Customer service type work order distribution method, device, equipment and medium

By using historical database and address level identification models to determine the service company in customer service work order allocation, the problem of insufficient efficiency and accuracy of work order allocation in the existing technology is solved, and the accuracy and response speed of the service company are improved.

CN118917619AInactive Publication Date: 2024-11-08GUANGZHOU BAILING DATA CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411098877.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, the allocation efficiency and accuracy of customer service work orders is low, and it is impossible to accurately describe the customer's area, resulting in inaccurate allocation of service companies.

Method used

By obtaining the customer address information in the pending work order, if there is a processed work order in the historical database, the historical service company will be preferred; if none, the target hierarchical address is determined using the trained address level identification model, including the first-level address and Secondary address, and then determine the target service company.

Benefits of technology

It improves the efficiency of work order allocation for old customers, and through the address level identification model, ensures the accuracy of work order allocation for new customers, and accurately determines the service company even if some address information is missing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917619A_ABST
    Figure CN118917619A_ABST
Patent Text Reader

Abstract

The invention provides a customer service type work order distribution method, device and equipment and a medium, relates to the technical field of data processing, and aims to solve the problem of how to improve the efficiency and accuracy of customer service type work order distribution. The method comprises the steps of obtaining a to-be-processed work order of a customer service class; if the processed work order of the target customer exists in the historical database, the historical service company in the processed work order is determined as the target service company, so that the work order distribution efficiency of the old customer can be improved; if the processed work order of the target customer does not exist in the historical database, inputting a first customer address in the work order to be processed into the trained address level identification model to obtain a target hierarchical address, and determining a target service company according to the target hierarchical address; the to-be-processed work order is allocated to the target service company, even if part of address information is lost, the target service company can be determined only according to the target hierarchical address, and the accuracy of work order allocation of new clients is 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 provides a method, device, equipment and medium for allocating customer service work orders. Background Art

[0002] In the customer service industry, door-to-door service is involved. After the customer fills out the work order, the customer service team will assign the work order to a designated service company based on the address information provided in the work order. The service company will arrange suitable service personnel and dispatch professional service personnel to provide the required services to the customer, such as maintenance, cleaning, installation, etc., based on the time and service requirements provided by the customer.

[0003] The efficiency of manual work order allocation is low. In the prior art, a service company is specified based on the final address in the address information. However, the final address is generally a building number or a unit number. Different communities may have the same building number and unit number. Therefore, the prior art cannot accurately describe the customer's area based on the final address alone, which leads to poor accuracy in work order allocation and inability to accurately provide door-to-door service to customers. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for allocating customer service work orders, which are used to solve the problem of how to improve the efficiency and accuracy of customer service work order allocation.

[0005] In a first aspect, a method for allocating customer service work orders is provided, comprising:

[0006] Get pending work orders for customer service;

[0007] If there is a processed work order of the target customer in the historical database, the historical service company in the processed work order is determined as the target service company; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer;

[0008] If there is no processed work order of the target customer in the historical database, the first customer address in the work order to be processed is input into the trained address level recognition model to obtain a target hierarchical address, and a target service company is determined according to the target hierarchical address; wherein the target hierarchical address includes a target primary address and / or a target secondary address; and the range of the target primary address is larger than the range of the target secondary address;

[0009] The pending work order is allocated to the target service company.

[0010] Optionally, determining the historical service company in the processed work order as the target service company includes:

[0011] Calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order;

[0012] If the similarity is greater than a preset similarity, the historical service company in the processed work order is determined as the target service company.

[0013] Optionally, calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order includes:

[0014] Using a string matching algorithm, determine the matching part and the unmatched part between the first customer address in the to-be-processed work order and the second customer address in the processed work order;

[0015] The similarity between the first customer address and the second customer address is determined based on the similarity of the matched portion and the similarity of the unmatched portion.

[0016] Optionally, determining the similarity between the first customer address and the second customer address according to the similarity of the matching part and the similarity of the unmatched part includes:

[0017] The similarity between the first customer address and the second customer address is calculated by performing a weighted summation on the similarity of the matching part and the similarity of the unmatched part; wherein the weight of the matching part is greater than the weight of the unmatched part.

[0018] Optionally, after calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order, the method further includes:

[0019] If the similarity is less than a preset similarity, inputting the first customer address in the to-be-processed work order into the trained address level recognition model to obtain a target hierarchical address, and determining a target service company according to the target hierarchical address;

[0020] Allocate the pending work order to the target service company.

[0021] Optionally, determining a target service company according to the target hierarchical address includes:

[0022] If the target hierarchical address includes the target first-level address, the service company corresponding to the target first-level address is determined as the target service company according to the first relationship table; the first relationship table includes multiple service companies and multiple first-level addresses corresponding to each service company;

[0023] If the target hierarchical address does not include the target first-level address, the first-level address corresponding to the target second-level address is determined as the target first-level address according to a second relationship table; the second relationship table includes multiple first-level addresses and multiple second-level addresses corresponding to each first-level address;

[0024] According to the first relationship table, the service company corresponding to the target first-level address is determined as the target service company.

[0025] Optionally, before inputting the first customer address in the to-be-processed work order into the trained address level recognition model to obtain the target hierarchical address, the method further includes:

[0026] Acquire a sample address data set; the sample address data set includes a plurality of sample addresses and a label of each sample address; the label is used to indicate the actual level of each sample address;

[0027] Input each sample address into the original address level recognition model to obtain the predicted level of each sample address;

[0028] According to the error between the predicted level and the actual level of each sample address, the parameters of the original address recognition model are continuously adjusted until the preset conditions are met to obtain a trained address level recognition model.

[0029] In a second aspect, a work order distribution device for customer service is provided, comprising:

[0030] The acquisition module is used to obtain pending work orders of customer service;

[0031] A determination module is used to determine the historical service company in the processed work order as the target service company if there is a processed work order of the target customer in the historical database; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer;

[0032] The determination module is further configured to input the first customer address in the to-be-processed work order into the trained address level recognition model if there is no processed work order for the target customer in the historical database, obtain a target hierarchical address, and determine a target service company according to the target hierarchical address; wherein the target hierarchical address includes a target primary address and / or a target secondary address; and the range of the target primary address is larger than the range of the target secondary address;

[0033] The allocation module is used to allocate the to-be-processed work order to the target service company.

[0034] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the customer service work order allocation method described in the first aspect.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and a processor executes the computer program to implement the customer service work order allocation method described in the first aspect.

[0036] Compared with the prior art, the beneficial effects of this application are as follows:

[0037] The present application provides a method for allocating customer service work orders, including: obtaining customer service work orders to be processed; if there is a processed work order of the target customer in the historical database, the historical service company in the processed work order is determined as the target service company; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer; if there is no processed work order of the target customer in the historical database, the first customer address in the work order to be processed is input into the trained address level recognition model to obtain the target hierarchical address, and the target service company is determined according to the target hierarchical address; wherein the target hierarchical address includes the target first-level address and / or the target second-level address; the range of the target first-level address is greater than the range of the target second-level address; and the work order to be processed is allocated to the target service company. The present application gives priority to the customer's processed work order, arranges the historical service company to provide services to the customer, omits the processes such as address identification and allocation of service companies, and can improve the efficiency of work order allocation for old customers. Moreover, the target hierarchical address is determined by the address level recognition model, and even if part of the address information is missing, the target service company can be determined only according to the target hierarchical address, thereby improving the accuracy of work order allocation for new customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technical customer service personnel in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0039] Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application;

[0040] Figure 2 A flowchart of a method for allocating customer service orders provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the structure of a customer service work order distribution device provided in an embodiment of the present application.

[0042] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technical customer service personnel in this field without making creative work are within the scope of protection of this application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be arbitrarily combined with each other. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0044] In order to improve the efficiency and accuracy of customer service work order allocation, the embodiment of the present application provides a customer service work order allocation method. The method can be executed by a computer device. Before introducing the specific technical solution of the present application, the hardware operating environment involved in the embodiment of the present application is first introduced.

[0045] Please refer to Figure 1 , Figure 1 A schematic diagram of the computer device structure of the hardware operating environment involved in the embodiment of the present application.

[0046] like Figure 1As shown, the computer device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 105 may optionally also be a storage device independent of the aforementioned processor 101.

[0047] Technical customer service personnel in this field can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the computer device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0048] like Figure 1 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a work order distribution device for customer service.

[0049] exist Figure 1 In the computer device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the computer device of the present invention can be set in the computer device, and the computer device calls the customer service type work order allocation device stored in the memory 105 through the processor 101, and executes the customer service type work order allocation method provided in the embodiment of the present application.

[0050] Based on the computer device of the aforementioned embodiment, Figure 2 A method for allocating customer service work orders provided in an embodiment of the present application is introduced.

[0051] S201. Obtain pending work orders of customer service.

[0052] In the specific implementation process, customer service work orders can be downloaded from the websites of customer service companies. Work orders include pending work orders and processed work orders. Pending work orders refer to work orders whose problems have not been processed. Pending work orders will record customer identity information, customer address, customer problem and other data. Customer identity information includes name, ID number, etc. Processed work orders refer to work orders that have completed the processing process and the customer's problem has been solved. Processed work orders will record customer identity information, customer address, customer problem, historical service company, processing process, processing results and other information.

[0053] S202: If there is a processed work order of the target customer in the historical database, the historical service company in the processed work order is determined as the target service company.

[0054] In the specific implementation process, a large number of processed work orders are stored in the historical database, and the target customer is the customer indicated by the customer identity information in the work order to be processed. After obtaining the work order to be processed of the customer service category, the customer identity information is extracted from the work order to be processed, for example: Zhang San, and whether there is a processed work order with the name Zhang San in the historical database is queried.

[0055] In a possible embodiment, if it is determined that there is a processed work order of the target customer in the history database, the historical service company in the processed work order can be directly determined as the target service company. The historical service company is a company that has provided door-to-door service to the target customer.

[0056] Taking into account the possibility that the target customer has changed his address, in another possible embodiment, the similarity between the first customer address in the work order to be processed and the second customer address in the processed work order can be calculated; if the similarity is greater than the preset similarity, the historical service company in the processed work order is determined as the target service company.

[0057] In the specific implementation process, the first customer address and the second customer address are first preprocessed, wherein the data preprocessing includes removing spaces, unifying upper and lower cases, removing special characters, unifying formats, correcting spelling errors, and processing abbreviations to ensure the consistency and accuracy of the addresses. Then, a fuzzy matching algorithm is used to calculate the similarity between the first customer address and the second customer address. If the similarity is greater than the preset similarity, it means that the first customer address and the second customer address are the same address, and the customer address of the target customer has not changed, then the historical service company in the processed work order is determined as the target service company.

[0058] In the embodiment of the present application, by determining the similarity between the customer address in the pending work order and the customer address in the processed work order, it is possible to avoid selecting the wrong service company due to slightly different customer addresses. Even if the customer's address information is slightly changed or wrong, it is possible to determine whether it belongs to the same customer through the similarity threshold.

[0059] In a possible embodiment, the step of calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order includes:

[0060] A string comparison algorithm is used to determine the matching part and the unmatched part between the first customer address in the to-be-processed work order and the second customer address in the processed work order; and the similarity between the first customer address and the second customer address is determined based on the similarity of the matching part and the similarity of the unmatched part.

[0061] In the specific implementation process, first, a string comparison algorithm is used to compare the first customer address and the second customer address to determine the matching part and the unmatched part between the two address strings. The string comparison algorithm can be a longest common subsequence (LCS) algorithm, a hash-based string matching algorithm, etc. Then the matching parts in the two address strings are extracted, and the similarity between them can be calculated based on the length of the matching parts, the number of identical characters, etc., for example: the similarity of the matching parts = the length of the matching parts / the longer address length of the first customer address and the second customer address. For the remaining part after the matching part is extracted from the address string, that is, the unmatched part, the edit distance, Jaccard similarity coefficient, etc. can also be used to calculate the similarity between them. Finally, the similarity between the first customer address and the second customer address is determined by combining the similarity of the matching parts and the similarity of the unmatched parts.

[0062] In the embodiment of the present application, the similarity of the matching part reflects the consistency of important information in the address, while the similarity of the unmatched part reflects possible differences or subtle inconsistencies in the address. Combining the similarity of the matching part and the unmatched part can more comprehensively evaluate the similarity between the two addresses.

[0063] In a possible embodiment, the step of determining the similarity between the first customer address and the second customer address according to the similarity of the matching part and the similarity of the unmatched part includes:

[0064] The similarity of the matching part and the similarity of the unmatched part are weightedly summed to calculate the similarity between the first customer address and the second customer address; wherein the weight of the matching part is greater than the weight of the unmatched part.

[0065] In the embodiment of the present application, in address matching, the matching part directly reflects the consistency of the core information of the address and is more important than the unmatched part. Therefore, giving a higher weight to the matching part can ensure that the matching result is more accurate.

[0066] In a possible embodiment, after calculating the similarity between the first customer address in the work order to be processed and the second customer address in the processed work order, if the similarity is less than a preset similarity, the customer address in the work order to be processed is input into the trained address recognition model to obtain the target hierarchical address; the target service company is determined based on the target hierarchical address, and the work order to be processed is assigned to the target service company.

[0067] S203: If it does not exist, input the first customer address in the work order to be processed into the trained address level recognition model to obtain the target hierarchical address, and determine the target service company according to the target hierarchical address.

[0068] In the specific implementation process, the first customer address in the work order to be processed is divided to obtain multiple hierarchical addresses, and the multiple hierarchical addresses are input into the trained address level recognition model to obtain the levels of the multiple hierarchical addresses. According to the levels of the multiple hierarchical addresses, the target hierarchical address is extracted from the multiple hierarchical addresses. The target hierarchical address includes a target first-level address and / or a target second-level address; the range of the target first-level address is larger than the range of the target second-level address. The target first-level address is a street / township address, and the target second-level address is a community / village address.

[0069] For example, the first customer's address is "Country A, Province B, City C, District D, Community F, Building G, Unit H", which is divided into multiple hierarchical addresses, including: Country address: Country A; Province / Municipality address: Province B; City address: City C; District / County address: District D; Street / Township address: Street E; Community / Village address: Community F; Building / Unit address: Building G, Unit H. The target hierarchical address is "Community F, Street E", the target first-level address is "Street E", and the target second-level address is "Community F".

[0070] In a possible embodiment, if the target hierarchical address includes a target first-level address, the service company corresponding to the target first-level address is determined as the target service company according to the first relationship table; the first relationship table includes multiple service companies and multiple first-level addresses corresponding to each service company; if the target hierarchical address does not include the target first-level address, the first-level address corresponding to the target second-level address is determined as the target first-level address according to the second relationship table; the second relationship table includes multiple first-level addresses and multiple second-level addresses corresponding to each first-level address; according to the first relationship table, the service company corresponding to the target first-level address is determined as the target service company.

[0071] In the specific implementation process, if the target hierarchical address is E Street, or the target hierarchical address is F Community of E Street, the pending work order is directly assigned to the target service company corresponding to E Street. When the street address is missing and the target hierarchical address is F Community, first determine the E Street to which F Community belongs, and then assign the pending work order to the target service company corresponding to E Street.

[0072] In an embodiment of the present application, a pre-set relationship table is used to automatically match addresses and service companies, thereby reducing the need for manual intervention and the probability of error. Work orders can be quickly assigned to the correct service company, thereby improving response speed and processing efficiency.

[0073] This involves a trained address level recognition model, which is trained based on a sample address data set. The sample address data set includes multiple sample addresses and a label for each sample address; the label is used to indicate the actual level of each sample address. The following describes the training process of the trained address level recognition model.

[0074] In a possible embodiment, before the customer address in the work order to be processed is input into the trained address level recognition model to obtain the target graded address, a sample address data set is obtained; each sample address is input into the original address level recognition model to obtain the predicted level of each sample address; based on the error between the predicted level and the actual level of each sample address, the parameters of the original address recognition model are continuously adjusted until the preset conditions are met to obtain the trained address level recognition model.

[0075] In the specific implementation process, the sample address data set should cover sample addresses of various levels, and each sample address should be input into the original address level recognition model to obtain the model's prediction results, which will be compared with the actual level of each sample address. By calculating the error between the predicted level and the actual level (usually using a loss function), using a back propagation algorithm or other optimization methods, adjusting the model's parameters according to the gradient of the loss function, and iterating continuously until the loss function is less than the preset error, or the maximum number of iterations is reached, then the iteration is stopped to obtain the trained address level recognition model.

[0076] In an embodiment of the present application, the original address level recognition model is trained through a sample address data set to obtain a trained address level recognition model, which can more accurately identify address information of different levels, improve the automated address level recognition capability, and thus improve the accuracy of customer service work order allocation.

[0077] S204: Allocate the pending work order to the target service company.

[0078] During the specific implementation process, the target service company arranges the corresponding service personnel to go to the first customer address in the pending work order based on the customer issues in the pending work order. After providing services to the target customer, the target service company, processing flow, and processing results are written into the pending work order and saved in the historical database as a processed work order.

[0079] Based on the same inventive concept, Figure 3 As shown, the embodiment of the present application also provides a work order distribution device for customer service, the device comprising:

[0080] The acquisition module is used to obtain pending work orders of customer service;

[0081] A determination module is used to determine the historical service company in the processed work order as the target service company if there is a processed work order of the target customer in the historical database; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer;

[0082] The determination module is further used for inputting the first customer address in the work order to be processed into the trained address level recognition model if there is no processed work order of the target customer in the historical database, obtaining the target hierarchical address, and determining the target service company according to the target hierarchical address; wherein the target hierarchical address includes the target first-level address and / or the target second-level address; and the range of the target first-level address is larger than the range of the target second-level address;

[0083] The allocation module is used to allocate pending work orders to target service companies.

[0084] Optionally, determine whether the module is specifically used for:

[0085] Calculate the similarity between the first customer address in the pending work order and the second customer address in the processed work order;

[0086] If the similarity is greater than the preset similarity, the historical service company in the processed work order is determined as the target service company.

[0087] Optionally, determine whether the module is specifically used for:

[0088] Using a string matching algorithm, determine the matching part and the unmatched part between the first customer address in the to-be-processed work order and the second customer address in the processed work order;

[0089] The similarity between the first customer address and the second customer address is determined based on the similarity of the matched portion and the similarity of the unmatched portion.

[0090] Optionally, determine whether the module is specifically used for:

[0091] The similarity of the matching part and the similarity of the unmatched part are weightedly summed to calculate the similarity between the first customer address and the second customer address; wherein the weight of the matching part is greater than the weight of the unmatched part.

[0092] Optionally, the determination module is further used to: after calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order, if the similarity is less than a preset similarity, input the first customer address in the to-be-processed work order into the trained address level recognition model to obtain a target hierarchical address, and determine the target service company according to the target hierarchical address;

[0093] The allocation module is also used to allocate the pending work orders to the target service company.

[0094] Optionally, determine whether the module is specifically used for:

[0095] If the target hierarchical address includes a target first-level address, the service company corresponding to the target first-level address is determined as the target service company according to the first relationship table; the first relationship table includes multiple service companies and multiple first-level addresses corresponding to each service company;

[0096] If the target hierarchical address does not include the target first-level address, the first-level address corresponding to the target second-level address is determined as the target first-level address according to the second relationship table; the second relationship table includes multiple first-level addresses and multiple second-level addresses corresponding to each first-level address;

[0097] According to the first relationship table, the service company corresponding to the target primary address is determined as the target service company.

[0098] Optionally, the customer service work order distribution device further includes a model training module, and the model training module is used to:

[0099] Before inputting the first customer address in the to-be-processed work order into the trained address level recognition model to obtain the target graded address, a sample address data set is obtained; the sample address data set includes multiple sample addresses and a label for each sample address; the label is used to indicate the actual level of each sample address;

[0100] Input each sample address into the original address level recognition model to obtain the predicted level of each sample address;

[0101] According to the error between the predicted level and the actual level of each sample address, the parameters of the original address recognition model are continuously adjusted until the preset conditions are met to obtain the trained address level recognition model.

[0102] It should be noted that each module in the work order allocation device for customer service in this embodiment corresponds one-to-one to each step in the work order allocation method for customer service in the aforementioned embodiment. Therefore, the specific implementation method of this embodiment can refer to the implementation method of the aforementioned customer service work order allocation method, which will not be repeated here.

[0103] Based on the same inventive concept, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory. When the computer program is executed by the processor, the aforementioned customer service work order allocation method is implemented.

[0104] Based on the same inventive concept, the present application also provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor, the aforementioned customer service work order allocation method is implemented.

[0105] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0106] In some embodiments, executable instructions may be in the form of a program, software, software module, script or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment.

[0107] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or code portions).

[0108] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0109] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system 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 system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0110] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0111] Through the description of the above implementation methods, technical customer service personnel in this field can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a disk, or an optical disk), and includes a number of instructions for a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0112] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A customer service work order allocation method, characterized in that: include: Get pending work orders for customer service; If there is a processed work order of the target customer in the historical database, the historical service company in the processed work order is determined as the target service company; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer; If there is no processed work order of the target customer in the historical database, the first customer address in the work order to be processed is input into the trained address level recognition model to obtain a target hierarchical address, and a target service company is determined according to the target hierarchical address; wherein the target hierarchical address includes a target primary address and / or a target secondary address; and the range of the target primary address is larger than the range of the target secondary address; The pending work order is allocated to the target service company.

2. The customer service work order allocation method according to claim 1, characterized in that: The step of determining the historical service company in the processed work order as the target service company includes: Calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order; If the similarity is greater than a preset similarity, the historical service company in the processed work order is determined as the target service company.

3. The customer service work order allocation method according to claim 2, characterized in that: The calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order includes: Using a string matching algorithm, determine the matching part and the unmatched part between the first customer address in the to-be-processed work order and the second customer address in the processed work order; The similarity between the first customer address and the second customer address is determined based on the similarity of the matched portion and the similarity of the unmatched portion.

4. The method for allocating customer service work orders as claimed in claim 3, characterized in that: Determining the similarity between the first customer address and the second customer address according to the similarity of the matching part and the similarity of the unmatched part includes: The similarity between the first customer address and the second customer address is calculated by performing a weighted summation on the similarity of the matching part and the similarity of the unmatched part; wherein the weight of the matching part is greater than the weight of the unmatched part.

5. The customer service work order allocation method according to claim 2, characterized in that: After calculating the similarity between the first customer address in the to-be-processed work order and the second customer address in the processed work order, the method further includes: If the similarity is less than a preset similarity, inputting the first customer address in the to-be-processed work order into the trained address level recognition model to obtain a target hierarchical address, and determining a target service company according to the target hierarchical address; The pending work order is allocated to the target service company.

6. The method for allocating customer service work orders as claimed in claim 1, characterized in that: The step of determining a target service company according to the target hierarchical address includes: If the target hierarchical address includes the target first-level address, the service company corresponding to the target first-level address is determined as the target service company according to the first relationship table; the first relationship table includes multiple service companies and multiple first-level addresses corresponding to each service company; If the target hierarchical address does not include the target first-level address, the first-level address corresponding to the target second-level address is determined as the target first-level address according to a second relationship table; the second relationship table includes multiple first-level addresses and multiple second-level addresses corresponding to each first-level address; According to the first relationship table, the service company corresponding to the target first-level address is determined as the target service company.

7. The method for allocating customer service work orders as claimed in claim 1, characterized in that: Before inputting the first customer address in the to-be-processed work order into the trained address level recognition model to obtain the target hierarchical address, the method further includes: Acquire a sample address data set; the sample address data set includes a plurality of sample addresses and a label of each sample address; the label is used to indicate the actual level of each sample address; Input each sample address into the original address level recognition model to obtain the predicted level of each sample address; According to the error between the predicted level and the actual level of each sample address, the parameters of the original address recognition model are continuously adjusted until the preset conditions are met to obtain a trained address level recognition model.

8. A work order distribution device for customer service, characterized in that: include: The acquisition module is used to obtain pending work orders of customer service; A determination module is used to determine the historical service company in the processed work order as the target service company if there is a processed work order of the target customer in the historical database; the target customer is the customer indicated by the customer identity information in the work order to be processed; the historical service company is the company that has provided door-to-door service to the target customer; The determination module is further configured to input the first customer address in the to-be-processed work order into the trained address level recognition model if there is no processed work order for the target customer in the historical database, obtain a target hierarchical address, and determine a target service company according to the target hierarchical address; wherein the target hierarchical address includes a target primary address and / or a target secondary address; and the range of the target primary address is larger than the range of the target secondary address; The allocation module is used to allocate the to-be-processed work order to the target service company.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the customer service work order allocation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the customer service work order allocation method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • House address similarity analysis method and device

    CN112347221A

  • Agent allocation method and device for acquiring new customers through Internet and storage medium

    CN112396326A

  • Automatic order dispatching method for power system

    CN113836898A

  • Power supply service work order processing method and device, electronic equipment and storage medium

    CN117744987A

  • Method for assisting automatic dispatching of fault repair work order in combination with multiple algorithms

    CN118096124A