Client portrait-based call-out method and system, medium and program product

Abstract

The invention provides an outbound method and system based on a customer portrait, a medium, a program product and an electronic terminal, and the method comprises the steps: obtaining the historical call records of all customers, and screening the customer groups according to the basic information of all customers and the preset rejection times according to a preset standard, thereby obtaining a second customer group with low call quality; and different call-out rules are respectively adopted for the customer group with low call quality and the customer group with high call quality, so that the call-out frequency of the customer group with low call quality is reduced, and call-out resources are saved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence outbound calling, and in particular to an outbound calling method, system, medium and program product based on customer portrait. Background Art

[0002] With the development of artificial intelligence and voice recognition technology, intelligent outbound (phone calls automatically made to customers through computers) systems, especially automated calls made by robots, have become an important tool for improving customer reach, business conversion rates and reducing labor costs. Therefore, in modern business operations, more and more companies are beginning to adopt intelligent outbound systems, which are usually combined with automated calling strategies to improve work efficiency, such as giving priority to high-potential customers and selecting corresponding words based on customer intentions.

[0003] As business volume grows, especially during peak hours, enterprises may encounter the problem of tight communication line resources when making intelligent outbound calls. For example, the outbound call system may require multiple telephone lines to make calls concurrently. When the outbound call task volume is large, line resources may become tight, and some outbound call tasks may have low returns (such as low answering rate, poor conversion rate, etc.). If these tasks still occupy resources, it will affect calls to high-value customers.

[0004] Therefore, given limited resources, how to reasonably screen and optimize outbound call tasks and effectively release concurrent pressure, thereby improving the overall performance of the outbound call system and customer conversion effects, is the problem we face today. Summary of the invention

[0005] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide an outbound calling method, system, medium, program product and electronic terminal based on customer portrait, so as to solve the problem in the prior art that there is no reasonable screening and optimization of outbound calling tasks, resulting in low utilization of outbound calling resources.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides an outbound calling method based on customer portrait, including: when executing a customer outbound call, querying whether the current to-be-called number is a marked customer group including a portrait tag based on the to-be-called data set; the marked customer group is a customer group whose number of unconnected days within a first time period is higher than a preset connection day threshold; within the preset time period, executing a single outbound call to the marked customer group, and executing at least two outbound calls to the unmarked customer group.

[0007] In an embodiment of the first aspect of the present application, the pre-screening process of the marked customer group includes: based on preset screening conditions and historical call information of the to-be-called number, screening out a first marked data set from the to-be-called data set, the preset screening conditions including the call date; combining the call date and the outbound number in the first marked data set through a window function, judging the connection status of each combined data set, and generating a second marked data set according to the judgment result; based on the second marked data set, screening out the combined data set whose connection status is not connected as a third marked data set; based on the third marked data set, counting the number of non-connection days corresponding to each of the outbound numbers, screening out the marked customer group according to the statistical results and performing portrait labeling.

[0008] In an embodiment of the first aspect of the present application, the preset screening condition also includes at least one of location, name, server information, and event record.

[0009] In an embodiment of the first aspect of the present application, the execution of a single outbound call to the first customer group specifically includes: obtaining a peak call time period in the pending call data set; the peak call time period is the time period with the highest daily outbound call connection rate in the second time period; executing a single outbound call to the first customer group during the peak time period, and executing at least two outbound calls to the first customer group during the non-peak time period.

[0010] In an embodiment of the first aspect of the present application, the execution of at least two outbound calls to the second customer group specifically includes: obtaining a call number threshold in the waiting-to-call data set; the call number threshold is the minimum number of outbound calls covering the preset connection rate for the day within a third time period; for the second customer group whose outbound call number exceeds the call number threshold, refusing to execute outbound calls within the third time period.

[0011] In an embodiment of the first aspect of the present application, the single outbound call to the marked customer group within the preset time period specifically includes: for the marked customer group including the portrait tag, the outbound call task request of the current number to be called is executed when the current number to be called is read for the first time, and the outbound call task request is not executed when the number is read again within the preset time period.

[0012] In an embodiment of the first aspect of the present application, it also includes: at the end of a preset statistical period, summarizing the event tags of the call numbers that have not executed the outbound call task request, generating and feeding back to the customer a call event record including the event tags.

[0013] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an outbound call system based on customer portraits, including: a big data query module, which is used to query whether the current to-be-called number is a marked customer group including a portrait tag based on the to-be-called data set when executing a customer outbound call; the marked customer group is a customer group whose number of unconnected days within a first time period is higher than a preset connection day threshold; an outbound call module, which is used to execute a single outbound call to the marked customer group within a preset time period, and to execute at least two outbound calls to the unmarked customer group.

[0014] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements any of the aforementioned methods when executed by a processor.

[0015] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements any of the methods described above.

[0016] As mentioned above, the present application has the following beneficial effects:

[0017] The present application obtains the historical call records of all customers, and obtains a second customer group with low call quality after screening the customer group based on the basic information of all customers and the preset number of rejections according to preset standards. Different outbound call rules are adopted for the customer group with low call quality and the customer group with medium call quality, thereby reducing the number of outbound calls to the customer group with low call quality and saving outbound call resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a flowchart of an outbound calling method based on customer portrait in one embodiment of the present application.

[0019] Figure 2 Shown is a flowchart of an outbound calling method based on customer portrait in one embodiment of the present application.

[0020] Figure 3 Shown is a structural diagram of an outbound calling system based on customer portrait in one embodiment of the present application. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0022] In the existing intelligent outbound calling system, outbound calling is mainly achieved by robots automatically dialing the phone. Enterprises can set up outbound calling tasks in the system, configure corresponding parameters, and use robots to automatically execute outbound calling tasks. For example:

[0023] First, when a user creates a task in the system, he needs to specify a task name, select a robot, configure a dialing line, set a task time, etc. for each task. The task configuration process includes task name, robot selection, line selection, time setting, redial strategy, etc. Task name refers to naming each task for easy management and subsequent tracking; robot selection refers to selecting a bound robot according to task requirements, and the robot is responsible for performing outbound calls; line selection refers to configuring a suitable outbound call line for the task to ensure that the line used for outbound calls matches the target phone; time setting refers to setting the start time and end time of the task to ensure that the outbound call is made within the specified time; redial strategy refers to setting an automatic redial strategy for unanswered calls, including the redial interval and the number of redials.

[0024] Secondly, users can upload a robot template for the task, which contains the framework code and task flow required for the robot to make outbound calls. The content of the template usually includes the speech template and task rules. The speech template refers to the interaction content between the robot and the customer, and the task rules refer to the dialing strategy, the customer group to be dialed first, etc. After uploading the template, the system will bind the task to the robot template to ensure that the outbound call process complies with the preset rules and strategies.

[0025] After the task configuration is completed, the system will verify the basic information of the task and create the robot outbound call task after ensuring that it is correct. The robot will automatically start outbound calls and dial the customer's phone according to the rules set in the task. It should be understood that the verification process is a key link to ensure that the outbound call task can be executed smoothly. The system ensures that the created task meets the execution requirements by format verification, data consistency check, format verification and robot configuration verification of the slot data in the task template. Once the verification passes, the system will successfully create the task and prepare to execute the outbound call operation. If the verification fails, the system will prompt the user to make necessary corrections to avoid execution problems caused by format or configuration errors. Through this verification mechanism, enterprises can ensure the smooth execution of outbound call tasks, reduce human errors, and improve the stability and efficiency of the system.

[0026] Then during the task execution, the system provides real-time task progress monitoring function, allowing users to view the execution status of the task, including the number of calls made, connection rate, etc. This helps managers monitor task execution and make adjustments as needed.

[0027] After the task is completed, the system will generate a detailed report for each call, including call tags and event tags, etc. Call tags refer to the connection status of the call (such as not connected, no sound, voicemail, etc.), and event tags refer to the records of key information and events generated during the call.

[0028] Robot outbound calls are made by creating a single task. Each task can cover 1-10,000 to-be-dial lists (10,000 is the recommended number of lists, and there is actually no limit to the number of lists for a single task). The corresponding call results are generated after the call is completed.

[0029] In actual use of the above technical solution, some outbound call tasks have low returns. For example, for unanswered calls, even if you continue to redial when the call is not connected, the connection rate is still low. Unanswered calls take up a lot of resources but do not generate actual value, especially for target customer groups with low answering rates. Repeatedly dialing unanswered calls will only waste call lines and system resources, resulting in low call resource utilization efficiency.

[0030] In addition, the system usually allocates a certain number of lines for tasks, and dials are made simultaneously according to the set tasks. When multiple outbound call tasks are carried out at the same time, unanswered calls will continue to occupy the call lines. Especially during peak hours, the lines may be occupied by a large number of unanswered calls, resulting in other high-return tasks not being dialed in time. In this case, the waste of line resources not only affects the execution efficiency of the task, but also reduces the overall resource utilization effect.

[0031] In addition, although the redial strategy in the system helps to increase the chances of answering missed calls, if the number of redials is too many, or the missed calls themselves do not have a high conversion probability, the system will occupy call resources for a long time to make invalid repeated calls. The resource consumption caused by repeated invalid calls is obvious, especially in tasks with low answer rates, the resource consumption efficiency is very low.

[0032] Also, during peak hours, the number of outbound call tasks surges, and the system needs to handle a large number of outbound call tasks at the same time. Without effective resource allocation and optimization, the system may cause line resource shortage due to a large number of unanswered calls, affecting the execution of other high-priority tasks. This will directly lead to reduced call efficiency and unsatisfactory overall outbound call results for the enterprise.

[0033] In summary, the existing system has low call resource utilization due to problems such as low-return tasks occupying resources, line resource waste, and repeated invalid calls when facing a large number of unanswered calls. These problems directly affect the performance of the system during high-concurrency periods and the overall outbound call efficiency. Therefore, it is necessary to improve the system's resource utilization and outbound call effect by optimizing dialing strategies, intelligently screening customers, and reasonably allocating resources.

[0034] Therefore, the first aspect of the present invention provides an outbound calling method based on customer portraits, such as Figure 1-2 As shown, the following steps are included:

[0035] S1: When executing an outbound call to a customer, query whether the current number to be called is a marked customer group including a portrait tag based on the data set to be called.

[0036] Among them, after the user sends the robot an instruction to call the call data set to make the robot perform an outbound call to the customer, the robot will call the batch query interface provided by the big data, and query whether the current number to be called has a portrait tag during the outbound call process to identify whether the current customer to be called is a marked customer group with unsatisfactory outbound call effect. In this embodiment, the marked customer group with unsatisfactory outbound call effect is screened by the number of days without connection. The marked customer group is a customer group with a number of days without connection in the first time period exceeding a preset connection day threshold. For example, a customer group with a number of days without connection exceeding 18 days in a month is screened as a marked customer group, and the outbound call strategy is adjusted for the marked customer group with unsatisfactory outbound call effect.

[0037] S2: Perform a single outbound call to the marked customer group within a preset time period.

[0038] Through the evaluation of historical call records, the first round connection rate for the outbound user group is relatively high, and the first round and first circle connection rate is as high as 90%, which is much higher than the second round and other subsequent rounds of connection rates. Therefore, in this embodiment, even if the marked customer group with unsatisfactory outbound call effect is targeted, the first round of outbound calls is still executed to reduce the overall connection rate loss.

[0039] S3: Perform at least two outbound calls to the non-marked customer group within a preset time period.

[0040] The outbound calling strategy adjustment for marked customers lasts for a preset time period, which can be adjusted by the user. For example, within a day, only a single outbound call is performed on the marked customer group who have not been connected for more than 18 days in the past month, and the preset call strategy is executed for the unmarked customer group. The call strategy for the unmarked customer group executes at least two outbound calls. The outbound calling requirements for different users may change. Common outbound calling strategies include calling customers once every half an hour, calling customers frequently during specific time periods every day, and calling customers less frequently during other time periods.

[0041] In one embodiment of the first aspect of the present application, when the robot performs batch outbound calls on a waiting call data set according to a user request, multiple rounds of outbound calls will be performed. For example, for a waiting call data set containing 10,000 outbound call numbers, the robot will perform outbound calls on 10,000 outbound call numbers in the first round, and then perform outbound calls on numbers that were not connected in the first round or had poor call quality in the second round. In this embodiment, for a marked customer group including a portrait tag, an outbound call task request for the current waiting call number is executed when the current waiting call number is read for the first time, and the task request is not executed when it is read again within a preset time period. That is, after the first round of outbound calls are still performed on the marked customer group with unsatisfactory outbound call results, no outbound calls will be made to the marked customers again within a period of time to reduce the waste of call resources. The preset time period can be set by the user according to user needs. For example, only a single outbound call is performed on the marked customer within a day, or only a single outbound call is performed on the user within 1 hour. All of these solutions belong to the protection scope of the present application.

[0042] In an embodiment of the first aspect of the present application, the robot can set the preset time period for executing a single outbound call with reference to the peak call period, or the robot can provide the peak call period to the user as a reference parameter for setting the preset time period. Taking the setting of the preset time period for executing a single outbound call by the robot with reference to the peak call period as an example, the robot executes a single outbound call to the first customer group, specifically including: obtaining the peak call period in the waiting-to-call data, executing a single outbound call to the first customer group during the peak period, and executing at least two outbound calls to the first customer group during the non-peak period. Among them, the peak call period is the time period with the highest daily outbound call connection rate in the second time period according to the statistics of historical outbound call data. In the second time period, the call resource occupancy rate is high and the call connection rate is high. In order to balance the call connection rate and call efficiency, it is necessary to execute only a single outbound call to the marked customer group in the second time period, and the non-marked customer group is not restricted by the single outbound call plan, and multiple rounds of outbound calls are executed normally.

[0043] For example, in hours, if the time period with the highest daily outbound call connection rate within 7 days is 9.00-10.00, the robot can be set between 9.00-10.00 today, and only perform a single outbound call to the marked customer group, and perform at least two (multiple rounds) of outbound calls to the unmarked customer group; in the time period except between 9.00-10.00 today, multiple rounds of outbound calls can be performed to both the marked customer group and the unmarked customer group.

[0044] In one embodiment of the first aspect of the present application, the number of outbound calls of the second customer group can be further limited according to the call number threshold in the call plan. Specifically, when the robot executes an outbound call on the data set to be called in each round, the call number threshold in the data set to be called is obtained, and the outbound call is refused within the third time period for the second customer group whose outbound call number exceeds the call number threshold. The call number threshold is a dynamically adjusted data parameter, which can be set to the minimum number of outbound calls covering the preset connection rate of the day within the third time period. For example, the minimum number of outbound calls covering 95% of the calls picked up on the day within half a year can be 20 times, and 20 times is used as the current call number threshold; when the number of outbound calls to the current outbound number in the second customer group today exceeds 20 times, the current outbound number will no longer be executed today, and the number is dynamically adjusted to achieve the effect of saving communication resources, saving ringing time, improving the connection rate, and increasing the effective call time per day. Among them, the call number threshold should be greater than or equal to 2.

[0045] In one embodiment of the first aspect of the present application, a robot provides a pre-screening and user portrait labeling process for a marked customer group, and the pre-screening process for the marked customer group includes: based on preset screening conditions and historical call information of the number to be called, a first marked data set is screened out from the to-be-called data set, and the preset screening conditions include the call date; the call date and the outbound number in the first marked data set are combined through a window function, and the connection status of each combined data set is judged, and a second marked data set is generated according to the judgment result; based on the second marked data set, a combined data set with a connection status of not connected is screened out as a third marked data set; based on the third marked data set, the number of days of not being connected corresponding to each outbound number is counted, and the marked customer group is screened out according to the statistical results and a portrait label is performed.

[0046] It should be understood that historical call information includes but is not limited to call duration, number of answers, number of rejections, call quality and call tags. Call duration refers to the duration of each call, and call duration reflects the customer's level of interaction. Number of answers refers to the number of calls answered by each customer, reflecting the customer's activity. Number of missed calls refers to the number of times a customer did not answer a call, which is used to analyze the customer's answering preferences. Call quality includes voice clarity, signal strength, etc., reflecting the effect of outbound calls. Call tags include call status (such as successful connection, no sound, voicemail, etc.). Based on this information, it is possible to analyze the customer's willingness to answer unknown calls and the degree of acceptance of obtaining information through telephone channels.

[0047] Assume that in a telecom company's outbound call system, the customer's historical call data is stored in the waiting-to-call data set, and each piece of data includes the customer's phone number, call date, and connection status (i.e., whether the call was connected). If the connection days threshold is set to 3, then if the customer has not answered the call for more than 3 days in the past 3 days, then the customer will be marked as a customer who needs attention and classified as a marked customer group.

[0048] For example, the historical call data of a customer is as follows:

[0049] day callee_number dialinfo_connected 2022-10-01 23456 Not connected 2022-10-02 23456 Not connected 2022-10-03 23456 Connect 2022-10-04 23456 Not connected

[0050] Based on this data, the system first filters it according to the preset filtering conditions. The filtering condition is the call date, that is, the customer's call date must be within the set time range, and then the system will combine and analyze the data through the window function. At this time, the window function can be used for filtering. The window function can analyze the connection status of each call date based on the different call dates and outbound call numbers of each customer. Furthermore, the customer's number of days without connection is 3 days, which exceeds the threshold of 3 days for the number of days of connection, so the customer is classified as a marked customer group.

[0051] It should be understood that the window function is used to perform calculations within a specific "window" of data while retaining the original data of each row. Unlike aggregate functions (such as SUM(), AVG()), window functions do not merge multiple rows into one row, but return a calculation result for each row.

[0052] For another example, assume that the historical call information includes the following data:

[0053]

[0054]

[0055] For day = 2023-10-01 and callee_number = 12345, the result of the IF expression is [1,0]; the result of MAX() is 1, so is_connected = 1. This means that the number received a call on that day.

[0056] For day = 2023-10-01 and callee_number = 67890, the result of the IF expression is [0]; the result of MAX() is 0, so is_connected = 0. This means that the number did not receive a call on that day.

[0057] For day = 2023-10-02 and callee_number = 12345, the result of the IF expression is [0]; the result of MAX() is 0, so is_connected = 0. This means that the number did not receive a call on that day.

[0058] It should be understood that in MAX(IF(dialinfo_connected='1',1,0)), IF(dialinfo_connected='1',1,0) is a conditional expression used to determine whether the value of the dialinfo_connected field is '1'. If dialinfo_connected='1', it returns 1, indicating that the call is connected; otherwise, it returns 0, indicating that the call is not connected. MAX() takes the maximum value of the result of the IF expression. Since the result of the IF expression can only be 1 or 0, the function of MAX() is: if there is at least one 1 in the group, it returns 1; if all the values ​​in the group are 0, it returns 0. is_connected is the calculation result of the window function, indicating whether there is a connected record under a certain combination of day and callee_number: if is_connected=1, it means that at least one record in the group has a dialinfo_connected value of '1' (i.e., connected); if is_connected=0, it means that the dialinfo_connected values ​​of all records in the group are '0' (i.e., not connected).

[0059] In addition, you can also use OVER(PARTITION BY day,callee_number) to process the data. OVER is a window function that is used to define the range of calculation (i.e., "window"). PARTITION BY day,callee_number: Group the data by day (date) and callee_number (called number). Within each group, the window function will be calculated independently. If there are multiple call records on a certain day (day) (with different callee_number), each callee_number will be grouped separately; if the same callee_number has records on multiple days, each day will be grouped separately.

[0060] In an embodiment of the first aspect of the present application, the preset screening condition also includes at least one of location, name, server information, and event record.

[0061] Basic information includes the customer's location, company, and server. Because the customer's geographical location will directly affect the outbound call time period and dialing strategy, the best dialing time can be set by analyzing the customer's geographical location and combining the local time zone and time period characteristics. In addition, the location can also help evaluate the customer's possible language preferences, industry characteristics, etc. Preferably, when the customer is located in a specific city or region, the dialing strategy is optimized according to the specific working hours, holiday arrangements, etc. of the region. By analyzing the company information to which the customer belongs, it is helpful to identify the customer's industry background, business needs, and potential customer value. For customers in different industries, different outbound call scripts and marketing content can be set. Preferably, when some companies frequently generate unanswered calls, by identifying these company customers, the dialing time or script strategy is adjusted to improve the connection rate. Server information is usually related to the customer's technical environment. Especially in B2B (business to business) scenarios, understanding the server or software platform used by the customer can help the system better analyze the type of customer needs. Preferably, when some companies use specific types of servers or systems, customized services or technical support are provided based on this information.

[0062] In an embodiment of the first aspect of the present application, it also includes: at the end of the preset statistical period, the event tags of the call numbers that have not executed the outbound call task request are summarized, and a call event record including the event tag is generated and fed back to the customer. In this embodiment, the current round of outbound call tasks for the call numbers that have not executed the outbound call task request can be marked as a non-connected event tag and recorded in the call event record, so that the user can obtain the summary of the call status of the marked customer group, and at the same time, the setting parameters of the robot when executing the outbound call task can be dynamically adjusted based on the non-connected events of the marked customer group, such as the peak call period, call number threshold and other parameters in this application.

[0063] Preferably, the call event record includes the intention of the call, marketing content, customer questionnaire, etc. By feeding back the record to the customer, on the one hand, the customer can obtain relevant information through the SMS channel even if the call is not received, and through the questionnaire, it is helpful to adjust the outbound call strategy later. For example, certain types of problems (such as wrong number) can be handled specifically, and the time or frequency of outbound calls can be adjusted for other types of problems (such as busy customers).

[0064] like Figure 3 As shown, the second aspect of the present application provides an outbound call system based on customer portraits, including: a big data query module, which is used to query whether the current to-be-called number is a marked customer group including a portrait tag based on the to-be-called data set when executing a customer outbound call; the marked customer group is a customer group whose number of unconnected days within a first time period is higher than a preset connection day threshold; an outbound call module, which is used to execute a single outbound call to the marked customer group within a preset time period, and to execute at least two outbound calls to the non-marked customer group.

[0065] Preferably, the outbound call system based on customer portrait also includes a screening module, which is used to pre-screen the marked customer group, and the pre-screening process includes: based on preset screening conditions and historical call information of the number to be called, screening out a first marked data set from the to-be-called data set, and the preset screening conditions include call date; combining the call date and the outbound number in the first marked data set through a window function, judging the connection status of each combined data set, and generating a second marked data set according to the judgment result; based on the second marked data set, screening out the combined data set whose connection status is not connected as a third marked data set; based on the third marked data set, counting the number of non-connected days corresponding to each of the outbound numbers, and screening out the marked customer group according to the statistical results and performing portrait labeling.

[0066] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0067] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0068] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements any of the aforementioned methods when executed by a processor.

[0069] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements any of the methods described above.

[0070] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. For example, the first XX and the second XX are only used to distinguish different XXs, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0071] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0072] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0073] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0074] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0076] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0079] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When loading and executing computer program instructions (programs) on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs), etc.).

[0080] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0081] 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.

[0082] In summary, the present invention effectively overcomes various shortcomings of the prior art and has high industrial utilization value.

[0083] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An outbound calling method based on customer portrait, characterized in that: include: When executing an outbound call to a customer, query whether the current number to be called is a marked customer group including a portrait tag based on the waiting-to-call data set; The marked customer group is a customer group whose number of unconnected days in the first time period is higher than a preset connection day threshold; Within a preset time period, a single outbound call is performed for the marked customer group, and at least two outbound calls are performed for the unmarked customer group.

2. The outbound calling method according to claim 1, characterized in that: The pre-screening process for the marked customer group includes: Filtering a first marked data set from the to-be-called data set based on a preset screening condition and historical call information of the to-be-called number, wherein the preset screening condition includes a call date; Combining the call date and the outbound call number in the first labeled data set by using a window function, determining the connection status of each combined data set, and generating a second labeled data set according to the determination result; Based on the second marked data set, filtering out the combined data set whose connection status is not connected as a third marked data set; The number of days without a call corresponding to each outbound call number is counted based on the third marked data set, and the marked customer group is screened out according to the statistical result and a portrait label is performed.

3. The outbound calling method according to claim 2, characterized in that: The preset screening condition also includes at least one of location, name, server information, and event record.

4. The outbound calling method according to any one of claims 1 to 3, characterized in that: The performing a single outbound call to the first customer group specifically includes: Obtain a peak call period in the waiting-to-call data set; the peak call period is a time period with the highest daily outbound call completion rate in the second time period; A single outbound call is performed for the first customer group during the peak period, and at least two outbound calls are performed for the first customer group during the non-peak period.

5. The outbound calling method according to any one of claims 1 to 3, characterized in that: The performing at least two outbound calls to the second customer group specifically includes: Obtaining a call count threshold in the waiting-to-call data set; the call count threshold is the minimum number of outbound calls covering a preset connection rate for the day within a third time period; For the second customer group whose outbound call times exceed the call time threshold, outbound calls are refused within the third time period.

6. The outbound calling method according to claim 1, characterized in that: The performing of a single outbound call to the marked customer group within a preset time period specifically includes: For the marked customer group including the portrait tag, the outbound call task request of the current number to be called is executed when the current number to be called is read for the first time, and the outbound call task request is not executed when the number is read again within the preset time period.

7. The outbound calling method according to claim 6, characterized in that: Also includes: At the end of the preset statistical period, the event tags of the call numbers that have not executed the outbound call task request are summarized, and a call event record including the event tags is generated and fed back to the customer.

8. An outbound calling system based on customer portrait, characterized in that: include: A big data query module is used to query whether the current to-be-called number is a marked customer group including a portrait tag based on the to-be-called data set when executing a customer outbound call; The marked customer group is a customer group whose number of unconnected days in the first time period is higher than a preset connection day threshold; The outbound calling module is used to execute a single outbound calling to the marked customer group and execute at least two outbound calling to the unmarked customer group within a preset time period.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes computer program codes, and when the computer program codes are executed on a computer, the computer is enabled to implement the method according to any one of claims 1 to 6.

Images