Customer intention identification method, device, equipment, medium and product

By analyzing customer journey data to calculate intent and allocate follow-up channels, the problem of resource waste and low conversion rate caused by an excessively large customer base was solved, achieving efficient resource utilization and improved conversion rates.

CN118941297APending Publication Date: 2024-11-12CHINA CONSTRUCTION BANK +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411055964.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In existing technologies, the customer screening process involves an excessively large customer pool, leading to wasted marketing resources and low conversion rates.

Method used

By defining target constraints, acquiring customer journey data, analyzing journey steps and participation frequency, calculating customer intent, and allocating appropriate follow-up channels based on intent.

Benefits of technology

This enabled the matching of marketing resources with high-intent customers, improving conversion rates and business metrics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941297A_ABST
    Figure CN118941297A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, in particular to a customer intention recognition method and device, equipment, a medium and a product. The method comprises the steps of determining a target customer group and a target product according to a target constraint condition; obtaining customer data of each customer in the target customer group; wherein the customer data comprises journey data of the target product; based on the journey data of each customer corresponding to the target product, determining journey ring nodes participated by each customer and journey participation times; determining the intention degree of each customer for the target product according to the journey ring node and the journey participation frequency of each customer; and based on the intention degree of each customer, determining a follow-up channel corresponding to each customer. According to the embodiment of the invention, an appropriate follow-up channel can be allocated according to the intention degree of each customer, so that the matching between marketing resources and high-intention-degree customers is realized, the conversion rate is improved, and the operating indexes are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment, medium and product for identifying customer intention. Background Art

[0002] At present, with the rapid development of the industry, the competition in the marketing market for customers is gradually intensifying. In order to improve the marketing success rate, customers who are willing to buy or use products are usually selected from the massive customer information, and appropriate marketing resources are allocated to these customers.

[0003] However, in the related art, the screening of customers is usually done by industry practitioners based on their past experience, and the final screened customer group is usually too large, resulting in a mismatch between current marketing resources and follow-up channels and the screened customer group. When the customer group is too large, it will not only lead to a waste of marketing resources, but also greatly reduce the marketing conversion rate due to the uneven actual intentions of customers. Summary of the invention

[0004] The embodiments of the present application provide a customer intention identification method, device, equipment, medium and product, which can improve the technical problem that the number of screened customers in the related technology does not match the actual marketing resources, resulting in waste of marketing resources and reduced conversion rate.

[0005] In a first aspect, an embodiment of the present application provides a method for identifying customer intentions, comprising:

[0006] Determine the target customer group and target product based on the target constraints;

[0007] Acquire customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product;

[0008] Based on the journey data corresponding to each customer and the target product, determine the journey links and journey participation times of each customer;

[0009] Determining each customer's intention for the target product according to the journey links and the number of times each customer has participated in the journey;

[0010] Based on the intention of each customer, determine the corresponding follow-up channel for each customer.

[0011] In a second aspect, an embodiment of the present application provides a device for identifying customer intentions, the device comprising:

[0012] A target determination module is used to determine the target customer group and target product according to the target constraints;

[0013] A data acquisition module, used to acquire customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product;

[0014] A journey determination module, used to determine the journey links and journey participation times of each customer based on the journey data corresponding to each customer and the target product;

[0015] An intention determination module, used to determine each customer's intention for the target product according to the journey link points and the number of times each customer has participated in the journey;

[0016] The channel allocation module is used to determine the follow-up channel corresponding to each customer based on the intention of each customer.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0018] When the processor executes the computer program instructions, the steps of the customer intention identification method in any one of the embodiments of the first aspect are implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the steps of the customer intention identification method in any one of the embodiments of the first aspect are implemented.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the instructions in the computer program product are executed by a processor, the steps of the customer intention identification method in any embodiment of the first aspect are implemented.

[0021] The customer intention identification method, device, equipment, medium and product in the embodiments of the present application can determine the target customer group and target product according to the pre-set target constraints. Based on the journey data related to the target product in the customer data of each customer in the target customer group, each journey link and the number of journey participations that can participate in the target product can be determined. The customer's intention for the target product can be calculated based on the journey link and the number of journey participations. According to the intention of each customer, a suitable follow-up channel can be assigned to each customer to achieve the matching of marketing resources with high-intention customers, improve conversion rates, and improve operating indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 It is a flowchart of a method for identifying customer intentions provided in one embodiment of the present application;

[0024] Figure 2 is a flow chart of a method for identifying customer intentions provided by another embodiment of the present application;

[0025] Figure 3 is a flowchart of a method for identifying customer intentions provided by another embodiment of the present application;

[0026] Figure 4 is a flow chart of a method for identifying customer intentions provided in yet another embodiment of the present application;

[0027] Figure 5 is a flow chart of a method for identifying customer intentions provided in yet another embodiment of the present application;

[0028] Figure 6 It is a structural schematic diagram of a customer intention identification device provided in an embodiment of the present application;

[0029] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0031] 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 statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0032] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0033] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0034] At present, with the rapid development of the industry, the competition in the marketing market for customers is gradually intensifying. In order to improve the marketing success rate, customers who are willing to buy or use products are usually selected from the massive customer information, and appropriate marketing resources are allocated to these customers.

[0035] However, in the related art, the screening of customers is usually done by industry practitioners based on their past experience, and the final screened customer group is usually too large, resulting in a mismatch between current marketing resources and follow-up channels and the screened customer group. When the customer group is too large, it will not only lead to a waste of marketing resources, but also greatly reduce the marketing conversion rate due to the uneven actual intentions of customers.

[0036] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment, medium and product for identifying customer intention.

[0037] The customer intention identification method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0038] Figure 1 Schematic diagram of a method for identifying customer intentions provided in an embodiment of the present application. Figure 1 As shown, the customer intention identification method may specifically include the following steps:

[0039] S110, determining the target customer group and target product according to the target constraint conditions;

[0040] S120, obtaining customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product;

[0041] S130, determining the journey link points and journey participation times of each customer based on the journey data corresponding to each customer and the target product;

[0042] S140, determining each customer's intention for the target product according to the journey links and journey participation times of each customer;

[0043] S150, determining a follow-up channel corresponding to each customer based on the intention of each customer.

[0044] In this embodiment, the target customer group and the target product can be determined according to the preset target constraint conditions. According to the journey data related to the target product in the customer data of each customer in the target customer group, each journey link and the number of journey participations that can participate in the target product can be determined. Based on the journey link and the number of journey participations, the customer's intention for the target product can be calculated. According to the intention of each customer, a suitable follow-up channel can be allocated to each customer to match marketing resources with high-intention customers, improve conversion rates, and improve operating indicators.

[0045] The specific implementation methods of the above steps are introduced below.

[0046] In S110, the user may set target constraints based on the current business status and operating indicators, and the device may determine the corresponding target customer group and target product according to the target constraints set by the user.

[0047] The target product may be one of the multiple products operated by the operating institution. For example, if the operating institution is a product provider, the products it operates include but are not limited to financial products, fund products, insurance products, deposit products, etc. The target product may be one of the multiple products mentioned above.

[0048] Similarly, the target customers mentioned above may be customer groups obtained by screening based on one or more characteristics. For example, the target customers may be all customers of the operating organization, customers of the operating organization who have undergone reputation testing, or customer groups consisting of customers of the operating organization that meet one or more other screening conditions.

[0049] In S120 , after the target customer group is determined, each customer included in the target customer group may be determined, and customer data of each customer may be acquired from a database.

[0050] The above customer data may include the customer's journey data in different products, that is, the customer's journey data in the target product may be determined from the customer data.

[0051] In S130, after obtaining the journey data corresponding to each customer and the target product, the journey of each customer participating in the target product can be determined based on the journey data. The journey refers to each behavior link of the customer in the entire life cycle of the target product, from seeing, holding to disappearance.

[0052] Taking the target product as a wealth management product as an example, the links included in the journey may include browsing the mobile banking wealth management page / browsing the cloud studio wealth management page / outbound calling intention, browsing wealth management product details, purchasing wealth management products, and redeeming wealth management products. Among them, browsing the mobile banking wealth management page / browsing the cloud studio wealth management page / outbound calling intention can all be used as the first journey link point in the journey, browsing the wealth management product details can be used as the second journey link point, purchasing wealth management products can be used as the third journey link point, and redeeming wealth management products can be used as the fourth journey link point.

[0053] Based on the journey data corresponding to each customer and the target product, the behavior of each customer associated with the target product within a certain period of time can be determined. For example, within the statistical period of time, if a customer's journey data includes browsing the details of financial products 3 times and purchasing fund products 2 times, based on the target product being a financial product, it can be determined that the behavior associated with the target product is browsing the details of financial products 3 times. That is, the customer participates in the second journey link of the target product, and the number of journey participations in the second journey link is 3 times.

[0054] It should be noted that a customer can participate in one or more journey links of the target product. And in each journey link, the customer can participate multiple times. For example, taking a wealth management product as an example, a customer can browse the mobile banking wealth management page 3 times, purchase a wealth management product 2 times, and redeem a wealth management product once within a certain period of time. At this time, based on the customer's journey data, it can be determined that the customer has participated in the first journey link, the third journey link, and the fourth journey link, and the number of journey participations corresponding to each journey link is 3 times, 2 times, and 1 time, respectively.

[0055] In S140, after determining the journey links and journey participation times of each customer based on the partial journey data associated with the target product in each customer's journey data, each customer's intention for the target product can be calculated based on the journey links and journey participation times of each customer.

[0056] In some embodiments, the above S130 may include:

[0057] S210, based on the journey data corresponding to each customer and the target product, determining all journey links of each customer participating in the target product and the number of journey participations corresponding to each journey link;

[0058] The above S140 may include:

[0059] S220, determining the link weights corresponding to each journey link point of the target product;

[0060] S230, calculating each customer's first intention degree for the target product according to the link weight corresponding to each journey link and the number of times each customer participates in each journey link.

[0061] In this embodiment, based on the customer's journey data for the target product, all journey links in which the customer participated and the number of journey participations corresponding to each journey link can be determined, and based on the link weight of each journey link, the first intention degree of each customer for the target product can be calculated. The first intention degree can be used as the customer's intention degree for the target product.

[0062] In S210 , after the journey data corresponding to each customer and the target product are obtained, all journey links of each customer participating in the target product and the number of journey participations corresponding to each journey link may be determined.

[0063] Taking a single customer as an example, based on the customer's journey data, we can determine each customer's behavior associated with the target product within a certain period of time. When a customer has multiple behaviors, the multiple behaviors can correspond to the same journey link or different journey links. Therefore, based on each customer's journey data, we can determine all the journey links in which each customer participates in the target product. Since a customer may have multiple behaviors in the same journey link, the number of journey participations corresponding to each journey link may be one or more.

[0064] When the target product contains multiple journey links, the customer can participate in any one or more of the journey links. For example, if the target product is a financial product, within a certain period of time, if the customer browses the mobile banking financial management page, it can be determined that the customer has participated in the first journey link; if the customer purchases the financial product, it can be determined that the customer has participated in the third journey link.

[0065] It should be noted that since the customer journey data obtained is the behavior associated with the target product within a certain period of time, if the customer has held a wealth management product before the period of time, and if the customer has redeemed the wealth management product within the period of time, but has no other behaviors related to the journey link, it can be determined that the customer only participates in the fourth journey link of the target product.

[0066] In S220, according to each journey link of the target product, the link weight corresponding to each journey link may be determined respectively. For example, if the target product includes 4 journey links, the link weights corresponding to the 4 journey links may be determined respectively.

[0067] In S230, after all journey links of each customer participating in the target product are determined, the first intention degree of each customer for the target product can be calculated according to the link weight of each journey link and the number of journey participation times of the customer participating in each journey link.

[0068] Taking the target product as a financial product as an example, if the user participates in the first journey link and the third journey link of the target product, and the number of journey participations in the first journey link is 3 times and the number of journey participations in the third journey link is 1 time, the first intention degree of the customer for the target product can be calculated by combining the link weights of the first journey link and the link weights of the third journey link.

[0069] The first intention degree mentioned above can be directly used as the customer's intention degree for the target product, or can be further calculated on the basis of the first intention degree to obtain the customer's intention degree for the target product.

[0070] In some embodiments, after the above S230, the following steps may also be included:

[0071] S240, obtaining a second intention degree calculated for each customer in a previous period;

[0072] S250, determining each customer's final intention degree for the target product based on the weight values ​​corresponding to the first intention degree and the second intention degree respectively.

[0073] In this embodiment, after calculating the first intention degree of the customer, the second intention degree calculated in the previous period can also be obtained, and the final intention degree of the customer is calculated by combining the first intention degree and the second intention degree. In the final intention degree, by adjusting the weight values ​​of the two intention degrees, the influence of the two intention degrees on the final intention degree can be adjusted, so that the calculated intention degree is more matched with the product type of the target product.

[0074] In S240, the device may also obtain the intention degree of each customer calculated in the previous period, and use the intention degree as the second intention degree.

[0075] In S250, after obtaining the first intention degree corresponding to the current period and the second intention degree corresponding to the previous period, the final intention degree of each customer for the target product can be calculated based on the weight values ​​corresponding to the first intention degree and the second intention degree respectively.

[0076] In some embodiments, the calculation formula of the final intention degree in the above embodiment includes:

[0077]

[0078] Among them, w T)is the final intention degree, j is the total number of journey links included in the target product, n is the number of journey participations corresponding to the i-th journey link and n is at least 1, is the weight value corresponding to the first intention degree; w T-1) is the second intention degree of the previous period, is the weight value corresponding to the second intention degree, d T is the weight factor.

[0079] In the above embodiment, if the journey links that the user participates in are only a part of all the journey links included in the target product, only the journey links that the user participates in and the number of times the user participates in the journey are substituted into the calculation formula of the final intention degree. For example, take the example that the customer participates in the first journey link and the third journey link of the target product, and the number of times the customer participates in the journey is 3 times and 1 time respectively. Then the first intention degree is:

[0080]

[0081] The final intention is:

[0082]

[0083] It should be noted that after the device calculates the second intention degree of the previous time period, when calculating the first intention degree of the current time period, the customer's journey data obtained is not the journey data of all time periods, but only the journey data of the current time period.

[0084] As an optional implementation, the weight factor d T It can be set based on the product type of the target product. For example, when the target product is an impulse purchase product, the weight factor d T It can be reduced so that the proportion of the first intention degree in the final intention degree increases. That is, the customer behavior in the current period has a greater impact on the final intention degree. On the contrary, if the target product is a planned consumption product, the weight factor d can be T The second intention degree is increased so that the proportion of the second intention degree in the final intention degree increases. That is, the customer behavior in the past period has a greater impact on the final intention degree.

[0085] In some other embodiments, the above S130 may include:

[0086] S310, based on the journey data corresponding to each customer and the target product, determining the last journey link point of each customer participating in the target product and the last journey participation number corresponding to the last journey link point;

[0087] The above S140 may include:

[0088] S320, determining the link weights corresponding to each journey link point of the target product;

[0089] S330, calculating each customer's third intention degree for the target product according to the link weight corresponding to the last journey link point participated by each customer and the last journey participation number of each customer participating in the last journey link point.

[0090] In this embodiment, based on the customer's journey data for the target product, the last journey link point in which the customer participated and the number of journey participations corresponding to the last journey link point can be determined, and based on the link weight of the last journey link point, the third intention degree of each customer for the target product can be calculated. The third intention degree can be used as the customer's intention degree for the target product.

[0091] In S310 , after the journey data corresponding to each customer and the target product are obtained, the last journey link point of each customer participating in the target product and the number of journey participations corresponding to the last journey link point may be determined.

[0092] When the target product includes multiple journey links, the customer can participate in any one or more of the journey links. When the customer participates in only one of the journey links, the journey link is the last journey link. When the customer participates in at least two journey links, the order of the journey links can be determined according to the pre-set order of the journey links, and the last journey link is determined therefrom.

[0093] After the last journey link is determined, the number of journey participations corresponding to the last journey link can be determined from the journey data. For example, taking the target product as a financial product, when the customer's journey data includes the behavior of browsing the details of the financial product and the behavior of purchasing the financial product, the second journey link and the third journey link of the customer's participation in the target product can be determined. According to the preset order of each journey link, the third journey link can be determined as the last journey link. By counting the number of behaviors of purchasing the financial product in the journey data, the number of journey participations corresponding to the last journey link can be determined.

[0094] In S320, according to each journey link of the target product, the link weight corresponding to each journey link may be determined respectively. For example, if the target product includes 4 journey links, the link weights corresponding to the 4 journey links may be determined respectively.

[0095] In S330 , after determining the last journey link point of each customer participating in the target product, the link weight corresponding to the last journey link point may be determined.

[0096] According to the link weight corresponding to the last journey link point and the last journey participation number of the last journey link point, the customer's third intention for the target product can be calculated.

[0097] Taking the target product as a financial product as an example, if the user has participated in the first and third journey links of the target product, and the number of journey participations in the first journey link is 3 times and the number of journey participations in the third journey link is 1 time, then the third journey link can be determined as the last journey link, and the customer's third intention for the target product can be calculated based on the link weight corresponding to the third journey link and the number of journey participations in the third journey link.

[0098] The third intention degree mentioned above can be directly used as the customer's intention degree for the target product, or can be further calculated based on the third intention degree to obtain the customer's intention degree for the target product.

[0099] In some embodiments, after the above S330, the following steps may also be included:

[0100] S340, obtaining the fourth intention degree calculated for each customer in the previous period;

[0101] S350, determining each customer's final intention degree for the target product based on the weight values ​​corresponding to the third intention degree and the fourth intention degree respectively.

[0102] In this embodiment, after calculating the third intention degree of the customer, the fourth intention degree calculated in the previous period can also be obtained, and the final intention degree of the customer is calculated by combining the third intention degree and the fourth intention degree. In the final intention degree, by adjusting the weight values ​​of the two intention degrees, the influence of the two intention degrees on the final intention degree can be adjusted, so that the calculated intention degree is more matched with the product type of the target product.

[0103] In S340, the device may also obtain the intention degree of each customer calculated in the previous period, and use the intention degree as the fourth intention degree.

[0104] In S350, after obtaining the third intention degree corresponding to the current period and the fourth intention degree corresponding to the previous period, the final intention degree of each customer for the target product can be calculated based on the weight values ​​corresponding to the third intention degree and the fourth intention degree respectively.

[0105] In some embodiments, the calculation formula of the final intention degree in the above embodiment includes:

[0106]

[0107] in, is the final intention degree, is the link weight of the last journey link, n is the number of participations in the last journey, is the weight value corresponding to the third intention degree; w n,s,T-1) is the fourth intention degree of the previous period, is the weight value corresponding to the fourth intention degree, d T is the weight factor.

[0108] In the above embodiment, it is taken that the customer participates in the first journey link point and the third journey link point of the target product, and the number of journey participation times is 3 times and 1 time respectively. Then the third intention degree is:

[0109]

[0110] The final intention is:

[0111]

[0112] It should be noted that after the device calculates the second intention degree of the previous time period, when calculating the first intention degree of the current time period, the customer's journey data obtained is not the journey data of all time periods, but only the journey data of the current time period.

[0113] In some embodiments, the above S220 or S320 may further include:

[0114] S410, determining the link weights of a portion of the journey links in the target product according to the weight configuration instruction;

[0115] S420, determining the link weights of another part of the journey link points in the target product according to the weight calculation formula; wherein, among any two journey link points of the target product, the link weight of the earlier journey link point is smaller than the link weight of the later journey link point.

[0116] In this embodiment, the user can customize the link weights of a part of the journey links through the weight configuration instructions, and for the other part of the journey links that the user has not configured, they can be automatically calculated through the weight calculation formula to obtain the link weight of each journey link in the target product.

[0117] In S410, the link weights corresponding to the various journey links of the target product may be determined by determining a portion of the journey links specified by the user in the target product and the link weights corresponding to the portion of the journey links according to a weight configuration instruction triggered by the user.

[0118] Users can customize the link weights of one or more journey links in the target product through weight configuration instructions based on the actual business type of each product.

[0119] In S420, after the user configures the link weights of some journey links in the target product through the weight configuration instruction, the link weights of the other journey links that are not configured with link weights can be calculated according to the weight calculation formula to achieve the configuration of the link weights of all journey links in the target product.

[0120] In the process of configuring link weights, it is necessary to satisfy that, among any two journey link nodes, the link weight of the earlier journey link node is smaller than the link weight of the later journey link node.

[0121] As an optional implementation, in order to satisfy that the link weight of the previous journey link point is less than the link weight of the subsequent journey link point. When the user performs custom configuration of the link weight, it is necessary to compare the link weights configured by the user. When the link weight configured by the user does not satisfy that the link weight of the previous journey link point is less than the link weight of the subsequent journey link point, the user is reminded of the abnormality so that the user can reconfigure the weight value that meets the rule.

[0122] When the user has configured weights for a part of the journey links, during the weight configuration process for the other part of the journey links, before configuring the link weight using the weight calculation formula, each journey link can determine the journey link points on both sides that are closest to the configured link weights, so that the link weight configured for the journey link is between the two link weights corresponding to the journey link points on both sides.

[0123] In some embodiments, multiple journey links of the target product are numbered in ascending order according to the order of the corresponding life cycle. The weight calculation formula includes:

[0124]

[0125] Among them, s i is the journey node, i is the number of the journey node, is the link weight of the i-th journey link node.

[0126] In the above embodiment, after the multiple journey links in the target product are numbered from small to large in the order of the life cycle, the link weight of the journey link can be calculated according to the number of each journey link, so that the link weight of the journey link with a smaller number is smaller than the link weight of the journey link with a larger number.

[0127] It should be noted that, in addition to the above-mentioned weight calculation formula, other functions that satisfy monotonically increasing within the numbering interval of the journey link nodes can be used to calculate the link weight.

[0128] As an optional implementation, when configuring the link weights of each journey link node, the link weight difference between two adjacent journey link nodes may be set to gradually increase.

[0129] In S150, after calculating each customer's intention for the target product, the follow-up channel corresponding to each customer can be determined according to the intention of each customer.

[0130] It should be noted that, since the customer data of each customer may contain journey data of multiple products, the customer's intention for each product can be calculated based on the journey data of a single customer on each product.

[0131] In some embodiments, the above S150 may include:

[0132] S510, dividing the plurality of customers into a plurality of customer groups based on the intention degree of each customer;

[0133] S520, determining a follow-up channel corresponding to each customer according to the follow-up strategy corresponding to each customer group.

[0134] In this embodiment, according to the intention degree of each customer, the customers can be divided according to the size of the intention degree to obtain multiple customer groups, and according to the follow-up strategy preset for each customer group, a suitable follow-up channel can be provided to each customer.

[0135] In S510, after calculating the intention of each customer for the target product, multiple customers can be divided into multiple customer groups based on the size of the intention.

[0136] The above customer groups can be divided based on the threshold of intention degree. For example, by setting a threshold of intention degree, a customer group with intention degree greater than the threshold and a customer group with intention degree less than the threshold can be divided, for a total of two customer groups. Similarly, by setting 2 thresholds of intention degree, three customer groups can be divided. Similarly, by setting n thresholds of intention degree, n+1 customer groups can be divided.

[0137] The above customer groups can also be divided based on customer ratios. For example, after obtaining the intention of each customer, the customers can be sorted according to the intention, and the first 50% of customers can be divided into one customer group, and the last 50% of customers can be divided into another customer group. Similarly, by setting n ratio thresholds, n+1 customer groups can be divided.

[0138] In S520, after the multiple customers are divided into customer groups, the follow-up channel corresponding to each customer can be determined according to the preset follow-up strategy corresponding to each customer group.

[0139] The above-mentioned follow-up channels include but are not limited to one-to-one follow-up, mobile banking advertising follow-up, SMS notification follow-up and intelligent outbound call follow-up.

[0140] In some embodiments, the above S520 may include:

[0141] S610, allocating a one-to-one follow-up channel to each customer in the first customer group; wherein the first customer group is the customer group with the highest average intention;

[0142] S620, providing the corresponding customer journey data to each business person in the one-to-one follow-up channel.

[0143] In this embodiment, after multiple customer groups are divided, a one-to-one follow-up channel can be assigned to the first customer group with the highest intention, and the corresponding customer journey data can be provided to the business personnel so that the business personnel can provide more accurate services to the customers based on the journey data.

[0144] In S610 , after all customers in the target customer group are divided into a plurality of customer groups, a customer group with the highest average intention degree may be determined from the plurality of customer groups as a first customer group.

[0145] For each customer in the first customer group, you can follow up the channel one-on-one to provide the customer with relevant information about the target product.

[0146] In S620 , after a one-to-one follow-up channel is allocated to each customer in the first customer group, the journey data of the corresponding customer may be provided to each business person in the one-to-one channel.

[0147] The above-mentioned journey data provided to the business personnel may be journey data associated with the target product, such as the journey links and the number of journey participation times of the journey links in which the customer participates. The journey data provided to the business personnel may also include journey data of other products, such as whether the customer participates in journeys of other products in addition to the target product, the journey links and the number of journey participation times of the customer in the journeys of other products, etc. The business personnel can provide more accurate services to the customers based on the journey data.

[0148] In some embodiments, the customer data also includes activity parameters, and after the above S120, it may also include:

[0149] S710, filtering out customers without a journey whose journey data of the target product is empty from multiple customers;

[0150] S720, screening out active customers from multiple no-trip customers according to the activity parameter of each no-trip customer;

[0151] After the above S510, the following steps may also be included:

[0152] S730, classifying the active users into a second customer group; wherein the average intention degree of the inactive users in the second customer group is lower than the average intention degree of the first customer group.

[0153] In this embodiment, after determining the target customer group, it is also possible to screen out non-travel customers who have no travel behavior for the target product. According to the active parameters of non-travel customers, customers who meet the active conditions can be determined as active customers. For active customers, they can be divided into a second customer group whose intention is lower than that of the first customer group. That is, the same follow-up strategy is adopted for active users and original customers in the second customer group.

[0154] In S710, after obtaining the customer data of each customer in the target customer group, customers whose journey data of the target product is empty can be screened out. Empty journey data indicates that the customer has not participated in any journey link of the target product. Therefore, the screened customers are customers without journeys.

[0155] In S720, since the customer data also includes the customer's activity parameter, after determining the no-trip customer from the target customer group, it is possible to determine whether the customer is an active customer based on the activity parameter of each no-trip customer. That is, based on the activity parameter of each no-trip customer, active customers can be screened out from multiple no-trip customers.

[0156] In S730 , after the active users are determined, the active users may be divided into a second customer group among the multiple customer groups.

[0157] The multiple customer groups include at least a first customer group and a second customer group, the first customer group is the customer group with the highest average intention, and the average intention of the second customer group is lower than that of the first customer group. It can be understood that since active customers are all non-trip customers, that is, active customers do not have intention. When calculating the average intention of the second customer group, the average intention of inactive users should be calculated.

[0158] As an optional implementation, after different follow-up channels are assigned to the first customer group and the second customer group respectively, if there are any remaining marketing resources, the remaining marketing resources can be allocated to the customers in the first customer group and the second customer group in turn according to the degree of customer intention until the remaining marketing resources are consumed.

[0159] In some embodiments, the above S720 may include:

[0160] S810, calculating the product coverage of each no-journey customer according to the number of products associated with each no-journey customer;

[0161] S820, obtaining the number of contacts between each non-journey customer and the product provider within a preset time period;

[0162] S830, screening out, from a plurality of no-trip customers, no-trip customers whose product coverage is greater than a first threshold or no-trip customers whose number of contacts is greater than a second threshold.

[0163] In this embodiment, the customer data of the non-journey customer includes the number of products associated with the customer and the number of contacts with the product provider within a preset time period. The customer coverage can be calculated based on the number of products associated with the customer. From the non-journey customers, customers whose product coverage or number of contacts meets the corresponding rules can be screened out as active customers.

[0164] In S810, after determining the no-journey customer, the number of products associated with the no-journey customer can be determined from the customer data. Based on the number of products associated with each no-journey customer, the product coverage of each no-journey customer can be calculated.

[0165] As an exemplary implementation, taking a single no-trip customer as an example, if the number of products associated with the no-trip customer among the m products that the product provider can provide is a, then the product coverage of the no-trip customer is a / m.

[0166] In S820, the customer data of each customer also includes the number of contacts between the customer and the product provider within a preset time period. After the non-travel customers are screened out from the target customer group, the number of contacts for each non-travel customer can be obtained.

[0167] In S830, among the multiple no-trip customers, no-trip customers whose product coverage is greater than a first threshold may be screened out as active customers, and no-trip customers whose contact times are greater than a second threshold may be screened out as active customers. That is, customers whose product coverage and contact times meet the active condition may be determined as active customers.

[0168] In some embodiments, before the above S150, the following steps may also be included:

[0169] When the journey data corresponding to any customer and the target product changes, the customer's intention degree is updated in real time according to the new journey data to obtain an updated intention degree.

[0170] In this embodiment, the device can obtain the customer data of the customer at a preset time node to calculate the customer's intention. In addition, when the journey data corresponding to any customer and the target product changes, the device can update the customer's intention in real time according to the changed new journey data to obtain an updated intention.

[0171] As an optional implementation, the device can calculate the intention of each customer with respect to each product at a preset interval. Taking a single customer as an example, after calculating the intention of the customer for a product, if the journey data of the customer corresponding to the product changes, the intention of the customer for the product can be updated in real time according to the new journey data to obtain an updated intention, and the follow-up channel corresponding to the customer is determined based on the updated intention.

[0172] In some embodiments, when the journey data of the target product in the original customer data of the customer is empty, the calculation formula of the updated intention degree is:

[0173]

[0174] in, is the intention to update, is the link weight of the unique journey link in the new journey data, n is the number of journey participations of the unique journey link, K1 is the first coefficient and K1>1.

[0175] Take a single customer as an example. When the journey data corresponding to the customer and the target product changes, if the journey data of the target product is empty in the original customer data of the customer, it means that the customer was a non-journey user for the target product before the journey data changed. That is, the customer had no intention of the corresponding target product before that.

[0176] In this case, since after the journey data changes, there is only one journey link of the target product in the new journey data, the updated intention degree can be calculated according to the link weight of the unique journey link and the number of journey participations. In addition, since when the customer's journey data changes, it means that the customer has a certain interest in the target product, the value of the real-time updated intention degree can be increased by the first coefficient to provide the customer with a more effective follow-up channel.

[0177] In some embodiments, when the journey data of the target product in the original customer data of the customer is not empty, the calculation formula of the updated intention degree is:

[0178]

[0179] in, is the intention to update, is the link weight of the last journey link in the new journey data, n is the number of journey participations at the last journey link, and w (n,s,T-1) is the intention degree of the previous period, K2 is the second coefficient and K2>1.

[0180] When the journey data corresponding to the customer and the target product changes, if the journey data of the target product in the original customer data of the customer is not empty, it means that the customer has the intention degree of the corresponding target product before. At this time, the updated intention degree can be calculated based on the intention degree calculated in the current period and the intention degree calculated in the previous period.

[0181] In the above embodiment, the intention degree of the current period can be calculated based on the last journey link in the journey data and the number of journey participations of the last journey link. In another embodiment, the intention degree of the current period can also be calculated based on each journey link in the journey data and the number of journey participations of each journey link.

[0182] It should be noted that the application scenarios described in the above-mentioned embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0183] Based on the same inventive concept, the present application also provides a customer intention identification device. Figure 6 Provide detailed explanation.

[0184] Figure 6 It is a structural diagram of a customer intention identification device 600 provided in an embodiment of the present application.

[0185] like Figure 6 As shown, the customer intention identification device 600 may include:

[0186] A target determination module 601 is used to determine a target customer group and a target product according to target constraints;

[0187] A data acquisition module 602 is used to acquire customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product;

[0188] A journey determination module 603, configured to determine the journey links and journey participation times of each customer based on the journey data corresponding to each customer and the target product;

[0189] The intention determination module 604 is used to determine the intention of each customer for the target product according to the journey link points and the number of times each customer participates in the journey;

[0190] The channel allocation module 605 is used to determine the follow-up channel corresponding to each customer based on the intention of each customer.

[0191] The customer intention identification device 600 is described in detail below, as follows:

[0192] In some embodiments, the above-mentioned journey determination module 603 may also include:

[0193] A first journey determination unit, configured to determine, based on the journey data corresponding to each customer and the target product, all journey links in which each customer participates in the target product and the number of journey participations corresponding to each journey link;

[0194] The intention determination module 604 may further include:

[0195] A link weight unit, used to determine the link weights corresponding to each journey link point of the target product;

[0196] The first intention degree calculation unit is used to calculate the first intention degree of each customer for the target product according to the link weights corresponding to each journey link and the number of journey participation times of each customer participating in each journey link.

[0197] In some embodiments, the customer intention identification device 600 may further include:

[0198] A second intention degree acquisition unit, used to acquire the second intention degree of each customer calculated in the previous period;

[0199] The first final intention degree calculation unit is used to determine the final intention degree of each customer for the target product based on the weight values ​​corresponding to the first intention degree and the second intention degree respectively.

[0200] In some embodiments, the above-mentioned journey determination module 603 may also include:

[0201] A second journey determination unit, configured to determine, based on the journey data corresponding to each customer and the target product, the last journey link point at which each customer participated in the target product and the last journey participation number corresponding to the last journey link point;

[0202] The intention determination module 604 may further include:

[0203] A link weight unit, used to determine the link weights corresponding to each journey link point of the target product;

[0204] The third intention degree of each customer for the target product is calculated according to the link weight corresponding to the last journey link point participated by each customer and the last journey participation number of each customer participating in the last journey link point.

[0205] In some embodiments, the customer intention identification device 600 may further include:

[0206] A fourth intention degree acquisition unit, used to acquire the fourth intention degree of each customer calculated in the previous period;

[0207] The second final intention degree calculation unit is used to determine the final intention degree of each customer for the target product based on the weight values ​​corresponding to the third intention degree and the fourth intention degree respectively.

[0208] The link weight unit may include:

[0209] A weight customization subunit, used to determine the link weights of a part of the journey link nodes in the target product according to the weight configuration instruction;

[0210] The weight automatic calculation subunit is used to determine the link weights of another part of the journey link points in the target product according to the weight calculation formula; wherein, among any two journey link points of the target product, the link weight of the earlier journey link point is less than the link weight of the later journey link point.

[0211] In some embodiments, the customer intention identification device 600 may further include:

[0212] The real-time updating module is used to update the intention degree of any customer in real time according to the new journey data when the journey data corresponding to the target product of any customer changes, so as to obtain the updated intention degree.

[0213] In some embodiments, the customer intention identification device 600 may further include:

[0214] Filter out customers with no journey whose journey data for the target product is empty from multiple customers;

[0215] An active screening module, used for screening active customers from multiple no-trip customers according to the activity parameter of each no-trip customer;

[0216] An active division module is used to divide the active users into a second customer group; wherein the average intention degree of the inactive users in the second customer group is lower than the average intention degree of the first customer group.

[0217] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0218] The electronic device 700 may include a processor 701 and a memory 702 storing computer program instructions.

[0219] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0220] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.

[0221] In certain embodiments, the memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.

[0222] The processor 701 implements any one of the customer intention identification methods in the above embodiments by reading and executing computer program instructions stored in the memory 702 .

[0223] In some examples, the electronic device 700 may further include a communication interface 703 and a bus 710. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 710 and communicate with each other.

[0224] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0225] Bus 710 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus 710 may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 710 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0226] Exemplarily, the electronic device 700 may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA).

[0227] The electronic device 700 can execute the customer intention identification method in the embodiment of the present application, thereby realizing the combination Figure 1 and Figure 6 A method and apparatus for identifying customer intent are described.

[0228] In addition, in combination with the customer intention identification method in the above embodiment, the embodiment of the present application may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the customer intention identification methods in the above embodiment is implemented. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0229] In addition, an embodiment of the present application also provides a computer program product, including computer instructions, which can implement the steps and corresponding contents of the aforementioned method embodiment when executed by a processor.

[0230] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0231] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0232] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0233] The above reference is according to the method of the embodiment of the present application, the flow chart of the device (system) and the computer program product and / or the block diagram described various aspects of the present application.It should be understood that each square box in the flow chart and / or the block diagram and the combination of each square box in the flow chart and / or the block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the realization of the function / action specified in one or more square boxes of the flow chart and / or the block diagram.Such a processor can be but is not limited to a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.It can also be understood that each square box in the block diagram and / or the flow chart and the combination of the square boxes in the block diagram and / or the flow chart can also be realized by the dedicated hardware that performs the specified function or action, or can be realized by the combination of dedicated hardware and computer instructions.

[0234] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for identifying customer intention, characterized in that: include: Determine the target customer group and target product based on the target constraints; Acquire customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product; Based on the journey data corresponding to each customer and the target product, determine the journey links and journey participation times of each customer; Determining each customer's intention for the target product according to the journey links and the number of times each customer has participated in the journey; Based on the intention of each customer, determine the corresponding follow-up channel for each customer.

2. The method for identifying customer intention according to claim 1, characterized in that: The determining, based on the journey data corresponding to each customer and the target product, the journey link points and the number of journey participations of each customer, includes: Based on the journey data corresponding to each customer and the target product, determine all journey links of each customer participating in the target product and the number of journey participations corresponding to each journey link; The determining, based on the journey link points and the number of journey participations of each customer, the intention of each customer for the target product includes: Determine the link weights corresponding to each journey link point of the target product; The first intention degree of each customer for the target product is calculated based on the link weights corresponding to each journey link and the number of times each customer participates in each journey link.

3. The method for identifying customer intention according to claim 2, characterized in that: After calculating the first intention degree of each customer for the target product according to the link weights corresponding to each journey link and the number of times each customer participates in each journey link, the method further includes: Obtain the second intention degree calculated for each customer in the previous period; Based on the weight values ​​corresponding to the first intention degree and the second intention degree respectively, a final intention degree of each customer for the target product is determined.

4. The method for identifying customer intention according to claim 3, characterized in that: The calculation formula for the final intention degree includes: Among them, w (T) is the final intention degree, j is the total number of journey links included in the target product, n is the number of journey participations corresponding to the i-th journey link, is the weight value corresponding to the first intention degree; w (T-1) is the second intention degree of the previous period, is the weight value corresponding to the second intention degree, d T is the weight factor.

5. The method for identifying customer intention according to claim 1, characterized in that: The determining, based on the journey data corresponding to each customer and the target product, the journey link points and the number of journey participations of each customer, includes: Based on the journey data corresponding to each customer and the target product, determining the last journey link point of each customer's participation in the target product and the last journey participation number corresponding to the last journey link point; The determining, based on the journey link points and the number of journey participations of each customer, the intention of each customer for the target product includes: Determine the link weights corresponding to each journey link point of the target product; The third intention degree of each customer for the target product is calculated according to the link weight corresponding to the last journey link point participated by each customer and the last journey participation number of each customer participating in the last journey link point.

6. The method for identifying customer intention according to claim 5, characterized in that: After calculating the third intention degree of each customer for the target product according to the link weight corresponding to the last journey link point participated by each customer and the last journey participation number of each customer participating in the last journey link point, the method further includes: Obtain the fourth intention degree calculated for each customer in the previous period; Based on the weight values ​​respectively corresponding to the third intention degree and the fourth intention degree, a final intention degree of each customer for the target product is determined.

7. The method for identifying customer intention according to claim 6, characterized in that: The calculation formula for the final intention degree includes: in, is the final intention degree, is the link weight of the last journey link, n is the number of participations in the last journey, is the weight value corresponding to the third intention degree; w (n,s,T-1) is the fourth intention degree of the previous period, is the weight value corresponding to the fourth intention degree, d T is the weight factor.

8. The method for identifying customer intention according to any one of claims 2 to 7, characterized in that: The step of determining the link weights corresponding to the respective journey links of the target product includes: Determine the link weights of a portion of the journey link nodes in the target product according to the weight configuration instruction; The link weights of another part of the journey link points in the target product are determined according to a weight calculation formula; wherein, in any two journey link points of the target product, the link weight of the earlier journey link point is less than the link weight of the later journey link point.

9. The method for identifying customer intention according to claim 8, characterized in that: The multiple journey links of the target product are numbered in ascending order according to the sequence of the corresponding life cycle; The weight calculation formula includes: Among them, s i is the journey node, i is the number of the journey node, is the link weight of the i-th journey link node.

10. The method for identifying customer intention according to any one of claims 1 to 7, characterized in that: Before determining the follow-up channel corresponding to each customer based on the intention of each customer, the following steps are also included: When the journey data corresponding to any customer and the target product changes, the customer's intention degree is updated in real time according to the new journey data to obtain an updated intention degree.

11. The method for identifying customer intention according to claim 10, characterized in that: When the journey data of the target product in the original customer data of the customer is empty, the calculation formula of the updated intention degree is: in, is the intention to update, is the link weight of the unique journey link in the new journey data, n is the number of journey participations of the unique journey link, K1 is the first coefficient and K1>

1.

12. The method for identifying customer intention according to claim 11, characterized in that: When the journey data of the target product in the original customer data of the customer is not empty, the calculation formula of the updated intention degree is: in, is the intention to update, is the link weight of the last journey link in the new journey data, n is the number of journey participations at the last journey link, and w (n,s,T-1) is the intention degree of the previous period, K2 is the second coefficient and K2>1.

13. The method for identifying customer intention according to claim 1, characterized in that: Based on the intention of each customer, the follow-up channel corresponding to each customer is determined, including: Based on the intention of each customer, multiple customers are divided into multiple customer groups; According to the follow-up strategy corresponding to each customer group, determine the follow-up channel corresponding to each customer.

14. The method for identifying customer intention according to claim 13, characterized in that: Determining the follow-up channels corresponding to each customer according to the follow-up strategies corresponding to each customer group includes: Allocating a one-to-one follow-up channel to each customer in the first customer group; wherein the first customer group is the customer group with the highest average intention; The journey data of the corresponding customer is provided to each business person in the one-to-one follow-up channel.

15. The method for identifying customer intention according to claim 14, characterized in that: The customer data also includes an activity parameter; after obtaining the customer data of each customer in the target customer group, the method further includes: Filter out customers with no journey whose journey data for the target product is empty from multiple customers; According to the activity parameter of each no-journey customer, active customers are screened out from multiple no-journey customers; After dividing the multiple customers into multiple customer groups based on the intention of each customer, the method further includes: The active users are divided into a second customer group; wherein the average intention degree of the inactive users in the second customer group is lower than the average intention degree of the first customer group.

16. The method for identifying customer intention according to claim 15, characterized in that: The active customers are screened out from multiple customers without a journey according to the active parameters of each customer without a journey, including: Calculate the product coverage of each no-journey customer based on the number of products that each no-journey customer has associated with; Obtain the number of contacts each no-journey customer has with the product provider within a preset time period; From the plurality of no-trip customers, the no-trip customers whose product coverage is greater than a first threshold or the no-trip customers whose contact times are greater than a second threshold are screened out.

17. A customer intention recognition device, characterized in that: The device comprises: A target determination module is used to determine the target customer group and target product according to the target constraints; A data acquisition module, used to acquire customer data of each customer in the target customer group; wherein the customer data includes journey data of the target product; A journey determination module, used to determine the journey links and journey participation times of each customer based on the journey data corresponding to each customer and the target product; An intention determination module, used to determine each customer's intention for the target product according to the journey link points and the number of times each customer has participated in the journey; The channel allocation module is used to determine the follow-up channel corresponding to each customer based on the intention of each customer.

18. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the steps of the customer intention identification method as described in any one of claims 1-16 are implemented.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the steps of the customer intention identification method according to any one of claims 1 to 16 are implemented.

20. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor, the steps of the customer intention identification method as described in any one of claims 1 to 16 are implemented.

Citation Information

Cited By

  • User class reporting intention prediction method based on hypergraph neural network and related product

    CN122550221A