Control method, device and system for outbound marketing process

Abstract

The present disclosure relates to a method, device and system for controlling an outbound marketing process, the method comprising: predicting a designated customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training a model based on the outbound marketing data of existing outbound customers; obtaining a list of target customers to be marketed and corresponding customer types based on the prediction result; for each target customer in the target customer list, when the customer type of the target customer is a first type, triggering an automatic outbound calling terminal to perform outbound marketing processing on the target customer; and when the customer type of the target customer is a second type, triggering a manual outbound calling terminal to perform outbound marketing processing on the target customer.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and more specifically, to a method, device, and system for controlling an outbound marketing process. Background Art

[0002] Outbound marketing is a fast, convenient and efficient marketing method. Companies can expand and maintain customers through outbound marketing in order to increase corporate benefits.

[0003] At present, considering that outbound marketing by manual agents usually has the characteristics of low efficiency and high labor costs, some companies choose to use automatic outbound calling terminals for outbound marketing.

[0004] However, the analysis and judgment capabilities of the automatic outbound calling terminal when conducting outbound marketing are relatively limited, resulting in poor marketing results. Summary of the invention

[0005] One purpose of the embodiments of the present disclosure is to provide a new technical solution for controlling the outbound marketing process.

[0006] According to a first aspect of the present disclosure, a method for controlling an outbound marketing process is provided, comprising: predicting a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training a model based on the outbound marketing data of existing outbound customers; obtaining a list of target customers to be marketed and the corresponding customer types based on the prediction result; for each target customer in the target customer list, when the customer type of the target customer is a first type, triggering an automatic outbound terminal to perform outbound marketing processing on the target customer; and when the customer type of the target customer is a second type, triggering a manual outbound terminal to perform outbound marketing processing on the target customer.

[0007] Optionally, the method further includes: acquiring marketing record data of each target customer; and optimizing the target model according to the marketing record data of each target customer.

[0008] Optionally, obtaining the marketing record data of each target customer includes: when the customer type is the first type and the automatic outbound calling terminal has not transferred the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving first marketing record data sent by the automatic outbound calling terminal; using the first marketing record data as the marketing record data of the target customer; wherein, the first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing of the target customer.

[0009] Optionally, obtaining the marketing record data of each target customer includes: when the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving second marketing record data sent by the automatic outbound calling terminal, and receiving third marketing record data sent by the manual outbound calling terminal; using the second marketing record data and the third marketing record data as the marketing record data of the target customer; wherein the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through performing outbound marketing processing on the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

[0010] Optionally, obtaining the marketing record data of each target customer includes: when the customer type is the second type, receiving fourth marketing record data sent by the manual outbound calling terminal; using the fourth marketing record data as the marketing record data of the target customer; wherein the fourth marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

[0011] Optionally, the method further comprises: obtaining marketing result data of each target customer;

[0012] The target model is optimized based on the marketing record data of each target customer, including: optimizing the target model based on the outbound marketing data of each target customer; wherein the outbound marketing data of the target customer includes: the customer data, marketing record data and marketing result data of the target customer.

[0013] Optionally, the outbound marketing data of the outbound customer includes: customer data of the outbound customer, marketing record data and marketing result data.

[0014] Optionally, the marketing record data includes at least one of: whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

[0015] Optionally, the marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

[0016] Optionally, predicting the specified customer data set through the target model to obtain a prediction result includes: for each target customer in the specified customer data set, scoring the marketing probability of the target customer based on the customer data of the target customer through the target model, and obtaining a first marketing probability value of the target customer as the prediction result.

[0017] Optionally, obtaining a list of target customers to be marketed and corresponding customer types based on the prediction results includes: obtaining a list of target customers to be marketed, the target customer list including the target customer; comparing a first threshold and a first marketing probability value of the target customer, wherein the first threshold is obtained based on the numerical size distribution of a first marketing probability value set, the first marketing probability value set including the first marketing probability value of the target customer and the first marketing probability values ​​of other customers in the target customer list; when the first marketing probability value of the target customer is less than the first threshold, obtaining the customer type of the target customer as the first type; and when the first marketing probability value of the target customer is not less than the first threshold, obtaining the customer type of the target customer as the second type.

[0018] Optionally, the method further includes: establishing a user portrait database based on the outbound marketing data of the outbound customers; obtaining a preset adjustment rule;

[0019] The method of obtaining a list of target customers to be marketed and corresponding customer types based on the prediction results includes: obtaining a list of target customers to be marketed, the list of target customers including the target customers; adjusting a first marketing probability value of the target customers based on the adjustment rules and the user portrait database to obtain a second marketing probability value of the target customers; and obtaining the customer type of the target customers based on the second marketing probability value of the target customers.

[0020] Optionally, obtaining the customer type of the target customer based on the second marketing probability value of the target customer includes: comparing a second threshold and the second marketing probability value of the target customer, wherein the second threshold is obtained based on the numerical size distribution of a second marketing probability value set, the second marketing probability value set including the second marketing probability value of the target customer and second marketing probability values ​​of other customers in the target customer list; when the second marketing probability value of the target customer is less than the second threshold, obtaining the customer type of the target customer as the first type; and when the second marketing probability value of the target customer is not less than the second threshold, obtaining the customer type of the target customer as the second type.

[0021] Optionally, before predicting the designated customer data set through the target model, it also includes: performing machine learning training based on the outbound marketing data of outbound customers according to a preset machine learning algorithm to obtain the target model.

[0022] Optionally, the machine learning algorithm includes an LR algorithm.

[0023] According to the second aspect of the present disclosure, there is also provided a control device for an outbound marketing process, including: a prediction module, used to predict a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by model training based on the outbound marketing data of existing outbound customers; a first processing module, used to obtain a list of target customers to be marketed and the corresponding customer types based on the prediction result; a second processing module, used to, for each target customer in the target customer list, trigger an automatic outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is a first type; and trigger a manual outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is a second type.

[0024] Optionally, the device further comprises: an optimization module, configured to obtain marketing record data of each target customer; and optimize the target model according to the marketing record data of each target customer.

[0025] Optionally, the optimization module is used to receive first marketing record data sent by the automatic outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal has not transferred the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the first marketing record data as the marketing record data of the target customer; wherein the first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing of the target customer.

[0026] Optionally, the optimization module is used to receive second marketing record data sent by the automatic outbound calling terminal and third marketing record data sent by the manual outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the second marketing record data and the third marketing record data as the marketing record data of the target customer; wherein the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through performing outbound marketing processing on the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

[0027] Optionally, the optimization module is used to receive fourth marketing record data sent by the manual outbound call end when the customer type is the second type; and use the fourth marketing record data as the marketing record data of the target customer; wherein the fourth marketing record data is the marketing record data obtained by the manual outbound call end through outbound marketing processing for the target customer.

[0028] Optionally, the optimization module is used to obtain marketing result data of each target customer; and optimize the target model according to the outbound marketing data of each target customer; wherein the outbound marketing data of the target customer includes: customer data, marketing record data and marketing result data of the target customer.

[0029] Optionally, the outbound marketing data of the outbound customer includes: customer data of the outbound customer, marketing record data and marketing result data.

[0030] Optionally, the marketing record data includes at least one of: whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

[0031] Optionally, the marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

[0032] Optionally, the prediction module is used to score the marketing probability of each target customer in the specified customer data set according to the customer data of the target customer through a target model, and obtain a first marketing probability value of the target customer as a prediction result.

[0033] Optionally, the first processing module is used to obtain a list of target customers to be marketed, the target customer list including the target customer; compare a first threshold value with a first marketing probability value of the target customer, wherein the first threshold value is obtained based on the numerical size distribution of a first marketing probability value set, the first marketing probability value set including the first marketing probability value of the target customer and the first marketing probability values ​​of other customers in the target customer list; when the first marketing probability value of the target customer is less than the first threshold value, the customer type of the target customer is the first type; when the first marketing probability value of the target customer is not less than the first threshold value, the customer type of the target customer is the second type.

[0034] Optionally, the first processing module is used to establish a user portrait database based on the outbound marketing data of the outbound customers; obtain pre-set adjustment rules; obtain a list of target customers to be marketed, the target customer list including the target customer; adjust the first marketing probability value of the target customer according to the adjustment rules and the user portrait database to obtain the second marketing probability value of the target customer; obtain the customer type of the target customer according to the second marketing probability value of the target customer.

[0035] Optionally, the first processing module is used to compare a second threshold value and a second marketing probability value of the target customer, wherein the second threshold value is obtained based on the numerical size distribution of a second marketing probability value set, and the second marketing probability value set includes the second marketing probability value of the target customer and the second marketing probability values ​​of other customers in the target customer list; when the second marketing probability value of the target customer is less than the second threshold value, the customer type of the target customer is the first type; when the second marketing probability value of the target customer is not less than the second threshold value, the customer type of the target customer is the second type.

[0036] Optionally, the device also includes: a model training module, which is used to perform machine learning training based on the outbound marketing data of outbound customers according to a preset machine learning algorithm to obtain the target model.

[0037] Optionally, the machine learning algorithm includes an LR algorithm.

[0038] According to a third aspect of the present disclosure, a system comprising at least one computing device and at least one storage device is also provided, wherein the at least one storage device is used to store instructions, and when the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute the method according to the first aspect of the present disclosure.

[0039] According to the fourth aspect of the present disclosure, a control system for an outbound marketing process is also provided, comprising: a control device for the outbound marketing process as described in any one of the first aspect of the present disclosure, an automatic outbound terminal and a manual outbound terminal; wherein the automatic outbound terminal is used to be triggered by the control device of the outbound marketing process to perform outbound marketing processing on the target customers specified by the control device of the outbound marketing process; the manual outbound terminal is used to be triggered by the control device of the outbound marketing process to perform outbound marketing processing on the target customers specified by the control device of the outbound marketing process.

[0040] Optionally, the automatic outbound calling terminal is used to be triggered by the control device of the outbound marketing process, and to perform outbound marketing processing on the target customers specified by the control device of the outbound marketing process according to a preset outbound marketing processing process;

[0041] The outbound marketing processing flow includes: asking questions according to pre-set questions to obtain the customer's answers to the questions; scoring the answers according to the preset scoring rules to obtain the marketing intention value; calculating the marketing intention cumulative value according to the marketing intention value; comparing the marketing intention cumulative value with a pre-set marketing intention threshold; and sending a transfer request to the manual outbound call terminal when the marketing intention cumulative value is not less than the marketing intention threshold;

[0042] The artificial outbound call terminal is used to execute a preset corresponding process in response to the transfer request.

[0043] Optionally, the automatic outbound calling terminal includes an AI robot.

[0044] According to a fifth aspect of the present disclosure, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0045] One beneficial effect of the disclosed embodiment is that a target model is used to predict a designated customer data set to obtain a prediction result, wherein the target model is a model obtained by training a model based on the outbound marketing data of outbound customers; based on the prediction result, a list of target customers to be marketed and the corresponding customer types are obtained; for each target customer in the target customer list, when the customer type of the target customer is the first type, the automatic outbound call terminal is triggered to perform outbound marketing processing on the target customer; and when the customer type of the target customer is the second type, the manual outbound call terminal is triggered to perform outbound marketing processing on the target customer. By adopting different outbound marketing processing methods for different types of customers, the outbound marketing processing is more targeted, thereby improving the marketing effect.

[0046] Other features and advantages of the embodiments of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the embodiments of the present disclosure.

[0048] Figure 1 is a schematic diagram of the hardware structure of an electronic device to which the method embodiment of the present invention can be applied;

[0049] Figure 2 is a flowchart of a method for controlling an outbound marketing process according to an embodiment;

[0050] Figure 3 is a flowchart of a method for controlling an outbound marketing process according to another embodiment;

[0051] Figure 4 is a block diagram of a control device for an outbound marketing process according to an embodiment;

[0052] Figure 5 is a schematic diagram of the hardware structure of a control device for an outbound marketing process according to an embodiment;

[0053] Figure 6 It is a block diagram of a control system for an outbound marketing process according to one embodiment. DETAILED DESCRIPTION

[0054] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0055] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0056] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0057] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0058] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0059] One application scenario of the disclosed embodiment is controlling the outbound marketing process.

[0060] During the implementation process, the inventors found that when only the automatic outbound calling terminal is used for outbound marketing, the automatic outbound calling terminal has limited analytical and judgment capabilities during outbound marketing, resulting in poor marketing results. For example, the automatic outbound calling terminal can only mechanically judge and identify the customer's willingness based on the preset model, and cannot conduct in-depth analysis of customers who refuse on the surface, and timely adjust the marketing strategy based on the reasons for customer refusal to conduct retention marketing.

[0061] In response to the technical problems existing in the above implementation methods, the inventors have proposed a control method for an outbound marketing process, which predicts a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training a model based on the outbound marketing data of outbound customers; based on the prediction result, a list of target customers to be marketed and the corresponding customer types are obtained; for each target customer in the target customer list, when the customer type of the target customer is the first type, the automatic outbound terminal is triggered to perform outbound marketing processing on the target customer; and when the customer type of the target customer is the second type, the manual outbound terminal is triggered to perform outbound marketing processing on the target customer. This method adopts different outbound marketing processing methods for different types of customers, making the outbound marketing processing more targeted, thereby improving the marketing effect.

[0062] <Hardware Configuration>

[0063] Figure 1 1 is a schematic diagram of the hardware structure of an electronic device 1000 to which the method embodiment of the present invention can be applied. The electronic device 1000 can be applied to the scenario of controlling the outbound marketing process.

[0064] The electronic device 1000 can be a smart phone, a portable computer, a desktop computer, a tablet computer, a server, etc., which is not limited here.

[0065] like Figure 1 As shown, the hardware configuration of the electronic device 1000 may include but is not limited to a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. Among them, the processor 1100 may be a central processing unit CPU, a graphics processing unit GPU, a microprocessor MCU, etc., for executing a computer program, and the computer program may be written in an instruction set of an architecture such as x86, Arm, RISC, MIPS, SSE, etc. The memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 1300 may include, for example, a USB interface, a serial interface, a parallel interface, etc. The communication device 1400 may, for example, be capable of performing wired communication using an optical fiber or a cable, or performing wireless communication, and may specifically include WiFi communication, Bluetooth communication, 2G / 3G / 4G / 5G communication, etc. The display device 1500 may be, for example, a liquid crystal display screen, a touch display screen, and the like. The input device 1600 may include, for example, a touch screen, a keyboard, a somatosensory input, etc. The user may input / output voice information through the speaker 1700 and the microphone 1800 .

[0066] As used in the embodiments of the present disclosure, the memory 1200 of the electronic device 1000 is used to store instructions, and the instructions are used to control the processor 1100 to operate to support the control method of the outbound marketing process according to any embodiment of the present disclosure. Technicians can design instructions according to the scheme disclosed in the present disclosure. How instructions control the processor to operate is well known in the art, so it will not be described in detail here. The electronic device 1000 can be installed with an intelligent operating system (such as Windows, Linux, Android, IOS, etc.) and application software.

[0067] It should be understood by those skilled in the art that although Figure 1 1 shows multiple devices of the electronic device 1000, but the electronic device 1000 of the embodiment of the present disclosure may only involve some of the devices, for example, only the processor 1100 and the memory 1200. This is well known in the art and will not be described in detail here.

[0068] Hereinafter, various embodiments and examples according to the present invention are described with reference to the accompanying drawings.

[0069] <Method Example>

[0070] Figure 2 1 is a flow chart of a method for controlling an outbound marketing process according to an embodiment. Figure 1 The electronic device 1000 shown in FIG.

[0071] like Figure 2 As shown, the control method of the outbound marketing process of this embodiment may include the following steps S201 to S203:

[0072] Step S201, predicting a designated customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training the model based on the outbound marketing data of outbound customers.

[0073] In detail, the product of outbound marketing can be any product that can be marketed, such as bank credit cards, etc.

[0074] Specifically, the designated customer data set may include customer data of target customers to be marketed, and then the outbound call type of the corresponding target customer may be predicted based on the customer data to obtain a prediction result. For example, based on the prediction result, it may be determined whether the outbound call marketing process for the target customer is to be performed by an automatic outbound call terminal or a manual outbound call terminal.

[0075] In this embodiment, a target model is obtained by training the outbound marketing data of existing outbound customers, and then the outbound call type of the customer to be marketed is predicted based on the target model, which can ensure good prediction accuracy. For example, for a customer who has successfully marketed among existing outbound customers, if the customer data of a customer to be marketed is the same or similar to his customer data, then the outbound call type of the customer to be marketed is preferably processed by a manual outbound call terminal for outbound marketing, otherwise it can be processed by an automatic outbound call terminal. In this way, it can be ensured that customers with a higher probability of successful marketing are served by the manual outbound call terminal, and customers with a lower probability of successful marketing are served by the automatic outbound call terminal, so as to fully utilize the labor costs and improve the efficiency of outbound marketing.

[0076] Based on this, in one embodiment of the present disclosure, the outbound marketing data of the outbound customer includes: customer data of the outbound customer, marketing record data and marketing result data.

[0077] In this embodiment, the marketing record data and marketing result data can reflect the marketing success probability of the corresponding customers to a certain extent. The marketing success probability can correspond to the corresponding customer data, and combined with the customer data of the customers to be marketed, the marketing success probability of the customers to be marketed can be predicted.

[0078] In one embodiment of the present disclosure, the marketing record data includes at least one of: whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

[0079] Specifically, the marketing record data can be obtained based on the specific processing results of the outbound marketing processing for the customer. The marketing record data can reflect the marketing success probability of the corresponding customer to a certain extent.

[0080] In one embodiment of the present disclosure, the marketing result data includes: data used to identify the success of product marketing, or data used to identify the failure of product marketing. The marketing result data can directly reflect the marketing success probability of the corresponding customer.

[0081] Based on the above content, in one embodiment of the present disclosure, in the above step S201, the specified customer data set is predicted by the target model to obtain a prediction result, including: for the customer data of each target customer in the specified customer data set, the marketing probability of the target customer is scored according to the customer data of the target customer by the target model, and a first marketing probability value of the target customer is obtained as the prediction result.

[0082] Generally, the larger the marketing probability value, the more likely the corresponding customer is to be successfully marketed, and vice versa. In this embodiment, the first marketing probability value is used as the prediction result, and the customer type of the corresponding customer to be marketed can be determined accordingly.

[0083] In one embodiment of the present disclosure, before predicting the specified customer data set through the target model, it also includes: performing machine learning training based on the outbound marketing data of outbound customers according to a preset machine learning algorithm to obtain the target model.

[0084] In one embodiment of the present disclosure, the machine learning algorithm includes an LR algorithm.

[0085] For example, taking bank credit card outbound marketing as an example, the electronic device 1000 can use the marketing records of successful bank card applications within 10 days after initiating outbound marketing to users as positive samples based on the credit card outbound marketing record data, and vice versa as negative samples, and use the LR algorithm to train the model in combination with the user's basic attribute data, user AUM (Asset Under Management) data, user bank card transaction behavior data, user behavior data on the use of mobile banking apps, credit card product attribute data and other data.

[0086] In the above step S201, after predicting the designated customer data set through the target model and obtaining the prediction result, the following step S202 can be executed.

[0087] Step S202, obtaining a list of target customers to be marketed and corresponding customer types according to the prediction results.

[0088] Specifically, the designated customer data set may include customer data of target customers to be marketed, so these target customers may form a list of target customers to be marketed. Further, for each target customer on the list, its customer type may be determined according to its prediction result.

[0089] For example, after using the trained model to score marketing customers, you can sort them by marketing probability to get a sorted customer list.

[0090] Corresponding to the above implementation method of using the first marketing probability value as the prediction result, in one embodiment of the present disclosure, the step S202, obtaining a list of target customers to be marketed and corresponding customer types according to the prediction result, includes the following steps A1 to A2:

[0091] Step A1, obtaining a target customer list to be marketed, wherein the target customer list includes the target customers.

[0092] As mentioned above, the target customer list may list the target customers corresponding to each item of customer data in the above-mentioned designated customer data set.

[0093] Step A2: comparing the first threshold value with the first marketing probability value of the target customer.

[0094] In detail, the first threshold is obtained according to the numerical size distribution of the first marketing probability value set, and the first marketing probability value set includes the first marketing probability value of the target customer and the first marketing probability values ​​of other customers in the target customer list.

[0095] In this embodiment, the first threshold is obtained according to the numerical distribution of the first marketing probability value of each target customer in the list. Compared with setting the first threshold on demand based on historical experience, the method for obtaining the first threshold provided in this embodiment helps to obtain a more accurate and targeted threshold.

[0096] Based on the above content, after comparison, when the first marketing probability value of the target customer is less than the first threshold, the customer type of the target customer is the first type. When the first marketing probability value of the target customer is not less than the first threshold, the customer type of the target customer is the second type.

[0097] Preferably, the first type may correspond to a situation of automatic outbound calling, and the second type may correspond to a situation of manual outbound calling.

[0098] In this embodiment, the first threshold value obtained according to the distribution of marketing probability values ​​corresponding to all target customers can ensure an expected balance between the manual outbound call ratio and the automatic outbound call ratio, avoid too many or too few manual outbound calls, and ensure full utilization of labor costs.

[0099] Based on the implementation method described in steps A1 to A2 above, it can be known that after scoring the marketing probability of the target customer according to the customer data of the target customer through the target model to obtain the first marketing probability value of the target customer, the customer type of the target customer can be directly determined based on the first marketing probability value.

[0100] Based on this, in order to further improve the accuracy of judging the customer type, the first marketing probability value may be further optimized to obtain a second marketing probability value, and then the customer type of the target customer may be determined according to the second marketing probability value.

[0101] Based on this, in one embodiment of the present disclosure, in order to illustrate a possible implementation method of optimizing the first marketing probability value, the method also includes: establishing a user portrait database based on the outbound marketing data of the outbound customers; and obtaining pre-set adjustment rules.

[0102] Specifically, a user portrait database can be established based on the customer data, marketing record data, and marketing result data of each outbound customer, and then the first marketing probability value can be adjusted and optimized based on the user portrait database. Specifically, the adjustment and optimization can be performed based on the adjustment rules set on demand.

[0103] For example, a user portrait database can be established based on analysis of sample features, user transaction data, bank credit card marketing records and other data output by the target model. At the same time, adjustment rules compiled based on the domain knowledge of the bank's internal business experts can be used to adjust the above-mentioned sorted customer list, thereby forming a final list sorted by the probability of marketing success.

[0104] Correspondingly, the step S202, based on the prediction result, obtains a list of target customers to be marketed and corresponding customer types, including the following steps B1 to B3:

[0105] Step B1, obtaining a list of target customers to be marketed, wherein the list of target customers includes the target customers.

[0106] As mentioned above, the target customer list may list the target customers corresponding to each item of customer data in the above-mentioned designated customer data set.

[0107] Step B2: adjusting the first marketing probability value of the target customer according to the adjustment rule and the user portrait database to obtain the second marketing probability value of the target customer.

[0108] In this step, based on the above-mentioned user portrait database, the first marketing probability value is adjusted and optimized by adjusting the rules, so that the second marketing probability value obtained after adjustment is usually closer to the actual marketing result than the first marketing probability value, thereby determining a more accurate customer type.

[0109] Step B3: obtaining the customer type of the target customer according to the second marketing probability value of the target customer.

[0110] In this step, the customer type of the target customer is determined based on the adjusted second marketing probability value. As described above, the customer type can be determined based on the numerical comparison between the second marketing probability value and the corresponding second threshold value, and the second threshold value can be determined specifically based on the distribution of each second marketing probability value.

[0111] Based on the above content, in one embodiment of the present disclosure, the step B3, obtaining the customer type of the target customer according to the second marketing probability value of the target customer, includes: comparing the second threshold value and the second marketing probability value of the target customer.

[0112] In detail, the second threshold is obtained according to the numerical size distribution of the second marketing probability value set, and the second marketing probability value set includes the second marketing probability value of the target customer and the second marketing probability values ​​of other customers in the target customer list.

[0113] Based on the above content, after comparison, when the second marketing probability value of the target customer is less than the second threshold, the customer type of the target customer is the first type. When the second marketing probability value of the target customer is not less than the second threshold, the customer type of the target customer is the second type.

[0114] As described above, the first type may correspond to the case of automatic outbound calls, and the second type may correspond to the case of manual outbound calls.

[0115] In the above step S202, after obtaining the target customer list and the corresponding customer type according to the prediction result, the following step S203 can be executed to perform corresponding outbound marketing processing on the target customer according to the customer type corresponding to each target customer in the list.

[0116] Step S203, for each target customer in the target customer list, when the customer type of the target customer is the first type, triggering the automatic outbound calling terminal to perform outbound marketing processing on the target customer; and when the customer type of the target customer is the second type, triggering the manual outbound calling terminal to perform outbound marketing processing on the target customer.

[0117] In detail, when the customer type is the first type, the automatic outbound calling terminal performs outbound marketing processing on the corresponding target customer, and when the customer type is the second type, the manual outbound calling terminal performs outbound marketing processing on the corresponding target customer.

[0118] For example, if the automatic outbound calling end is an AI robot, for example, the marketing list can be distributed and processed through the marketing management system. For long-tail customers of the first type, outbound calls are made through the AI ​​robot. For head customers of the second type, follow-up marketing is directly carried out by human agents. Through the combination of AI robots and human agents, the overall marketing efficiency is improved.

[0119] As can be seen from the above, the disclosed embodiment provides a control method for an outbound marketing process, which predicts a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training a model based on the outbound marketing data of outbound customers; based on the prediction result, a list of target customers to be marketed and the corresponding customer types are obtained; for each target customer in the target customer list, when the customer type of the target customer is the first type, the automatic outbound terminal is triggered to perform outbound marketing processing on the target customer; and when the customer type of the target customer is the second type, the manual outbound terminal is triggered to perform outbound marketing processing on the target customer. This method adopts different outbound marketing processing methods for different types of customers, making the outbound marketing processing more targeted, thereby improving the marketing effect. Based on this, the problem of poor marketing effect caused by only using the automatic outbound terminal for outbound marketing can be solved.

[0120] In detail, after the automatic outbound call terminal and the manual outbound call terminal perform outbound marketing processing, corresponding marketing record data can be generated, and the electronic device 1000 can obtain the marketing record data for optimization of the target model. Based on the optimized target model, a more accurate prediction result can be obtained by predicting the specified customer data set, so that the outbound marketing processing is more targeted and the marketing effect is better.

[0121] Based on this, in one embodiment of the present disclosure, after the above step S203, the method further includes the following steps C1 to C2.

[0122] Step C1, obtaining marketing record data of each target customer.

[0123] In this embodiment, the outbound marketing process is performed by the automatic outbound calling terminal or the manual outbound calling terminal, so the marketing record data can be obtained from the automatic outbound calling terminal or the manual outbound calling terminal. The specific acquisition situations may include at least the following three situations:

[0124] Case 1: The automatic outbound calling terminal conducts outbound marketing for target customers and is not transferred to the manual outbound calling terminal. In this case, the automatic outbound calling terminal provides corresponding marketing record data;

[0125] Case 2: The automatic outbound calling terminal conducts outbound marketing for target customers and transfers the call to the manual outbound calling terminal. In this case, the automatic outbound calling terminal and the manual outbound calling terminal provide corresponding marketing record data;

[0126] Case 3: The manual outbound calling terminal conducts outbound marketing to target customers. In this case, the manual outbound calling terminal provides corresponding marketing record data.

[0127] In detail, for the above situation 1:

[0128] In one embodiment of the present disclosure, obtaining the marketing record data of each target customer includes: when the customer type is the first type and the automatic outbound calling terminal has not transferred the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving the first marketing record data sent by the automatic outbound calling terminal; and using the first marketing record data as the marketing record data of the target customer.

[0129] The first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through performing outbound marketing processing on the target customer.

[0130] In detail, during or after the automatic outbound calling terminal performs outbound marketing to the target customers, corresponding marketing record data can be generated. As mentioned above, the marketing record data may include at least one of whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset questions, and whether the outbound marketing is successful.

[0131] In detail, for the above situation 2:

[0132] In one embodiment of the present disclosure, obtaining the marketing record data of each target customer includes: when the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving second marketing record data sent by the automatic outbound calling terminal and receiving third marketing record data sent by the manual outbound calling terminal; using the second marketing record data and the third marketing record data as the marketing record data of the target customer.

[0133] Among them, the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through outbound marketing processing for the target customer.

[0134] In this embodiment, the automatic outbound call terminal can perform outbound marketing processing on the target customers specified by the control device of the outbound marketing process according to the preset outbound marketing processing process. The outbound marketing processing process may include: asking questions according to preset questions and obtaining the customer's answers to the questions; scoring the answers according to the preset scoring rules to obtain the marketing intention value; calculating the marketing intention cumulative value according to the marketing intention value; comparing the marketing intention cumulative value with the preset marketing intention threshold; and sending a transfer request to the manual outbound call terminal when the marketing intention cumulative value is not less than the marketing intention threshold. Then, the manual outbound call terminal responds to the transfer request and performs the preset corresponding processing.

[0135] In this embodiment, the automatic outbound calling terminal makes a preliminary estimate of the marketing intention of the target customer based on the accumulated marketing intention value of the target customer. If it is considered that the marketing intention is strong but the automatic outbound calling terminal is usually unable to carry out in-depth and flexible marketing processing for the target customer and needs to be retained by the business personnel, the call is promptly transferred to the manual outbound calling terminal, which then continues to carry out outbound marketing processing for the target customer. Based on this, the problem of poor marketing effect caused by only using the automatic outbound calling terminal for outbound marketing can be solved.

[0136] In this embodiment, in addition to the automatic outbound calling terminal, the manual outbound calling terminal can also generate corresponding marketing record data during or after the outbound marketing processing for the target customers. The marketing record data can also include at least one of whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset questions, and whether the outbound marketing is successful.

[0137] In detail, these data can be generated by the processing module of the manual outbound call end according to the outbound marketing processing results, or they can be obtained in conjunction with the input information of the business personnel.

[0138] In detail, for the above situation 3:

[0139] In one embodiment of the present disclosure, obtaining the marketing record data of each target customer includes: when the customer type is the second type, receiving fourth marketing record data sent by the manual outbound call terminal; and using the fourth marketing record data as the marketing record data of the target customer.

[0140] Among them, the fourth marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

[0141] In this embodiment, as described above, the manual outbound calling terminal may generate corresponding marketing record data during or after the outbound marketing process for the target customer.

[0142] Step C2: optimizing the target model according to the marketing record data of each target customer.

[0143] As mentioned above, the target model can be obtained by training the model based on the outbound marketing data of the outbound customers. Based on this, when optimizing the target model, the target model can be optimized based on the outbound marketing data of each target customer, specifically based on the customer data, marketing record data and marketing result data of each target customer.

[0144] Based on this, in one embodiment of the present disclosure, after the above step C1, the method further includes: acquiring marketing result data of each target customer.

[0145] In detail, after the automatic outbound calling terminal and / or the manual outbound calling terminal performs outbound marketing processing on a target customer, the marketing result of the target customer can be obtained as marketing result data. As mentioned above, the marketing result data can include data for identifying successful product marketing or data for identifying failed product marketing.

[0146] Correspondingly, the step C2 optimizes the target model according to the marketing record data of each target customer, including: optimizing the target model according to the outbound marketing data of each target customer.

[0147] The target customer's outbound marketing data includes: the target customer's customer data, marketing record data and marketing result data. The data composition of the target customer's outbound marketing data may be consistent with the data composition of the outbound marketing data of the outbound customers.

[0148] For example, the customer marketing records of automatic outbound call terminals and manual outbound call terminals (for example, marketing record data includes outbound call time, whether the call was connected, the score of the customer's answer to preset questions, whether the marketing was successful, etc.) can be summarized and imported into the machine learning algorithm self-learning module to continuously improve the model effect, and ultimately further improve marketing efficiency.

[0149] Based on the above content, the control method of the outbound marketing process provided by the embodiment of the present disclosure can at least have the following features:

[0150] (1) Use machine learning algorithms to achieve accurate matching of customers and products and improve the marketing efficiency of AI robot outbound calls.

[0151] (2) Through the collaboration between AI robots and human agents, marketing efficiency is improved and the manpower input cost of human agents is reduced.

[0152] (3) Iterate and optimize the model through recording the marketing process to improve the model's predictive accuracy.

[0153] Figure 3 A flow chart of a method for controlling an outbound marketing process according to an embodiment is given. Figure 1 The electronic device 1000 shown is taken as an example as an implementation subject to illustrate the control method of the outbound marketing process of this embodiment.

[0154] like Figure 3 As shown, the method of this embodiment may include the following steps S301 to S311:

[0155] Step S301, performing machine learning training based on the outbound marketing data of outbound customers according to the LR algorithm to obtain the target model, wherein the outbound marketing data of the outbound customers includes the customer data, marketing record data and marketing result data of the outbound customers.

[0156] Step S302, for the customer data of each target customer in the specified customer data set, the target model is used to score the marketing probability of the target customer according to the customer data of the target customer, and a first marketing probability value of the target customer is obtained as a prediction result.

[0157] Step S303, obtaining a list of target customers to be marketed, wherein the list of target customers includes the target customers.

[0158] Step S304, obtaining a first threshold value according to the numerical distribution of the first marketing probability value set, wherein the first marketing probability value set includes the first marketing probability value of the target customer and the first marketing probability values ​​of other customers in the target customer list.

[0159] Step S305, comparing the first threshold and the first marketing probability value of the target customer. When the first marketing probability value of the target customer is less than the first threshold, the customer type of the target customer is obtained as the first type and step S306 is executed. When the first marketing probability value of the target customer is not less than the first threshold, the customer type of the target customer is obtained as the second type and step S309 is executed.

[0160] Step S306, triggering the automatic outbound calling terminal to perform outbound marketing processing on the target customer, and executing step S307 or step S308.

[0161] Step S307, when the automatic outbound calling terminal does not transfer the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving the first marketing record data sent by the automatic outbound calling terminal; using the first marketing record data as the marketing record data of the target customer, and executing step S311.

[0162] The first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through performing outbound marketing processing on the target customer.

[0163] Step S308, when the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving the second marketing record data sent by the automatic outbound calling terminal and receiving the third marketing record data sent by the manual outbound calling terminal; using the second marketing record data and the third marketing record data as the marketing record data of the target customer.

[0164] Among them, the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through outbound marketing processing for the target customer.

[0165] Step S309, triggering the manual outbound calling terminal to perform outbound marketing processing on the target customer, and executing step S310.

[0166] Step S310, when the customer type is the second type, receiving fourth marketing record data sent by the manual outbound calling terminal; and using the fourth marketing record data as the marketing record data of the target customer.

[0167] Among them, the fourth marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

[0168] Step S311, obtaining marketing result data of each target customer; optimizing the target model according to the outbound marketing data of each target customer, wherein the outbound marketing data of the target customer includes the customer data, marketing record data and marketing result data of the target customer.

[0169] The marketing record data includes at least one of: whether the contact number is empty, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

[0170] The marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

[0171] In this embodiment, the target model is trained based on the outbound marketing data of the outbound customers, and the customer data of the target customers to be marketed in the list are predicted based on the target model to obtain the corresponding marketing probability value. Then, the marketing type of each target customer is determined based on the distribution of the marketing probability value of each target customer and the corresponding marketing treatment is performed. Then, the target model is optimized based on the marketing results. Based on this control method for the outbound marketing process, not only can the full utilization of labor costs be improved, but also the efficiency of outbound marketing can be improved.

[0172] <Equipment Embodiment>

[0173] Figure 4 FIG. 4 is a block diagram of a control device 400 for an outbound marketing process according to an embodiment. Figure 4As shown, the control device 400 of the outbound marketing process may include a prediction module 401, a first processing module 402, and a second processing module 403. The control device 400 of the outbound marketing process may be Figure 1 An electronic device 1000 is provided.

[0174] Among them, the prediction module 401 predicts the specified customer data set through the target model to obtain the prediction result, and the target model is a model obtained by model training based on the outbound marketing data of outbound customers. The first processing module 402 obtains the target customer list and the corresponding customer type to be marketed according to the prediction result. For each target customer in the target customer list, the second processing module 403 triggers the automatic outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is the first type; and triggers the manual outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is the second type.

[0175] In one embodiment of the present disclosure, the control device 400 of the outbound marketing process further includes an optimization module. The optimization module obtains the marketing record data of each target customer and optimizes the target model according to the marketing record data of each target customer.

[0176] In one embodiment of the present disclosure, the optimization module is used to receive first marketing record data sent by the automatic outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal has not transferred the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the first marketing record data as the marketing record data of the target customer; wherein the first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer.

[0177] In one embodiment of the present disclosure, the optimization module is used to receive second marketing record data sent by the automatic outbound calling terminal and third marketing record data sent by the manual outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the second marketing record data and the third marketing record data as the marketing record data of the target customer; wherein the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through outbound marketing processing for the target customer.

[0178] In one embodiment of the present disclosure, the optimization module is used to receive fourth marketing record data sent by the manual outbound calling terminal when the customer type is the second type; and use the fourth marketing record data as the marketing record data of the target customer; wherein the fourth marketing record data is the marketing record data obtained by the manual outbound calling terminal by performing outbound marketing processing on the target customer.

[0179] In one embodiment of the present disclosure, the optimization module is used to obtain marketing result data of each target customer; based on the outbound marketing data of each target customer, the target model is optimized; wherein the outbound marketing data of the target customer includes: customer data, marketing record data and marketing result data of the target customer.

[0180] In one embodiment of the present disclosure, the outbound marketing data of the outbound customer includes: customer data of the outbound customer, marketing record data and marketing result data.

[0181] In one embodiment of the present disclosure, the marketing record data includes at least one of: whether the contact number is invalid, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

[0182] In one embodiment of the present disclosure, the marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

[0183] In one embodiment of the present disclosure, the prediction module 401 is used to score the marketing probability of each target customer in the specified customer data set according to the customer data of the target customer through a target model, and obtain a first marketing probability value of the target customer as a prediction result.

[0184] In one embodiment of the present disclosure, the first processing module 402 is used to obtain a list of target customers to be marketed, the target customer list including the target customer; compare a first threshold value with a first marketing probability value of the target customer, wherein the first threshold value is obtained according to the numerical size distribution of a first marketing probability value set, the first marketing probability value set including the first marketing probability value of the target customer and the first marketing probability values ​​of other customers in the target customer list; when the first marketing probability value of the target customer is less than the first threshold value, the customer type of the target customer is the first type; when the first marketing probability value of the target customer is not less than the first threshold value, the customer type of the target customer is the second type.

[0185] In one embodiment of the present disclosure, the first processing module 402 is used to establish a user portrait database based on the outbound marketing data of the outbound customers; obtain pre-set adjustment rules; obtain a list of target customers to be marketed, the target customer list including the target customer; according to the adjustment rules and the user portrait database, adjust the first marketing probability value of the target customer to obtain the second marketing probability value of the target customer; according to the second marketing probability value of the target customer, obtain the customer type of the target customer.

[0186] In one embodiment of the present disclosure, the first processing module 402 is used to compare a second threshold value and a second marketing probability value of the target customer, wherein the second threshold value is obtained based on the numerical size distribution of a second marketing probability value set, and the second marketing probability value set includes the second marketing probability value of the target customer and the second marketing probability values ​​of other customers in the target customer list; when the second marketing probability value of the target customer is less than the second threshold value, the customer type of the target customer is the first type; when the second marketing probability value of the target customer is not less than the second threshold value, the customer type of the target customer is the second type.

[0187] In one embodiment of the present disclosure, the control device 400 of the outbound marketing process further includes a model training module. The model training module performs machine learning training based on the outbound marketing data of outbound customers according to a preset machine learning algorithm to obtain the target model.

[0188] In one embodiment of the present disclosure, the machine learning algorithm includes an LR algorithm.

[0189] Figure 5 FIG. 5 is a schematic diagram of the hardware structure of a control system 500 for an outbound marketing process according to another embodiment. The control system 500 for the outbound marketing process may be Figure 1 An electronic device 1000 is provided.

[0190] like Figure 5 As shown, the control system 500 of the outbound marketing process includes at least one computing device 501 and at least one storage device 502, wherein the at least one storage device 502 is used to store instructions, and when the instructions are executed by the at least one computing device 501, the at least one computing device 501 is prompted to execute a method such as any of the above method embodiments.

[0191] Each module of the control system 500 of the above outbound marketing process can be implemented by the at least one computing device 501 in this embodiment executing a computer program stored in the at least one storage device 502, or can be implemented by other circuit structures, which is not limited here.

[0192] <System Embodiment>

[0193] Figure 6 FIG. 6 is a block diagram of a control system 600 for an outbound marketing process according to an embodiment. Figure 6 As shown, the control system 600 of the outbound marketing process may include a control device 601 of the outbound marketing process, an automatic outbound calling terminal 602, and a manual outbound calling terminal 603. The control device 601 of the outbound marketing process may be the electronic device 1000, the control device 400 of the outbound marketing process, or the control device 500 of the outbound marketing process.

[0194] The automatic outbound calling terminal 602 is triggered by the control device 601 of the outbound calling marketing process, and performs outbound calling marketing processing on the target customers specified by the control device 601 of the outbound calling marketing process. The manual outbound calling terminal 603 is triggered by the control device 601 of the outbound calling marketing process, and performs outbound calling marketing processing on the target customers specified by the control device 601 of the outbound calling marketing process.

[0195] In one embodiment of the present disclosure, the automatic outbound call terminal 602 may include an ASR (Automatic Speech Recognition, automatic speech recognition technology) speech recognition module, an NLU (Natural Language Processing, natural language understanding) natural language understanding module, a TTS (Text To Speech, from text to speech) speech synthesis module, and a conversation control module based on the Aviator rule engine.

[0196] For example, the automatic outbound calling terminal 602 can conduct outbound marketing according to the preset content, and report the marketing processing results to the control device 601 of the outbound marketing process after completion. For example, the reachability is filtered and screened (the empty numbers and the user's mobile phone numbers that cannot be connected are marked), and the customer's willingness is preliminarily judged in combination with the outbound marketing situation, and the willing customers are transferred to the manual seat (i.e. the above-mentioned manual outbound calling terminal 603) in real time for follow-up marketing. For example, the above-mentioned session control module can be used to score the user's answer to each preset question. When the cumulative value reaches a certain threshold, it is determined that the customer's willingness is high and can be transferred to a manual seat, otherwise it is also marked. In addition, business personnel can view and analyze the robot AI outbound call project to improve the per capita outbound marketing customer acquisition capacity of manual seats.

[0197] Based on the above content, in one embodiment of the present disclosure, the automatic outbound calling terminal 602 is triggered by the control device 601 of the outbound marketing process, and performs outbound marketing processing on the target customer specified by the control device 601 of the outbound marketing process according to the preset outbound marketing processing process. The manual outbound calling terminal 603 responds to the transfer request and executes the preset corresponding processing.

[0198] Among them, the outbound marketing processing flow includes: asking questions according to pre-set questions to obtain customers' replies to the questions; scoring the replies according to preset scoring rules to obtain a marketing intention value; calculating a cumulative marketing intention value based on the marketing intention value; comparing the cumulative marketing intention value with a pre-set marketing intention threshold; and sending a transfer request to the manual outbound call terminal 603 when the cumulative marketing intention value is not less than the marketing intention threshold.

[0199] In one embodiment of the present disclosure, the automatic outbound calling terminal includes an AI robot.

[0200] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the embodiments of the present disclosure is implemented.

[0201] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0202] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0203] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0204] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, 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 via 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., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0205] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0206] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0207] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0208] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0209] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for controlling an outbound marketing process, comprising: Predicting a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training the model based on the outbound marketing data of outbound customers; According to the prediction results, a list of target customers to be marketed and corresponding customer types are obtained; For each target customer in the target customer list, when the customer type of the target customer is the first type, triggering the automatic outbound calling terminal to perform outbound marketing processing on the target customer; and when the customer type of the target customer is the second type, triggering the manual outbound calling terminal to perform outbound marketing processing on the target customer, The step of predicting the designated customer data set by using the target model to obtain the prediction result includes: for each target customer in the designated customer data set, scoring the marketing probability of the target customer according to the customer data of the target customer by using the target model to obtain a first marketing probability value of the target customer as the prediction result; According to the prediction results, a list of target customers to be marketed and the corresponding customer types are obtained, including: according to the adjustment rules and the user portrait database, the first marketing probability value of the target customer is adjusted to obtain the second marketing probability value of the target customer, the adjustment rules are compiled based on domain knowledge, and the user portrait database is established based on the customer data, marketing record data and marketing result data of each outbound customer; according to the second marketing probability value of the target customer, the customer type of the target customer is obtained.

2. The method according to claim 1, wherein: The method further comprises: Obtain marketing record data for each target customer; The target model is optimized according to the marketing record data of each target customer.

3. The method according to claim 2, wherein: The obtaining of marketing record data of each target customer includes: When the customer type is the first type and the automatic outbound calling terminal does not transfer the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving first marketing record data sent by the automatic outbound calling terminal; Using the first marketing record data as the marketing record data of the target customer; The first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through performing outbound marketing processing on the target customer.

4. The method according to claim 2, wherein: The obtaining of marketing record data of each target customer includes: When the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal, receiving the second marketing record data sent by the automatic outbound calling terminal, and receiving the third marketing record data sent by the manual outbound calling terminal; using the second marketing record data and the third marketing record data as marketing record data for the target customer; Among them, the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through outbound marketing processing for the target customer.

5. The method according to claim 2, wherein: The obtaining of marketing record data of each target customer includes: When the customer type is the second type, receiving fourth marketing record data sent by the manual outbound calling terminal; Using the fourth marketing record data as the marketing record data of the target customer; Among them, the fourth marketing record data is the marketing record data obtained by the manual outbound calling terminal through performing outbound marketing processing on the target customer.

6. The method according to claim 2, wherein: The method further comprises: obtaining marketing result data of each target customer; The optimizing the target model according to the marketing record data of each target customer includes: optimizing the target model according to the outbound marketing data of each target customer; The outbound marketing data of the target customer includes: customer data, marketing record data and marketing result data of the target customer.

7. The method according to claim 1, wherein: The outbound marketing data of the outbound customers includes: customer data of the outbound customers, marketing record data and marketing result data.

8. The method according to claim 6 or 7, wherein: The marketing record data includes at least one of: whether the contact number is empty, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

9. The method according to claim 6 or 7, wherein: The marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

10. The method according to claim 1, wherein: The method further includes: establishing a user portrait database based on the outbound marketing data of the outbound customers; Get pre-set adjustment rules; A target customer list to be marketed is obtained, wherein the target customer list includes the target customers.

11. The method according to claim 1, wherein: The obtaining the customer type of the target customer according to the second marketing probability value of the target customer includes: Comparing a second threshold with the second marketing probability value of the target customer, wherein the second threshold is obtained according to the numerical distribution of a second marketing probability value set, and the second marketing probability value set includes the second marketing probability value of the target customer and the second marketing probability values ​​of other customers in the target customer list; When the second marketing probability value of the target customer is less than the second threshold, obtaining the customer type of the target customer as the first type; When the second marketing probability value of the target customer is not less than the second threshold, the customer type of the target customer is obtained as the second type.

12. The method according to claim 1, wherein: Before predicting the specified customer data set by using the target model, the method further includes: According to a preset machine learning algorithm, machine learning training is performed based on the outbound marketing data of outbound customers to obtain the target model.

13. The method according to claim 12, wherein: The machine learning algorithm includes the LR algorithm.

14. A control device for an outbound marketing process, comprising: A prediction module, used to predict a specified customer data set through a target model to obtain a prediction result, wherein the target model is a model obtained by training the model based on the outbound marketing data of outbound customers; A first processing module, used to obtain a list of target customers to be marketed and corresponding customer types according to the prediction results; The second processing module is used for, for each target customer in the target customer list, triggering the automatic outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is the first type; and triggering the manual outbound calling terminal to perform outbound marketing processing on the target customer when the customer type of the target customer is the second type, The first processing module scores the marketing probability of each target customer in the specified customer data set according to the target customer's customer data through the target model, and obtains the first marketing probability value of the target customer as the prediction result. The second processing module adjusts the first marketing probability value of the target customer according to the adjustment rules and the user portrait database to obtain the second marketing probability value of the target customer. The adjustment rules are compiled based on domain knowledge, and the user portrait database is established based on the customer data, marketing record data and marketing result data of each outbound customer; based on the second marketing probability value of the target customer, the customer type of the target customer is obtained.

15. The device according to claim 14, wherein: The device also includes: The optimization module is used to obtain the marketing record data of each target customer; and optimize the target model according to the marketing record data of each target customer.

16. The device according to claim 15, wherein: The optimization module is used to receive the first marketing record data sent by the automatic outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal has not transferred the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the first marketing record data as the marketing record data of the target customer; wherein the first marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer.

17. The device according to claim 15, wherein: The optimization module is used to receive the second marketing record data sent by the automatic outbound calling terminal and the third marketing record data sent by the manual outbound calling terminal when the customer type is the first type and the automatic outbound calling terminal transfers the outbound marketing processing flow of the target customer to the manual outbound calling terminal; and use the second marketing record data and the third marketing record data as the marketing record data of the target customer; wherein the second marketing record data is the marketing record data obtained by the automatic outbound calling terminal through outbound marketing processing for the target customer, and the third marketing record data is the marketing record data obtained by the manual outbound calling terminal through outbound marketing processing for the target customer.

18. The device according to claim 15, wherein: The optimization module is used to receive the fourth marketing record data sent by the manual outbound calling end when the customer type is the second type; and use the fourth marketing record data as the marketing record data of the target customer; wherein the fourth marketing record data is the marketing record data obtained by the manual outbound calling end through outbound marketing processing for the target customer.

19. The device according to claim 15, wherein: The optimization module is used to obtain marketing result data of each target customer; The target model is optimized based on the outbound marketing data of each target customer; wherein the outbound marketing data of the target customer includes: the customer data, marketing record data and marketing result data of the target customer.

20. The device according to claim 14, wherein: The outbound marketing data of the outbound customers includes: customer data of the outbound customers, marketing record data and marketing result data.

21. The device according to claim 19 or 20, wherein: The marketing record data includes at least one of: whether the contact number is empty, whether the contact number is not connected, the duration of the outbound call, the score corresponding to the customer's answer to the preset question, and whether the outbound marketing is successful.

22. The device according to claim 19 or 20, wherein: The marketing result data includes: data used to identify successful product marketing, or data used to identify failed product marketing.

23. The device according to claim 14, wherein: The first processing module is used to establish a user portrait database based on the outbound marketing data of the outbound customers; obtain pre-set adjustment rules; and obtain a list of target customers to be marketed, wherein the target customer list includes the target customers.

24. The device according to claim 14, wherein: The first processing module is used to compare a second threshold value and a second marketing probability value of the target customer, wherein the second threshold value is obtained based on the numerical size distribution of a second marketing probability value set, and the second marketing probability value set includes the second marketing probability value of the target customer and the second marketing probability values ​​of other customers in the target customer list; when the second marketing probability value of the target customer is less than the second threshold value, the customer type of the target customer is the first type; when the second marketing probability value of the target customer is not less than the second threshold value, the customer type of the target customer is the second type.

25. The device according to claim 14, wherein: The device also includes: The model training module is used to perform machine learning training based on the outbound marketing data of outbound customers according to a preset machine learning algorithm to obtain the target model.

26. The device according to claim 25, wherein The machine learning algorithm includes the LR algorithm.

27. A system comprising at least one computing device and at least one storage device, wherein: The at least one storage device is used to store instructions, which, when executed by the at least one computing device, cause the at least one computing device to perform the method according to any one of claims 1 to 13.

28. A control system for an outbound marketing process, comprising: The control device, automatic outbound calling terminal and manual outbound calling terminal of any one of claims 14 to 26; Wherein, the automatic outbound calling terminal is used to be triggered by the control device of the outbound calling marketing process to perform outbound calling marketing processing on the target customers specified by the control device of the outbound calling marketing process; The manual outbound calling terminal is used to be triggered by the control device of the outbound calling marketing process to perform outbound calling marketing processing on the target customers designated by the control device of the outbound calling marketing process.

29. The control system for outbound marketing process according to claim 28, wherein: The automatic outbound calling terminal is used to be triggered by the control device of the outbound calling marketing process, and to perform outbound calling marketing processing on the target customers specified by the control device of the outbound calling marketing process according to a preset outbound calling marketing processing process; The outbound marketing processing flow includes: Ask questions based on pre-set questions and obtain customers' responses to the questions; Scoring the responses according to a preset scoring rule to obtain a marketing intention value; Calculate the marketing intention cumulative value according to the marketing intention value; comparing the marketing intention cumulative value with a pre-set marketing intention threshold; When the marketing intention cumulative value is not less than the marketing intention threshold, sending a transfer request to the manual outbound calling terminal; The artificial outbound call terminal is used to execute a preset corresponding process in response to the transfer request.

30. The control system for outbound marketing process according to claim 29, wherein: The automatic outbound calling terminal includes an AI robot.

31. A computer-readable storage medium storing a computer program, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 13.

Images