Data selection method, device, equipment and medium based on quantitative model

Abstract

The embodiment of the present application provides a data selection method, device, equipment and medium based on a quantitative model, the method comprising: establishing a quantitative model; wherein the quantitative model comprises an age quantitative model and a connection quantitative model; optimizing the quantitative model based on a set strategy; obtaining outbound call leads, processing the outbound call leads based on the quantitative model, and obtaining a selection package in combination with business needs; wherein the outbound call leads include age characteristics and whether there is a connection feature in history; obtaining a call list based on the selection package, and making an outbound call; making full use of the age characteristics and whether there is a connection feature in history in the outbound call leads, processing to obtain a selection package for making an outbound call, effectively utilizing resources, making daily premiums easier to control, and improving business efficiency and the economic benefits of outbound calls.

Description

Technical Field

[0001] The present application relates to the technical field of outbound call processing, and in particular to a data selection method, device, equipment and medium based on a quantitative model. Background Art

[0002] In the insurance industry, outbound calls use the development of big data and machine learning technology, and quantitative models are introduced to optimize the selection process of outbound call targets, aiming to improve the connection rate and conversion rate by analyzing the customer's historical data. Although the quantitative model has brought a certain degree of optimization to the outbound call system, the existing technology has failed to fully utilize specific factors in customer data to improve business efficiency, resulting in a waste of resources and reducing the economic benefits of outbound calls. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a data selection method, device, equipment and medium based on a quantitative model, so as to solve the problem that the current outbound call quantitative model fails to fully utilize specific factors in customer data to improve business efficiency, resulting in waste of resources and reducing the economic benefits of outbound calls.

[0004] In a first aspect, an embodiment of the present application provides a data selection method based on a quantitative model, comprising:

[0005] Establishing a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model;

[0006] Optimize the quantitative model based on the set strategy;

[0007] Obtain outbound call leads, process them based on the quantitative model, and obtain the circle selection package based on business needs; among them, the outbound call leads include age characteristics and whether there are historical connection characteristics;

[0008] Get the call list based on the circle selection package and make an outbound call.

[0009] In the above implementation process, a quantitative model is established; wherein the quantitative model includes an age quantitative model and a connection quantitative model; the quantitative model is optimized based on the set strategy; outbound call leads are obtained, and the outbound call leads are processed based on the quantitative model, and a circle selection package is obtained in combination with business needs; wherein the outbound call leads include age characteristics and whether there is a connection feature in the past; a call list is obtained based on the circle selection package, and outbound calls are made; the age characteristics and whether there is a connection feature in the outbound call leads are fully utilized, and the circle selection package is processed to make outbound calls, so as to effectively use resources, make daily premiums easier to control, and improve business efficiency and the economic benefits of outbound calls.

[0010] Furthermore, the optimization of the quantitative model based on the set strategy includes:

[0011] Optimize the age quantification model based on age characteristics;

[0012] The connection quantification model is optimized based on whether there are connection characteristics in history.

[0013] In the above implementation process, the quantification model is optimized using age characteristics and connection characteristics, so that the quantification model can quantify the outbound call leads.

[0014] Furthermore, the obtaining of outbound call leads and processing of the outbound call leads based on the quantitative model include:

[0015] Obtain outbound call leads and divide them into several lead lists based on age characteristics and whether they have been connected in the past;

[0016] Scoring several clue lists based on the quantitative model to obtain corresponding clue list scores;

[0017] According to the lead list and the lead list score, the premium parameters of the lead list are obtained.

[0018] In the above implementation process, the age characteristics and connection characteristics are used to process the outbound call clues to facilitate the subsequent selection.

[0019] Furthermore, the premium parameters of the clue list are obtained according to the clue list and the clue list score, including:

[0020] According to the age characteristics of each clue list, the preset average parameter is obtained, where the average parameter is the average premium generated by each policy corresponding to each age group;

[0021] Based on historical experience, the connection rate of each clue list is calculated;

[0022] Calculate the APL corresponding to a positive ROI in a single lead list based on the outbound call cost; ROI is the return on investment, and APL is the average revenue of a single list;

[0023] The connection conversion rate is calculated based on the average number of calls, connection rate, APL and lead list score of a single lead list.

[0024] In the above implementation process, the premium parameters of each lead list are obtained to facilitate the selection of the lead list according to business needs.

[0025] Furthermore, the connection conversion rate is calculated based on the average number of calls, connection rate, APL and clue list score of a single clue list, including:

[0026] Multiply the average number of calls, connection rate, APL and lead list score of a single lead list to get the connection conversion rate.

[0027] Furthermore, the circle selection package obtained by combining business requirements includes:

[0028] Obtain premium targets for business needs;

[0029] According to the premium target, combined with the premium parameters and the number of leads in the lead list, the lead list is circled to obtain a circled package.

[0030] In the above implementation process, a selection package is obtained according to the premium target, so that outbound calls can be made according to the list of the selection package.

[0031] Furthermore, the list of leads is circled according to the premium target, in combination with the premium parameters and the number of the list of leads, to obtain a circled package, including:

[0032] Sort several lists of clues;

[0033] Based on the premium parameters of the lead list and the number of lists, calculate the premium of each lead list in turn;

[0034] The list of leads is arranged and combined to obtain the circled package so that the sum of the premiums of the combined list of leads is not less than the premium target.

[0035] In the above implementation process, according to the premium target, the list of leads is arranged and combined to obtain the circled package, which effectively utilizes resources, makes daily premiums easier to control, and improves business efficiency and the economic benefits of outbound calls.

[0036] Furthermore, the outbound call leads are divided into several lead lists based on age characteristics and whether there are historical connection characteristics, including:

[0037] Each age feature is combined with each historical connection feature, and all combination results are integrated to obtain several clue lists.

[0038] In the above implementation process, the clue list is divided so that the premiums generated by the clue lists can be calculated to obtain the circle selection package that meets the needs.

[0039] In a second aspect, an embodiment of the present application provides a data selection device based on a quantitative model, comprising:

[0040] A model building module is used to build a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model;

[0041] Model optimization module, used to optimize the quantitative model based on the set strategy;

[0042] The circle selection operation module is used to obtain outbound call leads, process the outbound call leads based on the quantitative model, and obtain the circle selection package based on business needs;

[0043] The outbound call operation module is used to obtain a call list based on the circle selection package and make an outbound call.

[0044] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0045] A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, they are used to implement the data selection method based on the quantitative model as described above.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a server, the data selection method based on the quantitative model as described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flowchart of a data selection method based on a quantitative model provided in an embodiment of the present application;

[0049] Figure 2 It is a structural schematic diagram of a data selection device based on a quantitative model provided in an embodiment of the present application;

[0050] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0052] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0053] Please see Figure 1 , Figure 1A flowchart of a data selection method based on a quantitative model provided in an embodiment of the present application. The data selection method based on a quantitative model includes:

[0054] 100. Establish a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model.

[0055] It is understandable that in order to ensure that the insurance business can produce premiums in a stable and controllable manner, it is necessary to circle and make outbound calls based on quantified leads according to strategies.

[0056] Among them, the two factors that have the greatest impact on the premium of daily outbound call cases are age and connection rate. The premiums purchased by people of different ages vary greatly, and the premiums with connection rates that differ by several times also vary greatly. The embodiment of the present application divides the quantitative models into: age quantitative model and connection quantitative model for the above two factors.

[0057] 200. Optimize the quantitative model based on the set strategy.

[0058] Specifically, the age quantification model is optimized according to the age characteristics; the connection quantification model is optimized according to whether there are connection characteristics in history; thus, the quantification model is optimized using the age characteristics and the connection characteristics, so that the quantification model can quantify the outbound call leads.

[0059] Among them, age characteristics can be divided into young age, middle age and old age; for example, according to the insurance products sold, the age is divided into the following age groups: young age 21-35, middle age 36-50, and old age 51-70.

[0060] Among them, the connection characteristics can be divided into historical connections and historical disconnections. According to whether the user has connected in the past, the circled time zone is divided into historical connections and historical disconnections. The connection rate of disconnections is generally more than 5 times that of connections.

[0061] 300. Obtain outbound call leads, process the outbound call leads based on the quantitative model, and obtain the circle selection package based on business needs; among which, the outbound call leads include age characteristics and historical connection characteristics.

[0062] 310. Obtain outbound call leads, and divide the outbound call leads into several lead lists based on age characteristics and whether there are historical connection characteristics.

[0063] Specifically, each age feature is combined with each historical connection feature, and all combination results are combined to obtain several clue lists; thus, the clue lists are divided, and the premiums generated by each clue list can be calculated to obtain a circle selection package that meets the needs.

[0064] Exemplarily, the clue list includes: a low-age historical connected list, a low-age historical unconnected list, a middle-age historical connected list, a middle-age historical unconnected list, an old-age historical connected list and an old-age historical unconnected list.

[0065] 320. Scoring several clue lists respectively based on the quantitative model to obtain corresponding clue list scores.

[0066] It should be noted that the quantitative model is trained based on historical data. Therefore, the quantitative model can score the clue list separately to obtain the corresponding clue list score.

[0067] For example, the scoring score for the younger historically unconnected list is 0.3 points, and the scoring score for the older historically connected list is 0.8 points.

[0068] 330. According to the clue list and the clue list score, the premium parameters of the clue list are obtained.

[0069] 331. According to the age characteristics of each clue list, obtain the preset average parameter, where the average parameter is the average premium generated by each insurance policy corresponding to each age group.

[0070] It should be noted that the average parameter is the average of products for each age group, that is, the average premium generated by each policy. For example, 1,000 policies generate 1,500,000 premiums, and the average parameter = 1,500,000 / 1,000 = 1,500.

[0071] 332. Based on historical experience, calculate the connection rate of each clue list.

[0072] It should be noted that the connection rate = connected list / outbound call list. For example, if 100 people are called out and 50 are answered, the connection rate is: 50 / 100 = 0.5.

[0073] Optionally, the connection rate of each current lead list can be automatically or manually calculated based on analyzing the historical connection rate of each lead list.

[0074] 333. Calculate the APL corresponding to a positive ROI in a single lead list based on the outbound call cost; where ROI is the return on investment, and APL is the average revenue value of a single list.

[0075] It should be noted that ROI measures the return on investment, ROI = (revenue - cost) / cost, and is used in business to measure whether calling a list of cases is profitable. Understandably, ROI is dynamic and can be monitored and adjusted periodically.

[0076] It should be noted that APL is the capacity of the connected list, APL = premium generated by the connected list / the number of connected lists, that is, the average income of a single list; for example, 1 million list cases were issued, 500,000 were connected after outbound calls, and 500,000 premiums were generated after the purchase of insurance among the 500,000 connected list, then, premium generated by the connected list / the number of connected lists = 1; if with the optimization of the quantitative model, the quantitative model selects 300,000 connected lists to generate 450,000 premiums, the connected list capacity will increase to 45 / 30=1.5.

[0077] 334. The connection conversion rate is calculated based on the average number of calls, connection rate, APL and lead list score of a single lead list.

[0078] It should be noted that the connection conversion rate = sold policies / connection list.

[0079] Optionally, the four parameters of average number of calls, connection rate, APL and lead list score of a single lead list are multiplied to obtain the connection conversion rate.

[0080] 340. Obtain premium targets for business needs.

[0081] 350. Based on the premium target, combined with the premium parameters and the number of clues in the clue list, the clue list is circled to obtain a circled package.

[0082] 351. Sort several lists of clues.

[0083] 352. Based on the premium parameters of the clue list and the number of lists, calculate the premium of each clue list in turn.

[0084] 353. Arrange and combine the clue list to obtain the circled package so that the sum of the premiums of the combined clue list is not less than the premium target.

[0085] Thus, according to the premium target, the list of leads is arranged and combined to obtain the circled package, which effectively utilizes resources, makes daily premiums easier to control, and improves business efficiency and the economic benefits of outbound calls.

[0086] For example, assuming that 1 million premiums need to be generated every day, to ensure APL1, a call list of 1 million is required. According to the daily premium target of 1 million and the available case volume, a circle selection package is made by permutations and combinations.

[0087] The average fee for younger people is 700 yuan, for middle-aged people is 1,500 yuan, and for older people is 2,800 yuan.

[0088] Historical call list for low-age people: call conversion rate 0.0014, call rate 0.2, 2 million outbound call lists are required, 400,000 call lists can be generated, and the premium generated is: 392,000 yuan.

[0089] List of low-age people with a history of not being connected: the connection conversion rate is 0.0014, the connection rate is 0.04, 1 million outbound call lists are required, 40,000 connection lists can be generated, and the premium generated is: 39,200 yuan.

[0090] Historical call list for middle-aged people: call conversion rate 0.0006, call rate 0.2, 1.5 million outbound call lists are required, 300,000 call lists can be generated, and the premium generated is: 270,000 yuan.

[0091] List of middle-aged people who have not been connected in the past: the connection conversion rate is 0.0006, the connection rate is 0.04, 1 million outbound call lists are required, 40,000 connection lists can be generated, and the premium generated is: 36,000 yuan.

[0092] Historical call list for the elderly: call conversion rate 0.00035, call rate 0.2, requiring 1.2 million outbound call lists, which can generate 240,000 call lists, generating premiums of 235,200 yuan.

[0093] List of elderly people with a history of missed calls: the call conversion rate is 0.00035, the call rate is 0.04, 1 million outbound call lists are required, 40,000 call lists can be generated, and the premium generated is: 39,200 yuan.

[0094] The combination of circle selection packages can generate premiums:

[0095] 392000+39200+270000+36000+235200+39200=1011600 yuan.

[0096] Therefore, the following lists need to be issued: list of young people with historical connections: 2 million; list of young people with historical non-connections: 1 million; list of middle-aged people with historical connections: 1.5 million; list of middle-aged people with historical non-connections: 1 million; list of old people with historical connections: 1.2 million; list of old people with historical non-connections: 1 million.

[0097] It is understandable that if it is found during the issuance process that there are only 1 million usable data in the database of the low-age historical connection list, then other types of data must be supplemented as long as the corresponding premium is sufficient.

[0098] 400. Obtain a call list based on the circle selection package and make an outbound call.

[0099] As described above, the embodiment of the present application establishes a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model; the quantitative model is optimized based on a set strategy; outbound call leads are obtained, the outbound call leads are processed based on the quantitative model, and a circle selection package is obtained in combination with business needs; wherein the outbound call leads include age characteristics and whether there is a connection feature in the history; a call list is obtained based on the circle selection package, and an outbound call is made; the age characteristics and whether there is a connection feature in the history of the outbound call leads are fully utilized, and the circle selection package is processed to make an outbound call, so as to effectively utilize resources, make daily premiums easier to control, and improve business efficiency and the economic benefits of outbound calls.

[0100] The above steps are not to be performed in a strict order as described in the numbers, but should be understood as an overall solution.

[0101] In the second aspect, based on the above embodiments, Figure 2 A schematic diagram of the structure of a data selection device based on a quantitative model provided in an embodiment of the present application. Figure 2 The data selection device based on the quantitative model provided in this embodiment specifically includes: a model building module 201, a model optimization module 202, a selection operation module 203 and an outbound call operation module 204.

[0102] Among them, the model building module 201 is used to establish a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model; the model optimization module 202 is used to optimize the quantitative model based on the set strategy; the circle selection operation module 203 is used to obtain outbound call leads, process the outbound call leads based on the quantitative model, and obtain the circle selection package based on business needs; the outbound call operation module 204 is used to obtain a call list based on the circle selection package and make an outbound call.

[0103] As described above, the embodiment of the present application establishes a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model; the quantitative model is optimized based on a set strategy; outbound call leads are obtained, the outbound call leads are processed based on the quantitative model, and a circle selection package is obtained in combination with business needs; wherein the outbound call leads include age characteristics and whether there is a connection feature in the history; a call list is obtained based on the circle selection package, and an outbound call is made; the age characteristics and whether there is a connection feature in the history of the outbound call leads are fully utilized, and the circle selection package is processed to make an outbound call, so as to effectively utilize resources, make daily premiums easier to control, and improve business efficiency and the economic benefits of outbound calls.

[0104] The data selection device based on the quantitative model provided in the embodiment of the present application can be used to execute the data selection method based on the quantitative model provided in the above embodiment, and has corresponding functions and beneficial effects.

[0105] In a third aspect, an embodiment of the present application further provides an electronic device, which can integrate the data selection device based on the quantitative model provided in an embodiment of the present application. Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 The electronic device includes: an input device 33, an output device 34, a memory 32 and one or more processors 31; the memory 32 is used to store one or more programs; when the one or more programs are executed by the one or more processors 31, the one or more processors 31 implement the data selection method based on the quantitative model provided in the above embodiment. The input device 33, the output device 34, the memory 32 and the processor 31 can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0106] The processor 31 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 32, that is, implements the above-mentioned data selection method based on the quantitative model.

[0107] The electronic device provided above can be used to execute the data selection method based on the quantitative model provided in the above embodiment, and has corresponding functions and beneficial effects.

[0108] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the data selection method based on the quantitative model as described above, and can achieve the same beneficial effects as above.

[0109] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present application is not limited to the data selection method based on the quantitative model as described above, and can also execute related operations in the data selection method based on the quantitative model provided in any embodiment of the present application.

[0110] In a fifth aspect, the embodiments of the present application also provide a computer program product, and the methods described in the various embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the various embodiments of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model) or other programmable device.

[0111] The computer program or instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disk; it may also be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0112] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a 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 flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0114] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0115] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0117] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A data selection method based on a quantitative model, characterized in that: The method comprises: Establishing a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model; Optimize the quantitative model based on the set strategy; Obtain outbound call leads, process them based on the quantitative model, and obtain the circle selection package based on business needs; among them, the outbound call leads include age characteristics and whether there are historical connection characteristics; Get the call list based on the circle selection package and make an outbound call.

2. The data selection method based on the quantitative model according to claim 1, characterized in that: The optimizing of the quantitative model based on the set strategy includes: Optimize the age quantification model based on age characteristics; The connection quantification model is optimized based on whether there are connection characteristics in history.

3. The data selection method based on the quantitative model according to claim 1, characterized in that: The obtaining of outbound call leads and processing of the outbound call leads based on the quantitative model include: Obtain outbound call leads and divide them into several lead lists based on age characteristics and whether they have been connected in the past; Scoring several clue lists based on the quantitative model to obtain corresponding clue list scores; According to the lead list and the lead list score, the premium parameters of the lead list are obtained.

4. The data selection method based on the quantitative model according to claim 3, characterized in that: The premium parameters of the clue list are obtained according to the clue list and the clue list score, including: According to the age characteristics of each clue list, the preset average parameter is obtained, where the average parameter is the average premium generated by each policy corresponding to each age group; Based on historical experience, the connection rate of each clue list is calculated; Calculate the APL corresponding to a positive ROI in a single lead list based on the outbound call cost; ROI is the return on investment, and APL is the average revenue of a single list; The connection conversion rate is calculated based on the average number of calls, connection rate, APL and lead list score of a single lead list.

5. The data selection method based on the quantitative model according to claim 4, characterized in that: The connection conversion rate is calculated based on the average number of cases, connection rate, APL and clue list score of a single clue list, including: Multiply the average number of calls, connection rate, APL and lead list score of a single lead list to get the connection conversion rate.

6. The data selection method based on quantitative model according to claim 3, characterized in that: The selected package obtained by combining business requirements includes: Obtain premium targets for business needs; According to the premium target, combined with the premium parameters and the number of leads in the lead list, the lead list is circled to obtain a circled package.

7. The data selection method based on quantitative model according to claim 6, characterized in that: According to the premium target, combined with the premium parameters and the number of the clue list, the clue list is circled to obtain a circle selection package, including: Sort several lists of clues; Based on the premium parameters of the lead list and the number of lists, calculate the premium of each lead list in turn; The list of leads is arranged and combined to obtain the circled package so that the sum of the premiums of the combined list of leads is not less than the premium target.

8. The data selection method based on quantitative model according to claim 3, characterized in that: The outbound call leads are divided into several lead lists based on age characteristics and whether there are historical connection characteristics, including: Combine each age feature with each historical connection feature, and integrate all the combination results to obtain several clue lists.

9. A data selection device based on a quantitative model, characterized in that: include: A model building module is used to build a quantitative model; wherein the quantitative model includes an age quantitative model and a connection quantitative model; Model optimization module, used to optimize the quantitative model based on the set strategy; The circle selection operation module is used to obtain outbound call leads, process the outbound call leads based on the quantitative model, and obtain the circle selection package based on business needs; among them, the outbound call leads include age characteristics and whether there are historical connection characteristics; The outbound call operation module is used to obtain a call list based on the circle selection package and make an outbound call.

10. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the processor is connected to the memory via the bus, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method for selecting data based on a quantitative model according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a server, implements the quantitative model-based data selection method as described in any one of claims 1 to 8.

Images