Task allocation method and device based on customer service capability prediction

Abstract

The invention relates to a task allocation method and device based on customer service capability prediction, and the method comprises the steps: obtaining the historical task data of each customer service, and calculating the historical capability score of each customer service in each task based on the historical key features corresponding to the historical task data; obtaining a to-be-allocated task, and extracting a current task feature in the to-be-allocated task; inputting the current task characteristics and the historical ability score of each customer service into a preset ability prediction model, and obtaining a predicted ability score of each customer service for processing the to-be-allocated task output by the ability prediction model; and obtaining the current working state of each customer service, and allocating the to-be-allocated task to the customer service with the highest matching degree for processing based on the prediction capability score of each customer service for processing the to-be-allocated task and the current working state. According to the scheme provided by the invention, the task can be reasonably and accurately allocated to the most suitable customer service for processing according to the processing capability of the customer service on different types of tasks, so that the working efficiency of the customer service and the satisfaction degree of customers are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of task allocation, and in particular to a task allocation method and device based on customer service capability prediction. Background Art

[0002] In the customer service industry, the reasonable allocation of tasks to customer service personnel can not only improve customer satisfaction, but also improve the operational efficiency of the enterprise. For example, the reasonable allocation of tasks can ensure that the workload of each customer service staff matches their capabilities, improve the work efficiency of customer service staff, and avoid waste of human resources. At the same time, it can also assign complex problems to customer service staff who are experienced or good at this field, which can more effectively solve customer problems and enhance customers' trust in the enterprise. However, with the rapid development of the customer service industry, enterprises are facing the challenge of how to reasonably and efficiently allocate tasks to customer service.

[0003] In the existing related technologies, the task allocation method usually adopts a simple polling or random allocation mechanism, which cannot fully take into account the personal ability and expertise of customer service personnel, which may lead to unreasonable task allocation. For example, tasks in field A are assigned to customer service personnel who are good at handling tasks in field B but not good at handling tasks in field A, resulting in the customer service personnel being unable to effectively solve customer problems, which not only reduces the work efficiency of customer service, but also affects customer satisfaction. Therefore, there is an urgent need for a solution that can reasonably allocate tasks based on the processing capabilities of customer service personnel on different types of tasks. Summary of the invention

[0004] The present application provides a method and device for task allocation based on customer service capability prediction, so as to realize reasonable allocation of tasks according to the processing capability of customer service on different types of tasks.

[0005] In a first aspect, the present application provides a task allocation method based on customer service capability prediction, the method comprising:

[0006] Obtain the historical task data of each customer service representative, and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data;

[0007] Obtaining tasks to be assigned, and extracting current task features from the tasks to be assigned;

[0008] Input the current task characteristics and the historical ability scores of each customer service representative into a preset ability prediction model, and obtain the predicted ability scores of each customer service representative for processing the to-be-assigned task output by the ability prediction model;

[0009] The current working status of each customer service is obtained, and based on the predicted ability score of each customer service for processing the task to be assigned and the current working status, the task to be assigned is assigned to the customer service with the highest matching degree for processing.

[0010] In a second aspect, the present application provides a task allocation device based on customer service capability prediction, the device comprising:

[0011] A historical capability evaluation module is used to obtain historical task data of each customer service representative and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data;

[0012] A task feature extraction module is used to obtain tasks to be assigned and extract current task features in the tasks to be assigned;

[0013] A prediction capability evaluation module, used to input the current task characteristics and the historical capability scores of each customer service representative into a preset capability prediction model, and obtain the prediction capability scores of each customer service representative for handling the to-be-assigned task output by the capability prediction model;

[0014] The dynamic task allocation module is used to obtain the current working status of each customer service, and based on the predicted ability score of each customer service in processing the task to be allocated and the current working status, allocate the task to be allocated to the customer service with the highest matching degree for processing.

[0015] In a third aspect, the present application provides an electronic device comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to execute a task allocation method based on customer service capability prediction as described in the first aspect above.

[0016] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the task allocation method based on customer service capability prediction described in the first aspect of the present application.

[0017] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the task allocation method based on customer service capability prediction provided by the embodiment of the present application obtains the historical task data of each customer service, and calculates the historical capability score of each customer service on various tasks based on the historical key features corresponding to the historical task data; obtains the task to be assigned, and extracts the current task features in the task to be assigned; inputs the current task features and the historical capability scores of each customer service into a preset capability prediction model, and obtains the predicted capability scores of each customer service for processing the task to be assigned output by the capability prediction model; obtains the current working status of each customer service, and based on the predicted capability scores and current working status of each customer service for processing the task to be assigned, assigns the task to be assigned to the customer service with the highest matching degree for processing. Compared with the problem of unreasonable task allocation that may be caused by the simple polling or random allocation mechanism in the prior art, the solution provided by the present application can reasonably and accurately assign tasks to the most suitable customer service for processing according to the processing capabilities of the customer service on different types of tasks, effectively improving the work efficiency of the customer service and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0021] Figure 1 A flowchart of a task allocation method based on customer service capability prediction provided by an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the structure of a task allocation device based on customer service capability prediction provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0025] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0026] In order to solve the technical problem of unreasonable task allocation that may be caused by the use of simple polling or random allocation mechanism in the prior art, the present application provides a task allocation method based on customer service capability prediction, which can reasonably and accurately allocate tasks to the most suitable customer service for processing according to the customer service's processing capability on different types of tasks, thereby effectively improving the work efficiency of customer service and customer satisfaction.

[0027] Figure 1 A task allocation method based on customer service capability prediction provided in an embodiment of the present application is provided, referring to Figure 1 , a task allocation method based on customer service capability prediction provided by this application includes:

[0028] S1: Obtain the historical task data of each customer service representative, and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data.

[0029] Specifically, the historical task data in this application refers to the data related to the task when the customer service performs past tasks, including but not limited to at least one of the items such as task type, processing time, customer satisfaction score, etc. The historical key features corresponding to the historical task data are the key features of the data related to the task when the customer service performs past tasks. Taking the above-mentioned historical task data including task type, processing time and customer satisfaction score as an example, the corresponding historical key features include but are not limited to average processing time, success rate of different types of tasks, customer satisfaction, etc.

[0030] In a feasible embodiment of the present application, a weighted average algorithm may be used to calculate the historical capability scores of customer service for various types of tasks. For example, the historical capability score of a certain type of task = average processing time score (the shorter the time, the higher the score) * weighted number of time score + success rate score of this type of task (the higher the success rate, the higher the score) * weighted number of success rate score + customer service satisfaction score (the higher the satisfaction, the higher the score) * weighted number of satisfaction score. It should be understood that the above historical capability score calculation method is only used as a feasible example of the present application, and does not mean that the present application can only adopt this calculation method. The present application does not make specific restrictions on the calculation method of the historical capability score. In addition, the weighted numbers corresponding to the above-mentioned scores can be set according to actual conditions, and the present application does not limit this.

[0031] S2: Obtain the tasks to be assigned and extract the current task features in the tasks to be assigned.

[0032] Specifically, the current task features in the task to be assigned are extracted, including the extraction of the following contents:

[0033] (1) The tasks to be assigned are analyzed by natural language processing technology to obtain the task description length and keywords of the tasks to be assigned. Then, based on the task description length and keywords, the complexity of the tasks to be assigned is calculated by a preset scoring function.

[0034] In a feasible embodiment of the present application, natural language processing (NLP) technology can be used to analyze the task description of the task to be assigned. Specifically, Python's NLTK (Natural Language Toolkit) library can be used for text analysis, and the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm can be used to extract keywords. NLTK is a widely used Python library that provides many text processing functions, including vocabulary analysis, text classification, word segmentation, tokenization, part-of-speech tagging, named entity recognition, etc. It is a powerful tool for text analysis, preprocessing and feature extraction. The TF-IDF algorithm can extract the most representative keywords from a group of documents by calculating the importance of each word in the document.

[0035] After obtaining the task description length and keywords, the complexity of the task to be assigned needs to be calculated using a preset scoring function. In a feasible embodiment of the present application, the scoring function is composed of the difficulty score of each keyword and the score of the task description length, and the calculation method is as follows:

[0036] The complexity score of the task to be assigned = (the difficulty score of keyword 1 + the difficulty score of keyword 2 + ... the difficulty score of keyword N) * the weighted number of the keyword score + the length of the task description * the unit score * the weighted number of the task description length score.

[0037] For example, for a task to be assigned, it has keywords 1, 2 and 3 with difficulty scores of 15, 20 and 25 respectively, the task description length of the task is 30, the unit score is 2, the keyword score weighting is 0.6, and the task description length score weighting is 0.4, then the complexity score of the task to be assigned = (15+20+25)*0.6+30*2*0.4=60.

[0038] It should be understood that the above-mentioned weighted numbers can be set according to actual conditions, and this application does not impose any restrictions on this.

[0039] (2) Extract the priority factors corresponding to the tasks to be assigned.

[0040] Specifically, the priority factor in the present application includes but is not limited to at least one of the customer level and the urgency of the problem. The priority factor can be used as an additional feature of the task to be assigned and can be obtained when obtaining the task to be assigned.

[0041] S3: Input the current task characteristics and the historical ability scores of each customer service representative into a preset ability prediction model, and obtain the predicted ability scores of each customer service representative for handling the tasks to be assigned output by the ability prediction model.

[0042] The capability prediction model in this application is based on a training data set, obtained by training with a gradient boosting decision tree algorithm, and the training data set includes a data combination of the historical capability scores of customer service and the predicted capability scores of processing tasks to be assigned. In a feasible embodiment of the present application, the capability prediction model can be trained using the scikit-learn library of Python to implement the XGBoost algorithm. Cross-Validation is used to optimize hyperparameters during model training. Cross-Validation can use different subsets of the data set for training and verification, thereby evaluating the performance of the model, finding the optimal hyperparameter combination, and reducing the risk of overfitting the model. The prediction results of the capability prediction model are expressed using probability distributions to reflect the uncertainty of the prediction.

[0043] After inputting the current task characteristics and the historical ability scores of each customer service representative into the ability prediction model, the ability prediction model can output the predicted ability scores of each customer service representative in handling the tasks to be assigned.

[0044] S4: Obtain the current work status of each customer service representative, and assign the task to be assigned to the customer service representative with the highest matching degree for processing based on the predicted ability score of each customer service representative in processing the task to be assigned and the current work status.

[0045] Specifically, the current working status of the customer service includes the online status and the current load score of the customer service. The online status includes online and offline status. The current load score is determined based on the tasks that the customer service currently needs to process or is processing. The lower the current load status, the higher the current load score.

[0046] Assigning the pending tasks to the customer service with the highest matching degree for processing includes the following steps:

[0047] S401: Evaluate the current online status and current load score of each customer service representative.

[0048] S402: Filter out all customer service representatives whose online status is “online” as candidate customer service representatives.

[0049] S403: Based on the predicted ability score of each customer service representative among the candidate customer service representatives for handling the task to be assigned and the current load score, the utility value of assigning the task to be assigned to each customer service representative for processing is calculated, and the customer service representative with the highest utility value is selected as the customer service representative with the highest matching degree, and the task to be assigned is assigned to the customer service representative with the highest matching degree for processing.

[0050] In a feasible embodiment of the present application, the utility value is calculated as follows:

[0051] Obtain the capability weight and load weight of each customer service representative; take the product of the predicted capability score of each customer service representative for handling the assigned task and the corresponding capability weight as the first score, take the product of the current load score of each customer service representative and the corresponding load weight as the second score, and take the sum of the first score and the second score as the utility value. That is, utility value = predicted capability score * capability weight + current load score * load weight.

[0052] For example, assuming that the predicted capability score of a customer service representative for handling a business to be assigned is 80, the capability weight is 0.7, the current load score is 60, and the load weight is 0.8, then the utility value of the customer service representative for handling the business = 80*0.7+60*0.8=104.

[0053] It should be understood that the above-mentioned weighted numbers can be set according to actual conditions, and this application does not impose any limitation on this.

[0054] In order to monitor the operating status of the entire system in real time and adjust the task allocation strategy according to real-time data to adapt to the ever-changing customer service environment, in a feasible embodiment of the present application, after step S4, it also includes:

[0055] S5: Monitor the recent key features of customer service processing in real time, and dynamically adjust the customer service capacity weight based on the recent key features.

[0056] Specifically, the recent key features of the customer service processing business refer to the key features within a recent period of time, corresponding to the above-mentioned historical key features, including but not limited to the average processing time, the success rate of different types of tasks, customer satisfaction, etc. Based on the monitoring of the recent key features of the customer service processing business, the weight of the customer service in the utility value calculation is dynamically adjusted to adjust the allocation result. For example, if it is detected that the processing efficiency of a certain customer service has dropped significantly over a period of time and exceeds the normal threshold (which can be set according to actual conditions), the capacity weighting number will be reduced according to the efficiency reduction ratio, thereby lowering the utility value of the customer service. The capacity weighting number will be adjusted to a normal value after executing step S6 feedback learning (for example, adjusted to the capacity weighting number before the reduction, or the capacity weighting number is set according to actual conditions).

[0057] S6: Feedback the actual performance data of the customer service in handling the tasks to be assigned to the capability prediction model, so that the capability prediction model can adjust parameters based on the actual performance data.

[0058] Specifically, in order to improve the prediction accuracy of the capability prediction model, the actual performance data of the customer service in handling the assigned tasks, such as processing time, success, customer satisfaction, etc., is fed back to the capability prediction model and used as new training data to adjust the parameters of the capability prediction model to improve the prediction accuracy of the capability prediction model.

[0059] In summary, the technical solution provided by the present application obtains the historical task data of each customer service, calculates the historical ability score of each customer service on various tasks based on the historical key features corresponding to the historical task data; obtains the tasks to be assigned, extracts the current task features in the tasks to be assigned; inputs the current task features and the historical ability scores of each customer service into the preset ability prediction model, obtains the predicted ability scores of each customer service for handling the tasks to be assigned output by the ability prediction model; obtains the current working status of each customer service, and assigns the tasks to be assigned to the customer service with the highest matching degree for processing based on the predicted ability scores and current working status of each customer service for handling the tasks to be assigned. Compared with the problem of unreasonable task allocation that may be caused by the use of simple polling or random allocation mechanisms in the prior art, the solution provided by the present application can reasonably and accurately assign tasks to the most suitable customer service for processing according to the processing capabilities of the customer service on different types of tasks, effectively improving the work efficiency of the customer service and the customer satisfaction. In addition, the solution provided by the present application can also feed back the actual performance data of the customer service in handling the tasks to be assigned to the ability prediction model, realize data closure, optimize the accuracy of the prediction of the ability prediction model, and thus adapt to the ever-changing customer service environment.

[0060] Corresponding to the above method embodiment, the present application also provides a task allocation device based on customer service capability prediction, referring to Figure 2A task allocation device based on customer service capability prediction provided in the present application includes: a slow log collection module 201, a history analysis module 202, a query analysis module 203 and a test module 204.

[0061] The slow log collection module 201 is used to obtain the historical task data of each customer service representative, and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data.

[0062] The history analysis module 202 is used to obtain the tasks to be assigned and extract the current task features in the tasks to be assigned.

[0063] The query analysis module 203 is used to input the current task characteristics and the historical ability scores of each customer service into a preset ability prediction model, and obtain the predicted ability scores of each customer service for handling the tasks to be assigned output by the ability prediction model.

[0064] The testing module 204 is used to obtain the current working status of each customer service representative, and based on the predicted ability score of each customer service representative in processing the task to be assigned and the current working status, assign the task to be assigned to the customer service representative with the highest matching degree for processing.

[0065] In order to monitor the operating status of the entire system in real time and adjust the task allocation strategy according to real-time data to adapt to the ever-changing customer service environment, in a feasible embodiment of the present application, the above-mentioned task allocation device based on customer service capability prediction also includes a real-time monitoring module and a data feedback module.

[0066] The real-time monitoring module is used to monitor the recent key features of customer service processing in real time, and dynamically adjust the customer service capacity weight based on the recent key features.

[0067] The data feedback module is used to feed back the actual performance data of the customer service in handling the assigned tasks to the capability prediction model, so that the capability prediction model can adjust parameters based on the actual performance data.

[0068] like Figure 3 As shown, an embodiment of the present application provides an electronic device, including a processor 311, a communication interface 312, a memory 313 and a communication bus 314, wherein the processor 311, the communication interface 312, and the memory 313 communicate with each other through the communication bus 314.

[0069] The memory 313 is used to store computer programs.

[0070] In one embodiment of the present application, the processor 311 is used to execute the program stored in the memory 313 to implement the task allocation method based on customer service capability prediction provided by any of the aforementioned method embodiments, including:

[0071] Obtain the historical task data of each customer service representative, and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data;

[0072] Obtain tasks to be assigned, and extract current task features from the tasks to be assigned;

[0073] Input the current task characteristics and the historical ability scores of each customer service representative into a preset ability prediction model, and obtain the predicted ability scores of each customer service representative for handling the tasks to be assigned output by the ability prediction model;

[0074] Get the current work status of each customer service representative, and assign the tasks to be assigned to the customer service representative with the highest matching degree for processing based on their predicted ability scores and current work status for processing the tasks to be assigned.

[0075] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the task allocation method based on customer service capability prediction provided in any of the aforementioned method embodiments are implemented.

[0076] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0078] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0079] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A task allocation method based on customer service capability prediction, characterized in that: include: Obtain the historical task data of each customer service representative, and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data; Obtaining tasks to be assigned, and extracting current task features from the tasks to be assigned; Input the current task characteristics and the historical ability scores of each customer service representative into a preset ability prediction model, and obtain the predicted ability scores of each customer service representative for processing the to-be-assigned task output by the ability prediction model; The current working status of each customer service is obtained, and based on the predicted ability score of each customer service for processing the task to be assigned and the current working status, the task to be assigned is assigned to the customer service with the highest matching degree for processing.

2. The task allocation method based on customer service capability prediction according to claim 1 is characterized in that: Obtaining tasks to be assigned and extracting current task features in the tasks to be assigned, including: Analyze the tasks to be assigned by natural language processing technology to obtain the task description length and keywords of the tasks to be assigned; Based on the length of the task description and the keywords, the complexity of the task to be assigned is calculated by a preset scoring function; The priority factor corresponding to the task to be assigned is extracted.

3. The task allocation method based on customer service capability prediction according to claim 1 is characterized in that: The capability prediction model is obtained by training the gradient boosting decision tree algorithm based on a training data set; the training data set includes a data combination of the customer service's historical capability score and the predicted capability score for processing the task to be assigned.

4. The task allocation method based on customer service capability prediction according to claim 1 is characterized in that: The current working status includes the online status of the customer service and the current load score.

5. The task allocation method based on customer service capability prediction according to claim 4 is characterized in that: Based on the predicted ability score of each customer service representative for processing the task to be assigned and the current working status, the task to be assigned is assigned to the customer service representative with the highest matching degree for processing, including: Among all the customer services whose online status is online, based on the predicted ability score of each customer service for processing the task to be assigned and the current load score, calculate the utility value of assigning the task to be assigned to each customer service for processing, take the customer service with the highest utility value as the customer service with the highest matching degree, and assign the task to be assigned to the customer service with the highest matching degree for processing.

6. The task allocation method based on customer service capability prediction according to claim 5 is characterized in that: Based on the predicted ability score of each customer service for processing the to-be-assigned task and the current load score, calculating the utility value of assigning the to-be-assigned task to each customer service for processing, includes: Obtain the capacity weight and load weight of each customer service representative; The product of the predicted ability score of each customer service representative for processing the task to be assigned and the corresponding ability weighted number is taken as the first score, the product of the current load score of each customer service representative and the corresponding load weighted number is taken as the second score, and the sum of the first score and the second score is taken as the utility value.

7. The task allocation method based on customer service capability prediction according to claim 6 is characterized in that: After assigning the task to be assigned to the customer service with the highest matching degree for processing, the method further includes: Monitoring recent key features of customer service processing services, and dynamically adjusting the customer service capability weight based on the recent key features; The actual performance data of the customer service in processing the task to be assigned is fed back to the capability prediction model, so that the capability prediction model adjusts parameters based on the actual performance data.

8. A task allocation device based on customer service capability prediction, characterized in that: The device comprises: A historical capability evaluation module is used to obtain historical task data of each customer service representative and calculate the historical capability score of each customer service representative on various tasks based on the historical key features corresponding to the historical task data; A task feature extraction module is used to obtain tasks to be assigned and extract current task features in the tasks to be assigned; A prediction capability evaluation module, used to input the current task characteristics and the historical capability scores of each customer service representative into a preset capability prediction model, and obtain the prediction capability scores of each customer service representative for handling the to-be-assigned task output by the capability prediction model; The dynamic task allocation module is used to obtain the current working status of each customer service, and based on the predicted ability score of each customer service in processing the task to be allocated and the current working status, allocate the task to be allocated to the customer service with the highest matching degree for processing.

9. An electronic device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor coupled to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to implement the task allocation method based on customer service capacity prediction as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the task allocation method based on customer service capability prediction as described in any one of claims 1-7.

Images