Electricity information automation case management method, system and medium

Abstract

The application provides an electric pin information automatic case management method, system and medium, the method comprises the following steps: importing customer list data of different sources through a standardized interface; storing the customer list data in batches after classifying the customer list data according to a real-time strategy and generating a rule code corresponding to the customer list data; dynamically marking the customer list data in the warehouse according to the rule code, and obtaining a shunt result by shunting the customer list data according to the marking result and a corresponding shunt mode; and distributing the cases corresponding to the shunt result to a seat to obtain a seat distribution result; the application can process different batches of cases in parallel, can effectively deal with the case processing situation of a large number of cases, effectively improves the efficiency of case distribution, and reduces the time consumption.

Description

Technical Field

[0001] This application belongs to the field of financial data management technology, and relates to a method for managing telemarketing information, and in particular to a method, system and medium for automated case management of telemarketing information. Background Technology

[0002] In the financial industry, telemarketing is one of the core methods of business operations, and its efficiency directly impacts a company's profitability. Therefore, improving telemarketing efficiency has become a key challenge for many financial institutions. To address this pain point, deploying a mature, stable, and efficient case processing system is crucial—namely, an automated telemarketing case pipeline system. Its lifecycle covers four stages: list import, case entry, case triage, and case assignment, each with detailed operational procedures. Through automated pipeline management, the system can significantly improve case processing efficiency, thereby driving business growth.

[0003] However, the existing automated case management system for telemarketing has the following problems when managing data from different customers:

[0004] Data silo problem: Customer data is scattered across different platforms such as Customer Relationship Management (CRM), Excel spreadsheets, and business systems. Importing lists requires manual downloading and uploading, which takes an average of more than 2 hours per day, resulting in low case processing efficiency. Furthermore, the manual method makes it impossible to match agent status in real time, which cannot meet the needs of processing large batches of cases. Summary of the Invention

[0005] The purpose of this application is to provide an automated case management method, system, and medium for telemarketing information, which addresses the problem of low efficiency in customer data processing across different platforms in the prior art.

[0006] Firstly, this application provides an automated case management method for telemarketing information, the method comprising:

[0007] Import customer list data from different sources using a standardized interface;

[0008] The customer list data is categorized according to the real-time strategy, then batch-added into the database and corresponding rule codes are generated.

[0009] The customer list data after being entered into the database is dynamically tagged according to the rule code, and the corresponding diversion method is matched according to the tagging result to obtain the diversion result.

[0010] The cases corresponding to the triage results are assigned seats to obtain the seat allocation results.

[0011] In one implementation of the first aspect, the step of classifying the customer list data according to a real-time strategy, batch-loading it into the database, and generating corresponding rule codes includes:

[0012] The basic information for obtaining the customer list data includes at least one of source information, upstream tags, and blacklist hit results.

[0013] Based on the basic information, the customer list data is divided into different types of category data, and corresponding rule codes are generated for different categories of data.

[0014] After filtering the different types of classified data by calling the business planning platform strategy, high-concurrency target data is obtained. The target data is then used to generate standardized cases and then batch-entered into the database.

[0015] In one implementation of the first aspect, the step of dynamically tagging the customer list data after it has been entered into the database according to the rule code, and then matching the tagging result with the corresponding traffic splitting method to obtain the traffic splitting result includes:

[0016] Obtain the case characteristics of the standardized cases that have been entered into the database, and dynamically tag the customers in the standardized cases according to the case characteristics and the rule code to obtain the tagging results;

[0017] Based on the tagging results and the rule code, a corresponding allocation method is selected for each standardized case, and the allocation method includes at least one of model allocation, rule allocation, and AI automatic allocation.

[0018] Each standardized case is further subdivided according to the selected allocation method to obtain the subdivision result;

[0019] The characteristics of the case include at least product type and customer value.

[0020] In one implementation of the first aspect, the step of assigning seats to the cases corresponding to the triage results to obtain seat allocation results includes:

[0021] Obtain the status information of the agent, including skill level and historical conversion rate;

[0022] The suitability of each agent is calculated based on the skill level and the historical conversion rate.

[0023] Based on the adaptability, the multiple agents are divided into different virtual agent groups, and based on the adaptability of the virtual agent groups, a corresponding case allocation ratio is assigned to the agents in each virtual agent group.

[0024] According to the case allocation ratio, the cases in the triage results are respectively assigned to the seats in the corresponding virtual agent groups.

[0025] In one implementation of the first aspect, the step of assigning seats to the cases corresponding to the triage results to obtain seat allocation results further includes:

[0026] After completing the seat allocation, determine whether there are any remaining cases in the triage results;

[0027] When it is determined after seat allocation that there are still remaining cases in the triage results, the current load status of each seat is obtained;

[0028] The remaining cases are assigned to the least busy agent.

[0029] In one implementation of the first aspect, the method further includes:

[0030] During the process of assigning seats to cases based on the triage results, abnormal cases with allocation anomalies are obtained and sent to the case recycling pool.

[0031] The case recycling pool will re-process the abnormal cases and assign corresponding agents.

[0032] In one implementation of the first aspect, during the triage process of the abnormal cases, when the number of reassignments of the abnormal case meets the retry condition, the triage of the abnormal case is abandoned, and the retry condition satisfies the following formula:

[0033]

[0034] in, Indicates the number of times the data is redistributed. This indicates the priority of the aforementioned abnormal cases. Indicates the first parameter. This represents the second parameter, where both the first and second parameters are preset constants.

[0035] In one implementation of the first aspect, the method further includes:

[0036] During the case triage process, when there is a jitter case that fails to triage due to network jitter, the jitter case is retried momentarily, and the retried momentary time is less than 200ms.

[0037] And / or during the seat allocation process, when the target of the allocation is a faulty node, the seat is bypassed and the seat is reallocated.

[0038] The present invention also provides an automated case management system for telemarketing information, comprising:

[0039] The import module is used to import customer list data from different sources through a standardized interface.

[0040] The classification module is used to classify the customer list data according to the real-time strategy, then batch-store it into the database and generate corresponding rule codes.

[0041] The traffic splitting module is used to dynamically tag the customer list data after it is entered into the database according to the rule code, and to match the corresponding traffic splitting method according to the tagging result to obtain the traffic splitting result.

[0042] The allocation module is used to allocate seats to the cases corresponding to the diversion results to obtain the seat allocation results.

[0043] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the above-described automated case management method for telemarketing information.

[0044] As described above, the automated case management method, system, and medium for telemarketing information described in this application have the following beneficial effects:

[0045] This invention uses a standardized interface to import customer list data from different sources and batch-enter the database, thereby reducing the time spent on manual import. Furthermore, it performs traffic splitting and agent allocation splitting on the batch-entered cases, enabling parallel processing of different batches of cases. This effectively addresses the challenges of handling large volumes of cases, significantly improving case allocation efficiency and reducing time consumption. Simultaneously, the parallel processing of list splitting, case splitting, and agent splitting significantly improves the management efficiency of telemarketing information. Moreover, it allows for case configuration based on the actual situation of agents, ensuring a high success rate and effectively improving case management efficiency. Attached Figure Description

[0046] Figure 1 The flowchart shown is a process for automated case management of telemarketing information as described in an embodiment of this application.

[0047] Figure 2 The diagram shown is a structural block diagram of the automated case management system for telemarketing information described in an embodiment of this application. Detailed Implementation

[0048] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0049] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0050] See Figure 1 and Figure 2 The following embodiments of this application provide an automated case management method, system, and medium for telemarketing information. This invention uses a standardized interface to import customer list data from different sources and batch-store it, thereby reducing the time spent on manual import. Furthermore, it performs traffic splitting and agent allocation splitting on the batch-stored cases, enabling parallel processing of different batches of cases. This effectively addresses the situation of processing large volumes of cases, significantly improving case allocation efficiency and reducing time consumption. Simultaneously, the parallel processing of list splitting, case splitting, and agent splitting significantly improves the management efficiency of telemarketing information. Moreover, it allows for case configuration based on the actual situation of agents, thereby ensuring a high success rate and effectively improving case management efficiency.

[0051] like Figure 1 As shown in the figure, this embodiment provides an automated case management method for telemarketing information, the method including the following steps:

[0052] S100: Import customer list data from different sources through a standardized interface.

[0053] S200. After classifying the customer list data according to the real-time strategy, the data is stored in batches and corresponding rule codes are generated.

[0054] S300. Dynamically tag the customer list data after it has been entered into the database according to the rule code, and perform traffic diversion processing according to the tagging result by matching the corresponding diversion method to obtain the diversion result.

[0055] S400. The cases corresponding to the diversion results are assigned to agents to obtain the agent assignment results.

[0056] In this embodiment, to automate the management of different telemarketing information, customer list data from various sources is first imported through a standardized interface. This eliminates the traditional manual import process, effectively reducing the time spent manually importing customer data from different sources. After importing the customer list data, it is categorized according to a real-time strategy and then batch-stored, generating corresponding rule codes. These rules codes are then used to dynamically tag the customer list data, and the results are matched with appropriate referral methods to process different cases. Finally, based on the referral results, the cases are assigned to agents, thus completing the automated agent allocation for different customer list data. This significantly improves the efficiency of customer list data management. The automated processing method effectively handles the simultaneous processing of large amounts of data while ensuring that different customer data is accurately assigned to suitable agents, thereby improving agent allocation efficiency and conversion rates.

[0057] Specifically, since different customer list data comes from various platforms, in order to import customer list data from different sources in a unified manner, a standardized interface is configured on the corresponding customer platform, and the customer list data from different sources is synchronized to the telemarketing system in real time through the standardized interface using a drag-and-drop method on a canvas. This eliminates the manual import step, effectively improves the efficiency of data import, reduces the time spent on manual data import, and helps improve the efficiency of subsequent agent allocation.

[0058] In some embodiments, the step of classifying the customer list data according to a real-time strategy, batch-loading it into the database, and generating corresponding rule codes includes:

[0059] The basic information for obtaining the customer list data includes at least one of source information, upstream tags, and blacklist hit results.

[0060] Based on the basic information, the customer list data is divided into different types of category data, and corresponding rule codes are generated for different categories of data.

[0061] After filtering the different types of classified data by calling the business planning platform strategy, high-concurrency target data is obtained. The target data is then used to generate standardized cases and then batch-entered into the database.

[0062] In this embodiment, after importing data from different sources into the platform, in order to further classify the customer list data, the basic information of the customer list data is first obtained, including source information, upstream tags and blacklist hit results. Then, according to the different basic information, the customer list data is divided into different types of category data, and corresponding rule codes are generated for different categories of data. After calling the business plan platform strategy to filter the different types of category data, high-concurrency target data is obtained. Then, the target data is automatically generated into standardized cases and then batch-stored.

[0063] In the above process, after the customer list data is divided into different types of category data based on basic information, the different types of category data are filtered using the business planning platform strategy to obtain high-concurrency target data. The target data is then generated into standardized cases and entered into the database in batches to facilitate the subsequent diversion and processing of the standardized cases entered into the database in batches.

[0064] In the process of generating standardized cases from target data, a distributed task scheduling framework based on rule code hash sharding is adopted to achieve parallel processing of massive amounts of target data, effectively improving the processing efficiency of target data.

[0065] It should be noted that the process of generating standardized cases from target data described above is existing technology and will not be repeated here.

[0066] In some other embodiments, the step of dynamically tagging the customer list data after it has been entered into the database according to the rule code, and then matching the tagging results with the corresponding traffic splitting method to obtain the traffic splitting result, includes:

[0067] Obtain the case characteristics of the standardized cases that have been entered into the database, and dynamically tag the customers in the standardized cases according to the case characteristics and the rule code to obtain the tagging results;

[0068] Based on the tagging results and the rule code, a corresponding allocation method is selected for each standardized case, and the allocation method includes at least one of model allocation, rule allocation, and AI automatic allocation.

[0069] Each standardized case is further subdivided according to the selected allocation method to obtain the subdivision result;

[0070] The characteristics of the case include at least product type and customer value.

[0071] In this embodiment, after the target data is generated into standardized cases and entered into the database in batches, the customer list data after entering the database is dynamically tagged according to the rule code generated in the aforementioned process, so that the corresponding diversion method can be matched according to the tagging results to divert different standardized cases.

[0072] Specifically, after batching standardized cases into the database, the case characteristics of each standardized case are first obtained from the records on the case platform. These characteristics include at least product type and customer value. Simultaneously, the case platform determines the corresponding traffic allocation mapping rule for each case based on its rule code. Then, the rule engine on the case platform is invoked. This rule engine dynamically tags the customers in each case based on the case characteristics and the corresponding traffic allocation mapping rule, generating corresponding tagging results. After generating the tagging results for each customer, a corresponding allocation method can be selected for each standardized case based on the tagging results. This includes model allocation, rule allocation, and AI automatic allocation. After completing the secondary traffic allocation of cases using the corresponding allocation method, the corresponding traffic allocation result is obtained.

[0073] In this process, the conversion rate is predicted based on machine learning by calling the internal AI department interface on the case platform. The corresponding allocation result is selected according to the conversion rate. The internal AI department uses existing large AI models for prediction. This solution does not involve any improvement to the model allocation, so it will not be elaborated here.

[0074] The rule allocation method involves obtaining the rule code of each customer in each standardized case, then performing a hash calculation on each rule code to obtain the corresponding hash value, and allocating customers in the standardized case according to preset rules based on the hash value, such as average allocation and proportional allocation. This avoids the problem of case allocation bias caused by directly allocating according to the rule code, which would affect the efficiency of case management.

[0075] AI-automated allocation utilizes existing AI models, combined with real-time agent status and historical performance, to select the corresponding allocation result. The AI ​​models used here are also existing models, and this solution does not impose any special restrictions on them, so they will not be elaborated on here.

[0076] It should be noted that both the model allocation and AI automatic allocation mentioned above utilize existing AI large-scale models to achieve secondary case triage, facilitating subsequent seat allocation for cases after secondary triage. On the other hand, the case platform in the above solution is a platform used in existing technology for case management, while the rule engine is an engine that stores the correspondence between rule codes and triage mapping rules on the case platform. This facilitates matching the corresponding triage mapping rule based on the customer's rule code in each standardized case, enabling dynamic tagging of cases according to the triage mapping rules. The correspondence between rule codes and triage mapping rules stored in the rule engine is pre-set; this solution does not involve improvements to the rule engine itself, and will not be elaborated upon here.

[0077] In some embodiments, the step of assigning seats to the cases corresponding to the triage results to obtain seat allocation results includes:

[0078] Obtain the status information of the agent, including skill level and historical conversion rate;

[0079] The suitability of each agent is calculated based on the skill level and the historical conversion rate.

[0080] Based on the adaptability, the multiple agents are divided into different virtual agent groups, and based on the adaptability of the virtual agent groups, a corresponding case allocation ratio is assigned to the agents in each virtual agent group.

[0081] According to the case allocation ratio, the cases in the triage results are respectively assigned to the seats in the corresponding virtual agent groups.

[0082] In this embodiment, after standardized cases are triaged and triage results are obtained, in order to further allocate seats, the current status information of each seat is first obtained, including skill level and historical conversion rate. Then, the suitability of each seat is calculated based on the skill level and historical conversion rate of each seat. Then, each seat is divided into different virtual seat groups according to the size of the suitability. And according to the size of the suitability, a corresponding case allocation ratio is configured for the seats in each virtual seat group. Then, according to the case allocation ratio, the cases in the triage results are respectively allocated to the seats in the corresponding virtual seat groups, thus completing the seat allocation of cases and maximizing the efficiency of case seat allocation.

[0083] In each of the virtual agent groups, the case allocation ratio of the agents is positively correlated with the suitability of the agents. The higher the suitability, the higher the corresponding case allocation ratio, thereby ensuring that cases with high suitability are preferentially allocated to suitable agents and improving case management efficiency.

[0084] Furthermore, each virtual agent group contains at least one agent, and the case allocation ratio in each virtual agent group can be set according to the degree of suitability, or it can be set manually or based on experience. The main purpose is to ensure that each agent in the virtual agent group can be reasonably allocated cases to maximize efficiency.

[0085] The suitability of each agent is positively correlated with skill level and historical conversion rate; the higher the skill level, the higher the suitability; the higher the historical conversion rate, the higher the suitability.

[0086] For example, the calculation process for the seat's fit degree satisfies the following formula:

[0087] Where A represents the agent's skill level, and B represents the agent's historical conversion rate. Indicates the first weight. This indicates the second weight; both the first and second weights are preset fixed parameters.

[0088] In some further embodiments, the step of assigning seats to the cases corresponding to the triage results to obtain seat allocation results further includes:

[0089] After completing the seat allocation, determine whether there are any remaining cases in the triage results;

[0090] When it is determined after seat allocation that there are still remaining cases in the triage results, the current load status of each seat is obtained;

[0091] The remaining cases are assigned to the least busy agent.

[0092] In the process of assigning seats to cases based on the triage results, it is first determined whether there are any remaining cases after the seats are assigned. If it is determined that there are remaining cases, the current load status of each seat in the virtual seat group is obtained first, and the remaining cases are assigned to the seats with the lowest load, so as to avoid some seats being overloaded and affecting efficiency.

[0093] When there are multiple remaining cases, after each case is assigned to the seat with the lowest load, the current load of the seat is recalculated, and the next remaining case is assigned to the seat with the lowest load calculated at the current time. This ensures that each case in the remaining cases can be assigned to the seat with the lowest load, so as to ensure the processing efficiency of each seat.

[0094] In some embodiments, the method further includes:

[0095] During the process of assigning seats to cases based on the triage results, abnormal cases with allocation anomalies are obtained and sent to the case recycling pool.

[0096] The case recycling pool will re-process the abnormal cases and assign corresponding agents.

[0097] In this embodiment, for abnormal cases with allocation errors, the abnormal cases are sent to the case recycling pool. The case recycling pool then re-processes the abnormal cases and assigns them to corresponding agents. Since the process of the case recycling pool re-processing abnormal cases and assigning agents is the same as the aforementioned process, it will not be repeated here.

[0098] In some further embodiments, during the triage process of the abnormal cases, when the number of reassignments of the abnormal case meets the retry condition, the triage of the abnormal case is abandoned, and the retry condition satisfies the following formula:

[0099]

[0100] in, Indicates the number of times the data is redistributed. This indicates the priority of the aforementioned abnormal cases. Indicates the first parameter. This represents the second parameter, where both the first and second parameters are preset constants.

[0101] In this embodiment, considering that some abnormal cases may be unable to be assigned, in order to avoid excessive retries for some abnormal cases, when the number of reassignments of abnormal cases meets the retry conditions, the abnormal cases are abandoned, thereby avoiding excessive retries that affect the efficiency of case management.

[0102] Specifically, when the number of times an abnormal case is reassigned is greater than or equal to the sum of the product of the current abnormal case's priority and the first parameter and the product of the number of reassignments and the second parameter, it indicates that the current abnormal case has reached its maximum number of retries. Therefore, the current abnormal case is abandoned, thus avoiding excessive retries that could affect the efficiency of case management.

[0103] In some other embodiments, the method further includes:

[0104] During the case triage process, when there is a jitter case that fails to triage due to network jitter, the jitter case is retried momentarily, and the retried momentary time is less than 200ms.

[0105] And / or during the seat allocation process, when the target of the allocation is a faulty node, the seat is bypassed and the seat is reallocated.

[0106] In this embodiment, during the case triage process, when a jittered case fails to be triaged due to network jitter, it is retried momentarily and triaged again, thereby avoiding case triage failure due to network jitter. During agent allocation, if the allocated agent is located at a faulty node, the allocation is bypassed and the agent is reassigned, thus ensuring a robust closed-loop fault-tolerant control mechanism that can effectively handle various problem situations.

[0107] It should be noted that in the above application scheme, customer list data in the same batch is processed sequentially, while customer list data in different batches is processed in parallel, thereby enabling the simultaneous processing of customer list data in different batches and effectively improving the efficiency of customer management.

[0108] This invention also discloses an automated case management system for telemarketing information, with reference to Figure 2 ,include:

[0109] Import module 201 is used to import customer list data from different sources through a standardized interface.

[0110] The classification module 202 is used to classify the customer list data according to the real-time strategy, then batch store it in the database and generate corresponding rule codes.

[0111] The diversion module 203 is used to dynamically tag the customer list data after it is entered into the database according to the rule code, and to match the corresponding diversion method according to the tagging result to obtain the diversion result.

[0112] The allocation module 204 is used to allocate seats to the cases corresponding to the diversion results to obtain seat allocation results.

[0113] Since each module of the aforementioned automated case management system for telemarketing information corresponds one-to-one with the steps of the aforementioned automated case management method for telemarketing information, they will not be repeated here.

[0114] It should be noted that the automated case management system for telemarketing information can implement the automated case management method for telemarketing information described in this application. However, the implementation device for the automated case management method for telemarketing information described in this application includes, but is not limited to, the structure of the automated case management system for telemarketing information listed in this embodiment. All structural modifications and substitutions of the prior art made based on the principles of this application are included within the protection scope of this application.

[0115] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the above-described automated case management method for telemarketing information.

[0116] The scope of protection of the automated case management method for telemarketing information described in this application is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principles of this application is included within the scope of protection of this application.

[0117] This invention also provides an electronic device, which includes a processor and a memory; the memory is used to store a computer program; the processor is used to execute the computer program stored in the memory, so that the electronic device performs the above-described automated case management method for telemarketing information.

[0118] This invention also provides a computer-readable storage medium storing a computer program that, when executed by an electronic device, implements the aforementioned automated case management method for telemarketing information.

[0119] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0120] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0121] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0122] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.

[0124] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for automated case management of telemarketing information, characterized in that, The method includes: Import customer list data from different sources using a standardized interface; The customer list data is categorized according to the real-time strategy, then batch-added into the database and corresponding rule codes are generated. The customer list data after being entered into the database is dynamically tagged according to the rule code, and the corresponding diversion method is matched according to the tagging result to obtain the diversion result. The cases corresponding to the triage results are assigned seats to obtain the seat assignment results; The process of classifying the customer list data according to a real-time strategy, batch-loading it into the database, and generating corresponding rule codes includes: The basic information for obtaining the customer list data includes at least one of source information, upstream tags, and blacklist hit results. Based on the basic information, the customer list data is divided into different types of category data, and corresponding rule codes are generated for different categories of data. After filtering the different types of classified data by calling the business planning platform strategy, high-concurrency target data is obtained. The target data is then used to generate standardized cases and then batch-entered into the database. The process of dynamically tagging the customer list data after it has been entered into the database according to the rule code, and then matching the tagging results with the corresponding traffic splitting method to obtain the traffic splitting result, includes: Obtain the case characteristics of the standardized cases that have been entered into the database, and dynamically tag the customers in the standardized cases according to the case characteristics and the rule code to obtain the tagging results; Based on the tagging results and the rule code, a corresponding allocation method is selected for each standardized case, and the allocation method includes at least one of model allocation, rule allocation, and AI automatic allocation. Each standardized case is further subdivided according to the selected allocation method to obtain the subdivision result; The characteristics of the case include at least product type and customer value; In the process of generating standardized cases from target data, a distributed task scheduling framework based on rule code hash sharding is adopted to achieve parallel processing of multiple target data.

2. The automated case management method for telemarketing information according to claim 1, characterized in that, The step of assigning seats to the cases corresponding to the triage results to obtain the seat allocation results includes: Obtain the status information of the agent, including skill level and historical conversion rate; The suitability of each agent is calculated based on the skill level and the historical conversion rate. Based on the adaptability, the multiple agents are divided into different virtual agent groups, and based on the adaptability of the virtual agent groups, a corresponding case allocation ratio is assigned to the agents in each virtual agent group. According to the case allocation ratio, the cases in the triage results are respectively assigned to the seats in the corresponding virtual agent groups.

3. The automated case management method for telemarketing information according to claim 2, characterized in that, The step of assigning seats to the cases corresponding to the triage results to obtain the seat allocation results also includes: After completing the seat allocation, determine whether there are any remaining cases in the triage results; When it is determined after seat allocation that there are still remaining cases in the triage results, the current load status of each seat is obtained; The remaining cases are assigned to the least busy agent.

4. The automated case management method for telemarketing information according to claim 2, characterized in that, The method further includes: During the process of assigning seats to cases based on the triage results, abnormal cases with allocation anomalies are obtained and sent to the case recycling pool. The case recycling pool will re-process the abnormal cases and assign corresponding agents.

5. The automated case management method for telemarketing information according to claim 4, characterized in that, During the triage process for the abnormal cases, if the number of reassignments for the abnormal case meets the retry condition, the triage of the abnormal case is abandoned. The retry condition satisfies the following formula: in, Indicates the number of times the allocation will be redistributed. This indicates the priority of the aforementioned abnormal cases. Indicates the first parameter. This represents the second parameter, where both the first and second parameters are preset constants.

6. The automated case management method for telemarketing information according to claim 2, characterized in that, The method further includes: During the case triage process, when there is a jitter case that fails to triage due to network jitter, the jitter case is retried momentarily, and the retried momentary time is less than 200ms. And / or during the seat allocation process, when the target of the allocation is a faulty node, the seat is bypassed and the seat is reallocated.

7. An automated case management system for telemarketing information, characterized in that, include: The import module is used to import customer list data from different sources through a standardized interface. The classification module is used to classify the customer list data according to the real-time strategy, then batch-store it into the database and generate corresponding rule codes. The traffic splitting module is used to dynamically tag the customer list data after it is entered into the database according to the rule code, and to match the corresponding traffic splitting method according to the tagging result to obtain the traffic splitting result. The allocation module is used to allocate seats to the cases corresponding to the diversion results to obtain seat allocation results; The process of classifying the customer list data according to a real-time strategy, batch-loading it into the database, and generating corresponding rule codes includes: The basic information for obtaining the customer list data includes at least one of source information, upstream tags, and blacklist hit results. Based on the basic information, the customer list data is divided into different types of category data, and corresponding rule codes are generated for different categories of data. After filtering the different types of classified data by calling the business planning platform strategy, high-concurrency target data is obtained. The target data is then used to generate standardized cases and then batch-entered into the database. The process of dynamically tagging the customer list data after it has been entered into the database according to the rule code, and then matching the tagging results with the corresponding traffic splitting method to obtain the traffic splitting result, includes: Obtain the case characteristics of the standardized cases that have been entered into the database, and dynamically tag the customers in the standardized cases according to the case characteristics and the rule code to obtain the tagging results; Based on the tagging results and the rule code, a corresponding allocation method is selected for each standardized case, and the allocation method includes at least one of model allocation, rule allocation, and AI automatic allocation. Each standardized case is further subdivided according to the selected allocation method to obtain the subdivision result; The characteristics of the case include at least product type and customer value; In the process of generating standardized cases from target data, a distributed task scheduling framework based on rule code hash sharding is adopted to achieve parallel processing of multiple target data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed, it implements the automated case management method for telemarketing information as described in any one of claims 1 to 6.

Images