Predictive call-out method and device, equipment and storage medium

Abstract

The invention discloses a predictive outbound method, device and equipment and a storage medium, and relates to the technical field of telephone outbound, and the method comprises the steps: determining an optimal connection time interval of a user according to historical outbound information of the user; dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; detecting whether the time interval between the current moment and the optimal switch-on time subinterval is lower than a preset time interval threshold value or not in real time; if yes, generating a user information outbound file corresponding to the optimal connection time subinterval; and executing an outbound task based on the user information outbound file through the predictive outbound system. By applying the technical scheme, the technical problems of low calling efficiency and low call completing rate caused by the fact that a predictive call-out system in the prior art usually calls the users in the call list in batches in the same time period are solved.

Description

Technical Field

[0001] The present application relates to the field of telephone outbound calling technology, and in particular to a predictive outbound calling method, device, equipment and storage medium. Background Art

[0002] In traditional predictive outbound calling systems, the dialing of user lists is usually carried out in a one-time large-scale sending form. Specifically, enterprises usually collect a large number of users, organize these user data into a file, and send the entire list to the outbound calling system before the call starts. Then the outbound calling system will start to dial users in batches according to the set call loss rate and the seat group used. In this process, the outbound calling system will adjust the dialing frequency and call intensity in real time to maximize the utilization efficiency of the seat group and reduce idle time. However, since the order of all users in the call list and the rhythm set by the outbound calling system are fixed when the outbound calling system makes batch calls, all users are uniformly regarded as dial objects in the same time period, and different users have different connection habits and connection time periods, resulting in low call efficiency and low connection rate. Summary of the invention

[0003] The main purpose of the present application is to provide a predictive outbound calling method, apparatus, device and storage medium, aiming to solve the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to users in the call list in the same time period, resulting in low calling efficiency and low connection rate.

[0004] To achieve the above objectives, the present application proposes a predictive outbound calling method, the method comprising: Determine the best connection time interval for the user according to the user's historical outbound call information; Dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; Real-time detection of whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold; If yes, then generating a user information outbound call file corresponding to the optimal connection time subinterval; An outbound calling task is executed based on the user information outbound calling file by a predictive outbound calling system.

[0005] In one embodiment, the step of determining the optimal connection time interval of the user according to the historical outbound call information of the user includes: Determine the user's historical connection times, user preference information and calling time period according to the user's historical outbound call information; Based on the historical connection times, the user preference information and the call time period, determining the target connection success rate of the user corresponding to different time intervals through a preset time prediction model; An optimal connection time interval for the user is determined according to the target connection success rate.

[0006] In one embodiment, before the step of dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals, the method further includes: Determine the number of batch groups based on the total number of users and the number of users in the target batch; The step of dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals includes: The users are dynamically divided based on the batch grouping quantity and the optimal connection time interval to obtain a plurality of optimal connection time subintervals.

[0007] In one embodiment, the step of executing the outbound calling task based on the user information outbound calling file by the predictive outbound calling system includes: Determine the task execution priority corresponding to the target user in the optimal connection time subinterval based on the user information outbound call file; An outbound calling task is executed for the target user based on the task execution priority by a predictive outbound calling system.

[0008] In one embodiment, after the step of executing the outbound calling task for the target user based on the task execution priority by the predictive outbound calling system, the method further includes: Determine a call failure user from the target users according to the outbound call task execution result of the target users; Adding the call failure users to a waiting outbound call list, and determining the re-call time corresponding to all the call failure users in the waiting outbound call list; Grouping the call failure users based on the re-call time to determine a group to be re-called; The group to be recalled is called again through a predictive outbound calling system.

[0009] In one embodiment, after the step of executing the outbound calling task for the target user based on the task execution priority by the predictive outbound calling system, the method further includes: Determine the connection success rate corresponding to the optimal connection time subinterval according to the outbound call task execution result of the target user; Determine the actual connection status of the target user according to the execution result of the outbound call task; Constructing a target optimization function based on the actual connection situation and the connection success rate; Optimizing the preset time prediction model by using the target optimization function; Wherein, the objective optimization function is:

[0010] In the formula, Optimize the function for the objective, is the actual connection situation, is the connection success rate, is the optimal on-time subinterval, is the model parameter.

[0011] In one embodiment, before the step of determining the optimal connection time interval of the user according to the historical outbound call information of the user, the method further includes: Determine the user's outbound calling status based on historical outbound calling task execution results; When the user's outbound call status is a successfully connected state, determining the successful call time period and historical call duration corresponding to the current successfully connected task; Determine the outbound call connection rate and the outbound call loss rate based on the user's outbound call status and the historical call duration; The initial time prediction model is trained based on the successful call time period, the outbound call connection rate and the outbound call loss rate to obtain a preset time prediction model.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a predictive outbound calling device, the device comprising: A time prediction module, used to determine the optimal connection time interval of the user according to the user's historical outbound call information; A dynamic batch division module, used for dynamically dividing the users based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; A time interval detection module, used for detecting in real time whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold; An outbound call file generation module, configured to generate a user information outbound call file corresponding to the optimal connection time subinterval; An outbound call task execution module is used to execute the outbound call task based on the user information outbound call file through a predictive outbound call system.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a predictive outbound calling device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the predictive outbound calling method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the predictive outbound calling method described above are implemented.

[0015] The present application provides a predictive outbound calling method, which discloses determining the best connection time interval of a user according to the historical outbound calling information of the user; dynamically dividing the user based on the best connection time interval to obtain a plurality of best connection time subintervals; detecting in real time whether the time interval between the current moment and the best connection time subinterval is lower than a preset time interval threshold; if so, generating a user information outbound calling file corresponding to the best connection time subinterval; executing an outbound calling task based on the user information outbound calling file by a predictive outbound calling system; compared with the prior art, when the outbound calling system dials users in batches according to a user list, the calling efficiency is low and the connection rate is low because the calling sequence and rhythm are fixed, and the connection habits and connection time periods of different users are different. The present invention can dynamically divide the best connection time interval of the user to obtain a plurality of best connection time subintervals, and when the current moment is close to the best connection time subinterval, the user is called based on the user outbound calling file, thereby solving the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to users in the call list in the same time period, resulting in low calling efficiency and low connection rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A flowchart of the first embodiment of the predictive outbound calling method of the present application is provided; Figure 2 A flow chart for generating a time prediction model in the predictive outbound calling method of this application; Figure 3 A flowchart of the second embodiment of the predictive outbound calling method of the present application is provided; Figure 4 This is a processing flow chart of the batch dialing task in the predictive outbound calling method of this application; Figure 5 A flowchart of the third embodiment of the predictive outbound calling method of the present application is provided; Figure 6 A flowchart of the redial strategy in the predictive outbound calling method of the present application; Figure 7 This is a flowchart for optimizing the outbound calling strategy in the predictive outbound calling method of this application; Figure 8 This is the overall flow chart of the outbound calling system in the predictive outbound calling method of this application; Fig. 9 This is a schematic diagram of the module structure of the predictive outbound calling device according to an embodiment of the present application; Fig.10 Schematic diagram of the device structure of the hardware operating environment involved in the predictive outbound calling method in the embodiment of the present application.

[0019] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0021] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0022] The main solution of the embodiment of the present application is: determine the best connection time interval for the user based on the user's historical outbound call information; dynamically divide the user based on the best connection time interval to obtain a number of best connection time sub-intervals; detect in real time whether the time interval between the current moment and the best connection time sub-interval is lower than a preset time interval threshold; if so, generate a user information outbound call file corresponding to the best connection time sub-interval; and execute the outbound call task based on the user information outbound call file through a predictive outbound call system.

[0023] In the prior art, when an outbound calling system makes batch calls to users based on a user list, the order of all users in the call list and the rhythm set by the outbound calling system are fixed. At this time, all users are uniformly regarded as dial objects in the same time period, but different users have different connection habits and connection time periods, resulting in low call efficiency and low connection rate.

[0024] The present application provides a solution that can dynamically divide the user's optimal connection time interval, obtain several optimal connection time sub-intervals, and make an outbound call to the user based on the user's outbound call file when the current time is close to the optimal connection time sub-interval, thereby solving the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to the users in the call list in the same time period, resulting in low call efficiency and low connection rate.

[0025] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a predictive outbound calling system, etc. The following takes the predictive outbound calling system as an example (hereinafter referred to as the device) to illustrate this embodiment and the following embodiments.

[0026] Based on this, the embodiment of the present application provides a predictive outbound calling method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the predictive outbound calling method of the present application.

[0027] In this embodiment, the predictive outbound calling method includes steps S10 to S50: Step S10: determining the best connection time interval for the user according to the user's historical outbound call information.

[0028] It should be understood that the above historical outbound call information may be the outbound call information of the user in the past period of time, such as the outbound call connection time, call times, connection success rate, etc. of the user in the past period of time, and this embodiment does not impose any limitation on this.

[0029] It should be noted that the above-mentioned optimal time interval for connecting a call may be the optimal time interval for a user to connect a call, that is, the time interval during which the probability of the user connecting a call is the highest when an outbound call is made to the user. In this embodiment, the user's historical outbound call information may be input into a time prediction model, and the time prediction model may calculate and output the optimal time interval for the user to connect a call based on the user's historical outbound call information.

[0030] Step S20: dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time sub-intervals.

[0031] It is understandable that the above-mentioned optimal connection time sub-interval can be a sub-interval within the optimal connection time interval. In this embodiment, the system can dynamically divide users according to the optimal connection time interval, so that users can be divided into multiple different time intervals. At this time, several optimal connection time sub-intervals can be obtained, among which the users divided into the optimal connection time sub-interval have the highest connection rate in the time sub-interval. Compared with the traditional outbound call system's method of dialing users in batches at one time, this solution can dynamically divide time intervals and make outbound calls during periods with high user connection rates, thereby greatly improving the success rate of outbound calls.

[0032] Step S30: Detect in real time whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold.

[0033] It should be noted that the above-mentioned preset time interval threshold may be a minimum time value used to indicate that the current moment is close to the optimal connection time subinterval.

[0034] Step S40: If yes, then generate a user information outbound call file corresponding to the optimal connection time sub-interval.

[0035] It should be noted that the user information outbound call file may be a file consisting of outbound call information of users within the optimal call connection time sub-interval. In this embodiment, the user information outbound call file may include information such as user contact information and optimal outbound call time.

[0036] Step S50: executing an outbound calling task based on the user information outbound calling file through the predictive outbound calling system.

[0037] It should be understood that the above-mentioned predictive outbound calling system may be a system for performing outbound calling operations on users.

[0038] In actual applications, the system can dynamically divide users according to the predicted optimal connection time interval of the users, divide the users into multiple different optimal connection time sub-intervals, and automatically collect the information of users in the optimal connection time sub-interval when the current time is close to the optimal connection time sub-interval, and then generate a user information outbound call file based on the user information. After the user information outbound call file is generated, the system can send the user information outbound call file to the predictive outbound call system, so that the predictive outbound call system can perform outbound call operations on users according to the user information outbound call file to ensure that the outbound call task is performed in a time period with a high user connection rate, thereby improving the success rate of outbound calls. In addition, business personnel can set multiple time prediction strategies, and the system can dynamically adjust the outbound call time of each batch of customers according to these strategies. For example, when the system predicts that the outbound call success rate in a certain time period is high, the system can give priority to the outbound call tasks in this time period. This embodiment allocates outbound call tasks in batches according to time intervals, so that the system can more reasonably utilize outbound call resources, reduce invalid calls, and improve the overall operating efficiency of the system.

[0039] Furthermore, before step S10, the method also includes: determining the user's outbound call status based on the historical outbound call task execution results; when the user's outbound call status is a successful connection state, determining the successful call time period and historical call duration corresponding to the current successful connection task; determining the outbound call connection rate and the outbound call loss rate based on the user's outbound call status and the historical call duration; training the initial time prediction model based on the successful call time period, the outbound call connection rate and the outbound call loss rate to obtain a preset time prediction model.

[0040] It can be understood that the above-mentioned historical outbound call task execution results may be the results obtained by executing outbound call tasks on users in the past period of time; the above-mentioned user outbound call status may be the user's connection status when an outbound call is made to the user. In this embodiment, the user's outbound call status may include but is not limited to a successful connection status, a failed connection status, etc.

[0041] It should be understood that the current successfully connected task can be an outbound call task that the user successfully connected. In this embodiment, the task in which the user's outbound call status is successfully connected can be determined as the current successfully connected task. The successful call time period can be the time period in which the user successfully connected the current successfully connected task; accordingly, the historical call duration can be the call duration after the user connected the current successfully connected task.

[0042] It should be noted that the above-mentioned outbound call completion rate may be the probability of a user completing an outbound call task during the system's automatic outbound call process.

[0043] It should be noted that the outbound call loss rate can be the probability that the call fails to be successfully assigned to the terminal seat due to various reasons during the automatic outbound call process of the system. In practical applications, the outbound call loss rate can reflect the loss of the outbound call system during the call process.

[0044] In this embodiment, the system can divide the number of outbound call tasks in which the user's outbound call status is the outbound call success status in the past period by the total number of outbound call tasks in the time period to determine the outbound call connection rate in the time period. At the same time, the number of outbound call tasks in which the user's outbound call status is the outbound call failure status in the past period can be divided by the total number of outbound call tasks in the time period to determine the outbound call loss rate in the time period. Among them, since the user may have a false touch when connecting the call, this embodiment can determine whether the user's current call connection is a false touch based on the historical call duration. If it is, the connection status of this outbound call task is still determined as a connection failure state, and the number of outbound call tasks in which the user's outbound call status is the outbound call success status and the number of outbound call tasks in which the user's outbound call status is the outbound call failure status in the time period are updated, and then the outbound call connection rate and the outbound call loss rate are calculated based on the updated number of outbound call tasks. Finally, the system can train the initial time prediction model based on the successful call time period, the outbound call connection rate and the outbound call loss rate to obtain a preset time prediction model. Specifically, the system can input the successful call time periods, outbound call connection rates and outbound call loss rates of inbound and outbound call tasks in the past period into an untrained time prediction model for training and optimization, so that the time prediction model can predict the most suitable time for outbound calls in different time periods of each day, and obtain the preset time prediction model after continuous iteration.

[0045] In the specific implementation, in order to improve the success rate of outbound call tasks, this solution can introduce a time prediction model to dynamically adjust the execution time of outbound call tasks. Figure 2 , Figure 2 This is a flow chart for generating a time prediction model in the predictive outbound calling method of this application. Figure 2 As shown, the system can first collect and analyze the user's historical outbound call data, such as successful call time, call duration, etc., and determine the successful connection rate and call loss rate of the outbound call task within a certain period of time based on these historical outbound call data, and then divide the time interval based on the successful connection rate and call loss rate to train the time prediction model. The model can make predictions based on different time periods, user behaviors, success rates and other factors, and output the most suitable time periods for outbound calls in different time periods every day. Finally, the trained time prediction model is obtained and updated to the outbound call task scheduling system. In addition, in this solution, the system can optimize the execution effect of outbound call tasks in real time through data analysis, generate key operational data such as connection rate and call loss rate, and through the analysis of these data, the system can further optimize the time prediction model and batch allocation strategy, thereby achieving continuous optimization and iteration, and improving the overall effect of outbound call tasks.

[0046] The present embodiment provides a predictive outbound calling method, which discloses determining the best connection time interval of a user according to the historical outbound calling information of the user; dynamically dividing the user based on the best connection time interval to obtain a plurality of best connection time subintervals; detecting in real time whether the time interval between the current moment and the best connection time subinterval is lower than a preset time interval threshold; if so, generating a user information outbound calling file corresponding to the best connection time subinterval; executing an outbound calling task based on the user information outbound calling file by a predictive outbound calling system; compared with the prior art, when the outbound calling system dials users in batches according to a user list, the calling efficiency is low and the connection rate is low because the calling sequence and rhythm are fixed and the connection habits and connection time periods of different users are different. Since the present embodiment can dynamically divide the best connection time interval of the user to obtain a plurality of best connection time subintervals, and when the current moment is close to the best connection time subinterval, the user is called based on the user outbound calling file, thereby solving the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to users in the call list in the same time period, resulting in low calling efficiency and low connection rate.

[0047] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , Figure 3 A flowchart diagram of the second embodiment of the predictive outbound calling method of the present application is provided.

[0048] In this embodiment, step S10 includes steps S101 to S103: Step S101: determining the user's historical connection times, user preference information and calling time period according to the user's historical outbound call information.

[0049] It should be understood that the above historical outbound call information may be information obtained after executing an outbound call task for a user in the past period of time. In this embodiment, the historical outbound call information may include at least one of the user's historical connection times, user preference information, and call time period. The historical connection times may be the number of times the user connected to the outbound call task in the past period of time; the user preference information may be the user's preferred time period for connecting to the outbound call task in the past period of time; and the call time period may be the time period during which the outbound call task made an outbound call to the user.

[0050] Step S102: Based on the historical connection times, the user preference information and the call time period, a target connection success rate corresponding to the user in different time intervals is determined by a preset time prediction model.

[0051] It can be understood that the above target connection success rate can be the probability of a user connecting to an outbound call task within different time intervals, which is predicted by a preset time prediction model.

[0052] Step S103: determining the optimal connection time interval for the user according to the target connection success rate.

[0053] In this embodiment, the system can input the user's historical connection times, user preference information and call time period into a preset time prediction model, so that the preset time prediction model predicts the probability of the user connecting to the outbound call task in different time intervals, obtains the target connection success rate, and then can determine the time interval with the highest target connection success rate as the user's optimal connection time interval.

[0054] In practical applications, in order to optimize the outbound call success rate, this embodiment can use a time prediction model to analyze the connection probability of each user in different time periods of the day. Specifically, historical data can be used and a regression model can be used to predict the connection probability P(t) of different time periods, where t represents a specific time period of the day. At this time, the time prediction model can be expressed as: P(t)=f(X), where f(X) represents a machine learning regression model, and X is a feature vector that includes historical connection information, customer preferences, call time periods, and other information. For example, for VIP customers, the time prediction model predicts that the connection probability from 2 to 4 pm is 70%, so VIP customers' outbound call tasks are prioritized during this time period.

[0055] Furthermore, before step S20, the method further includes: determining the number of batch groups according to the total number of users and the number of target batch users.

[0056] It should be noted that in order to make the outbound call task more efficient, this solution proposes a method of splitting the user list into multiple batches for processing. First, the outbound call system can split the list of users to be called into several batches according to a predetermined strategy. Specifically, this embodiment can be divided into several batches according to business needs or outbound call strategies. Each batch can be subdivided according to customer characteristics (such as geographic location, user type, contact frequency), and ensure that the number of users in each batch is appropriate to facilitate subsequent outbound call plans. Figure 4 , Figure 4 This is a processing flow chart of the batch dialing task in the predictive outbound calling method of this application. Figure 4 As shown, when making an outbound call, you can first generate a batch task, split the user list to be called into multiple batches for processing, determine the time interval for each batch of users to make calls, and then send these users to the predictive outbound call system in batches to make calls through the predictive outbound call system. After completing a batch of outbound call tasks, the system can wait for all calls in the batch to be completed before starting the next batch of outbound call tasks. In addition, for customers who need to be redialed, the system will re-add them to the next batch to be called for redialing according to the preset interval time.

[0057] It should be understood that the target batch user number can be the number of users in each batch of outbound calls in the batch outbound call task; the batch group number can be the number of this batch task. For example, if the total number of users is N and the number of users in each batch is n, then the batch group number B=N / n.

[0058] Correspondingly, the step S20 includes: dynamically dividing the users based on the number of batch groups and the optimal connection time interval to obtain a plurality of optimal connection time subintervals.

[0059] It is understandable that after determining the number B of batch groups, the users can be dynamically divided into B batches, and the optimal connection time of the users in each batch is within the corresponding optimal connection time sub-interval.

[0060] Further, the step S50 includes: determining the task execution priority corresponding to the target user within the optimal connection time subinterval based on the user information outbound call file; and executing the outbound call task for the target user based on the task execution priority through the predictive outbound call system.

[0061] It should be understood that the above task execution priority may be a priority for making outbound calls to target users within the optimal connection time subinterval. In this embodiment, the system may preferentially make outbound calls to users with high priorities.

[0062] In a specific implementation, for each task batch B_k, the system can generate an outbound call file containing user information according to the predicted optimal time period T_optimal, where the file format can be File(B_k, T_optimal). The system can then transmit the file to the predictive outbound call system, so that the predictive outbound call system can execute tasks in order of priority within the T_optimal time period until the outbound calls of all users in the batch are completed.

[0063] In the present embodiment, it is disclosed that the user's historical connection times, user preference information and calling time period are determined based on the user's historical outbound calling information; based on the historical connection times, user preference information and calling time period, the target connection success rate corresponding to the user in different time intervals is determined through a preset time prediction model; the user's optimal connection time interval is determined according to the target connection success rate, so that outbound calls can be made during the time period with a high user connection rate, thereby improving the success rate of the outbound calls.

[0064] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 5 , Figure 5 A flowchart diagram of the third embodiment of the predictive outbound calling method of the present application is provided.

[0065] In this embodiment, after step S50, the method further includes steps S601 to S604: Step S601: determining call failure users from the target users according to the outbound call task execution results of the target users.

[0066] It is understandable that the above-mentioned call failure users may be users among the target users who did not answer the call or whose numbers are wrong. In this embodiment, the system can determine the outbound call status of all target users according to the outbound call task execution results of the target users, including the connection success status and the connection failure status, and then all users in the connection failure status can be determined as call failure users.

[0067] Step S602: adding the call failure user to a waiting outbound call list, and determining the re-call time corresponding to all the call failure users in the waiting outbound call list.

[0068] It should be understood that the above-mentioned waiting outbound call list may be a list for storing information of users who need to be redialed. The above-mentioned re-calling time may be the time for making the next outbound call to the user whose call failed.

[0069] Step S603: Grouping the call failure users based on the re-call time to determine a group to be re-called.

[0070] Step S604: re-calling the group to be recalled through the predictive outbound calling system.

[0071] In this embodiment, refer to Figure 6 , Figure 6 This is a flow chart of the redial strategy in the predictive outbound calling method of this application. Figure 6 As shown, after executing the current outbound call task, the system can analyze the reasons why the call failed users were not connected based on the execution results of this outbound call task, and determine whether they need to be redialed based on these reasons. If necessary, the users who need to be redialed can be added to the outbound call list, and then the redial time of all the call failed users in the outbound call list can be predicted through the preset time prediction model, and these call failures can continue to be called in batches based on the redial time. Finally, it can be determined whether these call failed users are connected when redialed. If connected, the success result can be recorded and the outbound call status of the call failed users can be switched to a successful connection status.

[0072] In actual applications, if the outbound call result is represented by the variable R_i, where R_i=1 indicates successful connection and R_i=0 indicates unconnected, the system classifies and counts all customer outbound call results: S=∑R_i, where S represents the total number of connections. For unconnected customers (R_i=0), the system can add them to the next batch B_{k+1} of waiting outbound calls to further improve the connection rate.

[0073] Further, after step S50, the method further includes: determining the connection success rate corresponding to the optimal connection time subinterval according to the outbound call task execution result of the target user; determining the actual connection situation of the target user according to the outbound call task execution result; constructing a target optimization function based on the actual connection situation and the connection success rate; optimizing the preset time prediction model through the target optimization function; Wherein, the objective optimization function is:

[0074] In the formula, Optimize the function for the objective, is the actual connection situation, is the connection success rate, is the optimal on-time subinterval, is the model parameter.

[0075] It is understandable that the target optimization function may be a function for optimizing a preset time prediction model. The actual connection condition may be a feature value for characterizing whether the target user is connected, and if the user is connected, the value is 1; if the user is not connected, the value is 0.

[0076] In this embodiment, refer to Figure 7 , Figure 7 This is a flowchart for optimizing the outbound calling strategy in the predictive outbound calling method of this application. Figure 7 As shown, after each outbound call task is completed, the system can collect dialing data to generate an analysis report of the outbound call task, count the outbound call success rate, call duration and other data in different time periods, and generate a connection rate report and a call loss rate report based on these data, and then analyze the report data, so that the actual prediction model can be adjusted and optimized in combination with the actual effect of the outbound call task to improve the success rate of subsequent outbound call tasks. For example, the system can count the connection rates in different time periods and calculate the connection success rate P_success(t)=∑(R_i) / |T| for each time period, where T represents the set of all customers in time period t, and |T| is the number of users. The system can then fine-tune the model based on the feedback of the connection success rate to achieve higher prediction accuracy. Model adjustment can be implemented based on the optimization loss function L_adjust(θ), such as:

[0077] Where y_i is the actual connection status (connected is 1, not connected is 0), f(X) is a machine learning regression model, X is a feature vector, which may contain information such as historical connection status, customer preferences, and call time period, and θ is a model parameter.

[0078] Through repeated optimization and testing, the model eventually determined the best outbound calling time periods for different customer categories, ensuring the highest success rate and efficiency of outbound calling tasks.

[0079] In the specific implementation, refer to Figure 8 , Figure 8 This is the overall flow chart of the outbound calling system in the predictive outbound calling method of this application. Figure 8 As shown, first, the data of outbound calls made to users in the past period of time can be collected, and a time prediction model can be trained and generated based on the historical outbound call information of users. Then, users can be dynamically divided according to the optimal connection time interval of users, and users can be divided into multiple batches. Then, these users can be sent to the predictive outbound call system in batches for outbound calls. At this time, the system can determine whether the user is connected based on the outbound call results. If connected, the successful result is recorded; if not connected, the user can be added to the redial task to facilitate subsequent redialing of users who failed to call. Among them, for customers who need to be redialed, the system can re-add them to the next batch to be called out according to the preset interval time.

[0080] In this embodiment, the method disclosed is to determine the call failure users from the target users according to the execution results of the outbound call task of the target users; add the call failure users to the waiting outbound call list, and determine the re-call time corresponding to all the call failure users in the waiting outbound call list; group the call failure users based on the re-call time to determine the waiting re-call group; and re-call the waiting re-call group through the predictive outbound call system, so that the users with outbound call failure can be redialed based on the re-call time, thereby further improving the success rate of the outbound calls.

[0081] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the predictive outbound calling method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0082] This application also provides a predictive outbound calling device, please refer to Fig. 9 , the predictive outbound calling device comprises: A time prediction module 10, for determining an optimal connection time interval for the user according to the user's historical outbound call information; A dynamic batch division module 20, configured to dynamically divide the users based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; A time interval detection module 30, used for detecting in real time whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold; An outbound call file generating module 40, configured to generate an outbound call file of user information corresponding to the optimal connection time subinterval; The outbound call task execution module 50 is used to execute the outbound call task based on the user information outbound call file through the predictive outbound call system.

[0083] The predictive outbound calling device provided by the present application adopts the predictive outbound calling method in the above embodiment, which can solve the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to users in the call list in the same time period, resulting in low call efficiency and low connection rate. Compared with the prior art, the beneficial effects of the predictive outbound calling device provided by the present application are the same as the beneficial effects of the predictive outbound calling method provided by the above embodiment, and the other technical features of the predictive outbound calling device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0084] The present application provides a predictive outbound calling device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the predictive outbound calling method in the above-mentioned embodiment 1.

[0085] Reference below Fig.10 , which shows a schematic diagram of the structure of a predictive outbound calling device suitable for implementing the embodiment of the present application. The predictive outbound calling device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The predictive outbound calling device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0086] like Fig.10 As shown, the predictive outbound calling device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In RAM 1004, various programs and data required for the operation of the predictive outbound calling device are also stored. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the predictive outbound calling device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a predictive outbound calling device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0087] In particular, according to the embodiments disclosed in the present application, 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 application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0088] The predictive outbound calling device provided by the present application adopts the predictive outbound calling method in the above embodiment, which can solve the technical problems of predictive outbound calling. Compared with the prior art, the beneficial effects of the predictive outbound calling device provided by the present application are the same as the beneficial effects of the predictive outbound calling method provided by the above embodiment, and the other technical features in the predictive outbound calling device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0091] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the predictive outbound calling method in the above-mentioned embodiment.

[0092] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, 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: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0093] The computer-readable storage medium may be included in the predictive outbound calling device; or may exist independently without being assembled into the predictive outbound calling device.

[0094] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the predictive outbound calling device, the predictive outbound calling device: determines the optimal connection time interval of the user based on the user's historical outbound calling information; dynamically divides the user based on the optimal connection time interval to obtain a number of optimal connection time sub-intervals; detects in real time whether the time interval between the current moment and the optimal connection time sub-interval is lower than a preset time interval threshold; if so, generates a user information outbound calling file corresponding to the optimal connection time sub-interval; and executes an outbound calling task based on the user information outbound calling file through the predictive outbound calling system.

[0095] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] 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 application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the 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 square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0097] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0098] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned predictive outbound calling method, and can solve the technical problem that the predictive outbound calling system in the prior art usually makes batch calls to users in the call list in the same time period, resulting in low call efficiency and low connection rate. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the predictive outbound calling method provided by the above-mentioned embodiment, and will not be elaborated here.

[0099] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A predictive outbound calling method, characterized in that: The method includes: Determine the best connection time interval for the user according to the user's historical outbound call information; Dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; Real-time detection of whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold; If yes, then generating a user information outbound call file corresponding to the optimal connection time subinterval; An outbound calling task is executed based on the user information outbound calling file by a predictive outbound calling system.

2. The method according to claim 1, characterized in that The step of determining the optimal connection time interval of the user according to the historical outbound call information of the user comprises: Determine the user's historical connection times, user preference information and calling time period according to the user's historical outbound call information; Based on the historical connection times, the user preference information and the call time period, determining the target connection success rate of the user corresponding to different time intervals through a preset time prediction model; An optimal connection time interval for the user is determined according to the target connection success rate.

3. The method according to claim 2, characterized in that Before the step of dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals, the method further includes: Determine the number of batch groups based on the total number of users and the number of users in the target batch; The step of dynamically dividing the user based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals includes: The users are dynamically divided based on the batch grouping quantity and the optimal connection time interval to obtain a plurality of optimal connection time subintervals.

4. The method according to claim 3, characterized in that The step of executing the outbound calling task based on the user information outbound calling file by the predictive outbound calling system includes: Determine the task execution priority corresponding to the target user in the optimal connection time subinterval based on the user information outbound call file; An outbound calling task is executed for the target user based on the task execution priority by a predictive outbound calling system.

5. The method according to claim 4, characterized in that After the step of executing the outbound calling task for the target user based on the task execution priority by the predictive outbound calling system, the method further includes: Determine a call failure user from the target users according to the outbound call task execution result of the target users; Adding the call failure users to a waiting outbound call list, and determining the re-call time corresponding to all the call failure users in the waiting outbound call list; Grouping the call failure users based on the re-call time to determine a group to be re-called; The group to be recalled is called again through a predictive outbound calling system.

6. The method according to claim 4, characterized in that After the step of executing the outbound calling task for the target user based on the task execution priority by the predictive outbound calling system, the method further includes: Determine the connection success rate corresponding to the optimal connection time subinterval according to the outbound call task execution result of the target user; Determine the actual connection status of the target user according to the execution result of the outbound call task; Constructing a target optimization function based on the actual connection situation and the connection success rate; Optimizing the preset time prediction model by using the target optimization function; Wherein, the objective optimization function is: In the formula, Optimize the function for the objective, is the actual connection situation, is the connection success rate, is the optimal on-time subinterval, is the model parameter.

7. The method according to claim 1, characterized in that Before the step of determining the optimal connection time interval of the user according to the historical outbound call information of the user, the method further includes: Determine the user's outbound calling status based on historical outbound calling task execution results; When the user's outbound call status is a successful connection status, determining a successful call time period and a historical call duration corresponding to the current successful connection task; Determine the outbound call connection rate and the outbound call loss rate based on the user's outbound call status and the historical call duration; The initial time prediction model is trained based on the successful call time period, the outbound call connection rate and the outbound call loss rate to obtain a preset time prediction model.

8. A predictive outbound calling device, characterized in that: The device comprises: A time prediction module, used to determine the optimal connection time interval of the user according to the user's historical outbound call information; A dynamic batch division module, used for dynamically dividing the users based on the optimal connection time interval to obtain a plurality of optimal connection time subintervals; A time interval detection module, used for detecting in real time whether the time interval between the current moment and the optimal connection time subinterval is lower than a preset time interval threshold; An outbound call file generation module, configured to generate a user information outbound call file corresponding to the optimal connection time subinterval; An outbound call task execution module is used to execute the outbound call task based on the user information outbound call file through a predictive outbound call system.

9. A predictive outbound calling device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the predictive outbound calling method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the predictive outbound calling method according to any one of claims 1 to 7 are implemented.

Images