waiting time of the idle manual seats and the call loss rate of the robot-to-manual transfer; and add the interference coefficient to the calculation of the outbound call volume.

[0075] According to another embodiment of the present invention, the first outbound call module 301 is further used to calculate the initial outbound call volume within a specified time period according to the number of idle manual agents and the initial outbound call connection rate in the initial outbound call parameters.

[0076] According to another embodiment of the present invention, the first outbound call module 301 is further used for: according to the initial outbound call volume, reading a target list that meets the initial outbound call volume from a pre-prepared outbound call list, and using the target list as the initial outbound call users; wherein the outbound call list is obtained by shuffling a regularly sorted source list.

[0077] According to another embodiment of the present invention, the outbound calling device 300 further includes a number verification module (not shown in the figure), which is used to: before calculating the outbound calling volume according to the real-time outbound calling parameters, determine and confirm that the total number of manual agents exceeds the number threshold; when the total number of manual agents does not exceed the number threshold, calculate the outbound calling volume according to the number of idle manual agents and the outbound calling connection rate in the real-time outbound calling parameters.

[0078] Figure 4 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0079] like Figure 4 As shown, system architecture 400 may include terminal devices 401, 402, 403, network 404 and server 405. Network 404 is used to provide a medium for communication links between terminal devices 401, 402, 403 and server 405. Network 404 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0080] Users can use terminal devices 401, 402, 403 to interact with server 405 through network 404 to receive or send messages, etc. Terminal devices 401, 402, 403 can be installed with various communication client applications, such as outbound call applications, etc. (only for example).

[0081] The terminal devices 401 , 402 , and 403 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0082] The server 405 may be a server that provides various services, such as a background management server that supports outbound calls made by users using the terminal devices 401, 402, and 403 (for example only). The background management server may calculate the initial outbound call volume based on the initial outbound call parameters, and screen the initial outbound call users based on the initial outbound call volume, so that the robot performs outbound call tasks for the initial outbound call users and transfers the outbound call tasks to the manual seat when the robot receives a transfer instruction; calculate the real-time outbound call parameters based on the outbound call tasks being performed by the robot and the outbound call tasks being performed by the manual seat, and the real-time outbound call parameters include robot behavior parameters and manual seat behavior parameters; calculate the outbound call volume based on the real-time outbound call parameters, screen the outbound call users based on the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to the manual seat when the robot receives a transfer instruction, and feeds back the processing results to the terminal device.

[0083] It should be noted that the outbound calling method provided in the embodiment of the present invention is generally executed by the server 405 , and accordingly, the outbound calling device is generally arranged in the server 405 .

[0084] It should be understood that Figure 4 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0085] Reference below Figure 5 , Figure 5 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 5 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0086] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0087] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0088] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0089] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0090] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, it may be described as follows: a processor includes: a first outbound call module, a parameter calculation module and a second outbound call module.

[0092] Among them, the names of these modules do not constitute a limitation of the modules themselves in certain cases. For example, the first outbound call module can also be described as "a module used to calculate the initial outbound call volume according to the initial outbound call parameters, and to screen the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call users and transfers the outbound call task to the manual agent when the robot receives the transfer instruction."

[0093] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or may exist independently without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: calculating the initial outbound call volume according to the initial outbound call parameters, screening the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction; calculating the real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the manual agent, the real-time outbound call parameters including the robot behavior parameters and the manual agent behavior parameters; calculating the outbound call volume according to the real-time outbound call parameters, screening the outbound call users according to the outbound call volume, so that the robot performs the outbound call task for the outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction.

[0094] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by calculating the initial outbound call volume according to the initial outbound call parameters, and screening the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction; calculating the real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the manual agent, and the real-time outbound call parameters include the robot behavior parameters and the manual agent behavior parameters; calculating the outbound call volume according to the real-time outbound call parameters, and screening the outbound call users according to the outbound call volume, so that the robot performs the outbound call task for the outbound call user and transfers the outbound call task to the manual agent when the robot receives the transfer instruction. The technical solution realizes a method for making outbound calls based on the outbound call volume calculated dynamically and finely granularly, adds the robot behavior and the manual agent behavior to the calculation of the outbound call volume, and ensures the accuracy of the outbound call volume, so as to give full play to the business capabilities of the robot and the manual agent, improve the outbound call efficiency, and ensure the outbound call effect.

[0095] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. An outbound calling method, characterized in that: include: Calculate the initial outbound call volume according to the initial outbound call parameters, and screen the initial outbound call users according to the initial outbound call volume, so that the robot performs the outbound call task for the initial outbound call users and transfers the outbound call task to the manual seat when the robot receives the transfer instruction; Calculate real-time outbound call parameters according to the outbound call tasks being performed by the robot and the outbound call tasks being performed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters; The outbound call volume is calculated according to the real-time outbound call parameters, and outbound call users are screened according to the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to manual agents when the robot receives a transfer instruction.

2. The method according to claim 1, characterized in that The robot behavior parameters include the robot connection rate and the transfer rate to human; the human agent behavior parameters include the length of time after the human agent call; Calculating the outbound call volume according to the real-time outbound call parameter includes: Calculate the number of receptions by the human agent within a specified time period according to the post-call duration of the human agent, the robot connection rate and the transfer rate to human agents; Calculating the amount of labor transfer according to the robot connection rate and the labor transfer rate; The outbound call volume is obtained by subtracting the transfer volume and the ongoing call volume from the manual seat reception volume.

3. The method according to claim 2, characterized in that The number of calls received by the human agent within a specified time period is calculated according to the post-call duration of the human agent, the robot connection rate, and the transfer rate to human agents, including: The number of agents who have completed outbound calls but have not made a new round of outbound calls is taken as the post-call volume; Calculate the number of released artificial seats according to the post-call duration of the artificial seat and the post-call volume; The number of manual seats received is calculated according to the number of idle manual seats and the number of released manual seats, as well as the robot connection rate and the transfer rate to manual seats.

4. The method according to claim 2, characterized in that: After removing the transfer volume and the ongoing call volume from the manual agent reception volume, the method further includes: An interference coefficient is determined according to the monitored waiting time of idle human seats and the call loss rate of robot-to-human transfer; and the interference coefficient is added to the calculation of the outbound call volume.

5. The method according to claim 1, characterized in that Calculate the initial outbound call volume based on the initial outbound call parameters, including: The initial outbound call volume within a specified time period is calculated according to the number of idle manual seats and the initial outbound call connection rate in the initial outbound call parameters.

6. The method according to claim 1, characterized in that Screening initial outbound call users according to the initial outbound call volume includes: According to the initial outbound call volume, a target list that meets the initial outbound call volume is read from a pre-prepared outbound call list, and the target list is used as the initial outbound call users; wherein the outbound call list is obtained by shuffling a regularly sorted source list.

7. The method according to claim 1, characterized in that Before calculating the outbound call volume according to the real-time outbound call parameters, the method further includes: Determine and confirm that the total number of manual seats exceeds the threshold; When the total number of manual agents does not exceed the number threshold, the outbound call volume is calculated according to the number of idle manual agents and the outbound call connection rate in the real-time outbound call parameter.

8. An outbound calling device, characterized in that: include: A first outbound call module, configured to calculate an initial outbound call volume according to initial outbound call parameters, and screen initial outbound call users according to the initial outbound call volume, so that the robot performs an outbound call task for the initial outbound call users and transfers the outbound call task to a manual agent when the robot receives a transfer instruction; A parameter calculation module, used to calculate real-time outbound call parameters based on the outbound call tasks being performed by the robot and the outbound call tasks being performed by the human agent, wherein the real-time outbound call parameters include robot behavior parameters and human agent behavior parameters; The second outbound call module is used to calculate the outbound call volume according to the real-time outbound call parameters, and screen outbound call users according to the outbound call volume, so that the robot performs outbound call tasks for the outbound call users and transfers the outbound call tasks to manual seats when the robot receives a transfer instruction.

9. A mobile electronic device terminal, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images