Method and system for improving outbound call completing rate

Abstract

The invention belongs to the technical field of telephone outbound calls, and discloses a method and a system for improving the outbound call completing rate, and the method for improving the outbound call completing rate comprises the following specific steps: step 1, setting an outbound call period and customer active time; step 2, number selection and attribution calculation; 3, executing a number selection model and an attribution mode; step 4, customer matching and call execution; 5, switching a number selection mode to an external number display provincial meeting city mode; step 6, switching a number selection mode to a mode of displaying numbers in other cities of the province; and step 7, adopting a business city to initiate an outbound mode. According to the innovative system and method provided by the invention, the AI capability and the big data model algorithm are applied to intelligently select and call the customer in a time period with a high call-out call completing rate, and meanwhile, a number selection model is optimized by adopting various strategies to ensure that the most suitable attribution external display number is used to contact the customer, so that the call-out call completing rate is remarkably improved, the customer loss is reduced, and the customer experience is improved. And the overall conversion rate is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of outbound telephone calls, and in particular relates to a method and a system for improving an outbound call connection rate. Background Art

[0002] The current outbound call system mainly relies on line monitoring to improve the connection rate by disabling numbers that cannot be dialed. However, there is a lack of a comprehensive system and number selection strategy to more effectively improve the connection rate.

[0003] There are two existing strategies, each with its own focus:

[0004] The first strategy focuses on real-time monitoring of the status of intermediate numbers. Once an abnormal number is found, the status in the number pool is updated and the privacy number platform is notified to handle it. In addition, the account balances of all intermediate numbers in the number pool are monitored. After receiving the offline information of the abnormal number, the system will intelligently analyze the optimal billing strategy based on the number usage time and call behavior, and calculate the fees for the abnormal number, and then send the fees and billing model to the privacy number platform. This method does not require active inquiries or customer feedback, and can eliminate or process problem numbers before affecting the connection rate. The key is to use numbers that match the location for outbound calls.

[0005] The second strategy focuses on line-level optimization. First, obtain the line type, determine the physical line, and then obtain the characteristic information of the physical line. Based on this information, physical lines with the same characteristics are combined into a group of physical lines. Next, obtain the routing rule information, combine the group of physical lines and the routing rule information to generate a virtual line. By obtaining the monitoring data of the virtual line in real time, a line management database is established. This method also focuses on whether the number can be successfully dialed to improve the connection rate.

[0006] However, both strategies only consider whether the number can be successfully dialed, and fail to improve the connection rate from the business level. Therefore, it is necessary to improve this. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for improving the outbound call connection rate, so as to solve the problems raised in the above background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for improving the outbound call connection rate, the method for improving the outbound call connection rate comprises the following specific steps:

[0009] Step 1: Setting the outbound call time period and customer active time

[0010] The outbound call module uses the prediction model to calculate the time period with the highest customer connection rate, and sets this time period as the customer active time; within this set customer active time window, the outbound call module executes the outbound call initiation instruction;

[0011] Step 2: Number selection and location calculation

[0012] After receiving the outbound call instruction, the number pool module selects the number with the highest connection rate according to the historical connection rate ranking; pushes the selected number to the location model to calculate the location of the external number;

[0013] Step 3: Number selection model and location model execution

[0014] The calculated location information is pushed to the number selection model. In the number selection model, the location mode is first executed, that is, finding customers whose location is consistent with the displayed number;

[0015] Step 4: Customer matching and call execution

[0016] If a customer with the same location is matched, the customer and the external number are bound; the bound information is pushed to the outbound call system to complete the call; steps 3 to 4 are repeated until no more qualified customers are matched;

[0017] Step 5: Switch the number selection mode to the visible provincial capital city mode

[0018] After the outbound call is completed using the home location mode, the outbound call system checks whether there are any customers that have not been called; if there are any remaining customers, the number selection model is switched to the external number provincial capital city mode; steps 3 to 4 are repeated until no customers can be matched;

[0019] Step 6: Switch the number selection mode to the external number display mode for other cities in the province

[0020] After the outbound call in the provincial capital city mode is completed, the outbound call system checks again whether there are any customers who have not been called; if there are any remaining customers, the number selection model is switched to the other cities in the province mode of the external number; steps 3 to 4 are repeated until no customers can be matched;

[0021] Step 7: Use the business city to initiate an outbound call mode

[0022] If there are still remaining customers after going through all the above modes, the outbound calling mode is initiated in the business city; steps 3 to 4 are executed repeatedly until all customers have been called.

[0023] Preferably, the method is divided into four modes, namely: the place of origin mode, the provincial capital city mode, the other cities in the province mode and the business city initiating outbound call mode; the four modes are executed in sequence.

[0024] Preferably, the step 4 specifically includes three steps of binding external display, initiating an outbound call and successful outbound call, and they are executed one by one in sequence.

[0025] Preferably, the calculation of the place of origin of the visible number in step 2 specifically includes: obtaining the first 7 digits of the mobile phone number according to the mobile phone number, matching the place of origin in the number pool module through the first 7 digits, and obtaining the city and province to which the customer belongs;

[0026] If it does not exist, the positioning city is obtained based on the customer's IP. If the positioning city does not exist, the location of the visible number is located according to the city recorded. If it does not exist, a visible number with a high connection rate is randomly selected.

[0027] Preferably, the outbound call time period and customer active time setting in step 1 further include: if the customer exists in the system, setting the time period of answering calls in the historical portrait as the customer active time;

[0028] If the customer does not exist in the system, the system will compare the time periods with the highest connection rates in the last 30 days, the last 7 days, and the last day, using coefficients of 0.5, 0.3, and 0.2 to obtain the maximum value, and the corresponding time period will be defined as the customer's active time.

[0029] Preferably, the system is composed of the following modules: prediction model module, number pool module, location model module, number selection model module and outbound call module;

[0030] Prediction model module: used to establish a customer active period prediction model to predict the period with the highest customer connection rate.

[0031] Number pool module: stores a large number of numbers and intelligently selects the number with the highest connection rate based on the historical connection rate ranking.

[0032] Location model module: calculates the location information of the visible number.

[0033] Number selection model module: executes the place of origin mode, the provincial capital city mode, the other cities in the province mode and the business city outbound call initiation mode to achieve accurate matching and multi-mode switching.

[0034] Outbound call module: receives information pushed by the number selection model and performs calling operations.

[0035] Preferably, the prediction model module is established using big data and machine learning technology, and uses big data matching technology to find the place of origin and bind the customer to the external number in real time.

[0036] Preferably, the number pool module intelligently selects the number with the highest connection rate according to the historical connection rate ranking.

[0037] Preferably, the number selection model module also includes a logic control unit for switching different number selection modes.

[0038] Preferably, the system further comprises a database module for storing customer information and call data.

[0039] The beneficial effects of the present invention are as follows:

[0040] The present invention aims to reduce customer churn and improve conversion rate by calling customers during the period when the outbound call connection rate is high. At the same time, the present invention also adopts an innovative number selection model, which prevents customers from rejecting calls due to out-of-town numbers through various strategies. The process predicts the period when the customer connection rate is the highest through the outbound call system, and initiates outbound call tasks during this period. In addition, the self-developed number pool model and number selection model use big data matching technology to find the place of origin, and bind customers to the external numbers in real time, thereby further improving the overall connection rate. This module adopts a variety of strategy models, including the use of provincial capital external numbers, external numbers of other places of origin in the province, and external numbers designated by the business, to optimize the use of external numbers of the place of origin to contact customers. The priorities of these strategy models decrease in turn, ensuring that the most appropriate number is used to make calls during the period with the highest customer connection rate, thereby improving the conversion rate. Through this solution, the possibility of customers rejecting calls due to out-of-town numbers and reducing customer churn can be significantly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a simplified flow chart of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] like Figure 1 As shown, the embodiment of the present invention provides a method for improving the outbound call connection rate, and the specific steps of the method for improving the outbound call connection rate are:

[0044] Step 1: Setting the outbound call time period and customer active time

[0045] The outbound call module uses the prediction model to calculate the time period with the highest customer connection rate, and sets this time period as the customer active time; within this set customer active time window, the outbound call module executes the outbound call initiation instruction;

[0046] Step 2: Number selection and location calculation

[0047] After receiving the outbound call instruction, the number pool module selects the number with the highest connection rate according to the historical connection rate ranking; pushes the selected number to the location model to calculate the location of the external number;

[0048] Step 3: Number selection model and location model execution

[0049] The calculated location information is pushed to the number selection model. In the number selection model, the location mode is first executed, that is, finding customers whose location is consistent with the displayed number;

[0050] Step 4: Customer matching and call execution

[0051] If a customer with the same location is matched, the customer and the external number are bound; the bound information is pushed to the outbound call system to complete the call; steps 3 to 4 are repeated until no more qualified customers are matched;

[0052] Step 5: Switch the number selection mode to the visible provincial capital city mode

[0053] After the outbound call is completed using the home location mode, the outbound call system checks whether there are any customers that have not been called; if there are any remaining customers, the number selection model is switched to the external number provincial capital city mode; steps 3 to 4 are repeated until no customers can be matched;

[0054] Step 6: Switch the number selection mode to the external number display mode for other cities in the province

[0055] After the outbound call in the provincial capital city mode is completed, the outbound call system checks again whether there are any customers who have not been called; if there are any remaining customers, the number selection model is switched to the other cities in the province mode of the external number; steps 3 to 4 are repeated until no customers can be matched;

[0056] Step 7: Use the business city to initiate an outbound call mode

[0057] If there are still remaining customers after going through all the above modes, the outbound calling mode is initiated in the business city; steps 3 to 4 are executed repeatedly until all customers have been called.

[0058] Among them, the method is divided into four modes, namely: the place of origin mode, the provincial capital city mode, the other cities in the province mode and the business city initiating outbound call mode; the four modes are executed in sequence.

[0059] Among them, step four specifically includes three steps: binding external display, initiating outbound call and outbound call success, and they are executed one by one in sequence.

[0060] The calculation of the location of the visible number in step 2 specifically includes: obtaining the first 7 digits of the mobile phone number according to the mobile phone number, matching the location in the number pool module through the first 7 digits, and obtaining the city and province to which the customer belongs;

[0061] If it does not exist, the positioning city is obtained based on the customer's IP. If the positioning city does not exist, the location of the visible number is located according to the city recorded. If it does not exist, a visible number with a high connection rate is randomly selected.

[0062] Among them, the outbound call time period and customer active time setting in step 1 also include: if the customer exists in the system, the time period of answering the call in the historical portrait is set as the customer active time;

[0063] If the customer does not exist in the system, the system will compare the time periods with the highest connection rates in the last 30 days, the last 7 days, and the last day, using coefficients of 0.5, 0.3, and 0.2 to obtain the maximum value, and the corresponding time period will be defined as the customer's active time.

[0064] Among them, the system consists of the following modules: prediction model module, number pool module, location model module, number selection model module and outbound call module;

[0065] Prediction model module: used to establish a customer active period prediction model to predict the period with the highest customer connection rate.

[0066] Number pool module: stores a large number of numbers and intelligently selects the number with the highest connection rate based on the historical connection rate ranking.

[0067] Location model module: calculates the location information of the visible number.

[0068] Number selection model module: executes the place of origin mode, the provincial capital city mode, the other cities in the province mode and the business city outbound call initiation mode to achieve accurate matching and multi-mode switching.

[0069] Outbound call module: receives information pushed by the number selection model and performs calling operations.

[0070] Among them, the prediction model module is built using big data and machine learning technology, and uses big data matching technology to find the place of origin and bind customers with external numbers in real time.

[0071] Among them, the number pool module intelligently selects the number with the highest connection rate based on the historical connection rate ranking.

[0072] Among them, the number selection model module also includes a logic control unit for switching different number selection modes.

[0073] The system also includes a database module for storing customer information and call data.

[0074] The present invention realizes a system and method that fully utilizes AI capabilities and big data model algorithms to improve the connection rate. By reducing customer churn and calling customers during periods with high connection rates, the conversion rate can be effectively improved. The number selection model adopts multiple strategies and executes them one by one according to priority to prevent customers from rejecting calls due to out-of-town numbers.

[0075] 1. Use AI technology to predict the customers who have been connected to determine the time period with the highest outbound call connection rate.

[0076] 2. During the time period with the highest outbound call connection rate, the local number model is used to select the number with the highest connection rate from the preset number pool, and big data matching technology is used to find customers who match the number's location.

[0077] 3. Call the found customer and record the call result (such as connected or not connected).

[0078] 4. If there are still customers who have not been connected after a round of calls, the provincial capital number model is used to continue to select numbers with the highest connection rate from the number pool, and find eligible customers to call.

[0079] 5. If there are still customers who have not been connected, use other numbers in the province of origin to continue selecting customers to call.

[0080] 6. Finally, use the business location number to make follow-up calls to all customers whose outbound calls failed.

[0081] By implementing the outbound call system and method provided by the present invention, the outbound call connection rate can be significantly improved, thereby effectively improving customer satisfaction and business results. At the same time, the use of multiple strategies for number selection and calling can minimize the possibility of customers rejecting calls due to out-of-town numbers and reduce customer churn.

[0082] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for improving the outbound call connection rate, characterized by: The specific steps of the method for improving the outbound call connection rate are as follows: Step 1: Setting the outbound call time period and customer active time The outbound call module uses the prediction model to calculate the time period with the highest customer connection rate, and sets this time period as the customer active time; within this set customer active time window, the outbound call module executes the outbound call initiation instruction; Step 2: Number selection and location calculation After receiving the outbound call instruction, the number pool module selects the number with the highest connection rate according to the historical connection rate ranking; pushes the selected number to the location model to calculate the location of the external number; Step 3: Number selection model and location model execution The calculated location information is pushed to the number selection model. In the number selection model, the location mode is first executed, that is, finding customers whose location is consistent with the displayed number; Step 4: Customer matching and call execution If a customer with the same location is matched, the customer and the external number are bound; the bound information is pushed to the outbound call system to complete the call; steps 3 to 4 are repeated until no more qualified customers are matched; Step 5: Switch the number selection mode to the visible provincial capital city mode After the outbound call is completed using the home location mode, the outbound call system checks whether there are any customers that have not been called; if there are any remaining customers, the number selection model is switched to the external number provincial capital city mode; steps 3 to 4 are repeated until no customers can be matched; Step 6: Switch the number selection mode to the external number display mode for other cities in the province After the outbound call in the provincial capital city mode is completed, the outbound call system checks again whether there are any customers who have not been called; if there are any remaining customers, the number selection model is switched to the other cities in the province mode of the external number; steps 3 to 4 are repeated until no customers can be matched; Step 7: Use the business city to initiate an outbound call mode If there are still remaining customers after going through all the above modes, the outbound calling mode is initiated in the business city; steps 3 to 4 are executed repeatedly until all customers have been called.

2. A method for improving the outbound call connection rate according to claim 1, characterized in that: This method is divided into four modes, namely: the place of origin mode, the provincial capital city mode, the other cities in the province mode and the business city initiating outbound call mode; the four modes are executed in sequence.

3. A method for improving outbound call connection rate according to claim 1, characterized in that: The step 4 specifically includes three steps: binding external display, initiating an outbound call and successful outbound call, and they are executed one by one in sequence.

4. The method for improving the outbound call connection rate according to claim 1, characterized in that: Calculating the location of the visible number in step 2 specifically includes: obtaining the first 7 digits of the mobile phone number according to the mobile phone number, matching the location in the number pool module through the first 7 digits, and obtaining the city and province to which the customer belongs; If it does not exist, the location city is obtained based on the customer's IP. If the location city does not exist, the location of the visible number is located according to the city recorded. If it does not exist, a visible number with a high connection rate is randomly selected.

5. A method for improving outbound call connection rate according to claim 1, characterized in that: The outbound call time period and customer active time setting in step 1 also include: if the customer exists in the system, setting the time period of answering calls in the historical portrait as the customer active time; If the customer does not exist in the system, the system will compare the time periods with the highest connection rates in the last 30 days, the last 7 days, and the last day, using coefficients of 0.5, 0.3, and 0.2 to obtain the maximum value, and the corresponding time period will be defined as the customer's active time.

6. A system for improving the outbound call connection rate, characterized in that: The system consists of the following modules: prediction model module, number pool module, location model module, number selection model module and outbound call module; Prediction model module: used to establish a customer active period prediction model to predict the period with the highest customer connection rate; Number pool module: stores a large number of numbers and intelligently selects the number with the highest connection rate based on the historical connection rate ranking; Location model module: calculates the location information of the visible number; Number selection model module: executes the home location mode, the external number provincial capital city mode, the external number other city mode and the business city initiating outbound call mode to achieve accurate matching and multi-mode switching; Outbound call module: receives information pushed by the number selection model and performs calling operations.

7. A system for improving outbound call connection rate according to claim 6, characterized in that: The prediction model module is established using big data and machine learning technology, and uses big data matching technology to find the place of origin and bind the customer to the external number in real time.

8. A system for improving outbound call connection rate according to claim 6, characterized in that: The number pool module intelligently selects the number with the highest connection rate according to the historical connection rate ranking.

9. A system for improving outbound call connection rate according to claim 6, characterized in that: The number selection model module also includes a logic control unit for switching different number selection modes.

10. A system for improving outbound call connection rate according to claim 6, characterized in that: The system also includes a database module for storing customer information and call data.

Images