Incoming line seat distribution management method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to an incoming line seat distribution management method and device, computer equipment and a storage medium, and the method comprises the steps: receiving an incoming call incoming line request of a user wireless bandwidth; calling an artificial intelligence robot to carry out robot wiring operation on the incoming call incoming line request to obtain a robot wiring result; if the wiring result of the robot does not solve the incoming call and incoming line request of the wireless bandwidth of the user, the incoming call and incoming line request of the wireless bandwidth of the user is transferred to a centralized seat for centralized wiring operation, and a centralized wiring result is obtained; and if the concentrated wiring result still does not solve the incoming call and incoming call request of the user wireless bandwidth, transferring the incoming call and incoming call request of the user wireless bandwidth to a front seat to carry out front wiring operation until the incoming call and incoming call request of the user wireless bandwidth is completely solved. According to the invention, the case report communication time of the user can be greatly reduced, and the communication cost is reduced; and meanwhile, the communication efficiency of the seats can be greatly improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly to an incoming call agent allocation management method, device, computer device, and storage medium. Background Art

[0002] Agent service is an important way for a call center system to provide services to customers. Agent service refers to the process in which an agent provides corresponding services to customers through the support system of the call center.

[0003] There are mainly two ways for traditional call centers to allocate agents to incoming calls: one is to randomly allocate idle agents, and the other is to allocate a fixed agent queue to a divided customer group.

[0004] However, the applicant has found that the agent allocation methods of traditional call centers are not applicable to scenarios where dialects are used. As an example, when the alarm caller is from a township or remote area, there are problems with their Mandarin communication, and they often speak with a certain dialect, which leads to certain understanding problems during the call, brings communication costs, and the user experience is also relatively poor. Summary of the Invention

[0005] The purpose of the embodiments of this application is to propose an incoming call agent allocation management method, device, computer device, and storage medium to solve the problem that the agent allocation methods of traditional call centers are not applicable to scenarios where dialects are used.

[0006] To solve the above technical problems, the embodiments of this application provide an incoming call agent allocation management method, which adopts the following technical solutions:

[0007] Receive an incoming call request for the user's wireless bandwidth;

[0008] Call an artificial intelligence robot to perform a robot connection operation on the incoming call request to obtain a robot connection result;

[0009] If the robot connection result does not solve the incoming call request for the user's wireless bandwidth, then transfer the incoming call request for the user's wireless bandwidth to a centralized agent for centralized connection operation to obtain a centralized connection result;

[0010] If the centralized connection result still does not solve the incoming call request for the user's wireless bandwidth, then transfer the incoming call request for the user's wireless bandwidth to a front-end agent for front-end connection operation until the incoming call request for the user's wireless bandwidth is completely solved.

[0011] Further, if the centralized connection result still fails to resolve the incoming call request for the user's wireless bandwidth, the incoming call request for the user's wireless bandwidth is transferred to the front desk operator for front desk connection operation until the incoming call request for the user's wireless bandwidth is completely resolved. The specific steps include the following steps:

[0012] Obtain the mobile phone number location corresponding to the user's wireless bandwidth, and transfer the incoming call request for the user's wireless bandwidth to the front desk operator corresponding to the mobile phone number location for front desk connection operation until the incoming call request for the user's wireless bandwidth is completely resolved.

[0013] Further, the steps of obtaining the mobile phone number location corresponding to the user's wireless bandwidth, and transferring the incoming call request for the user's wireless bandwidth to the front desk operator corresponding to the mobile phone number location for front desk connection operation until the incoming call request for the user's wireless bandwidth is completely resolved, specifically include the following steps:

[0014] During the matching process of the front desk operator, combining the business capabilities and knowledge reserves of the front desk operator, a weighted scoring mechanism is used to evaluate the comprehensive capabilities of the front desk operator;

[0015] Send the comprehensive capabilities of the front desk operator to the call routing system, and adjust the call distribution strategy in real time according to the dynamic routing algorithm;

[0016] According to the call distribution strategy, allocate the best front desk operator for the incoming call request of the user's wireless bandwidth for front desk connection operation.

[0017] Further, if the centralized connection result still fails to resolve the incoming call request for the user's wireless bandwidth, the incoming call request for the user's wireless bandwidth is transferred to the front desk operator for front desk connection operation until the incoming call request for the user's wireless bandwidth is completely resolved. The specific steps include the following steps:

[0018] Obtain the voice data in the user's incoming call request;

[0019] Call the dialect recognition model, input the voice data into the dialect recognition model for dialect recognition operation, and obtain the dialect location;

[0020] Transfer the incoming call request for the user's wireless bandwidth to the front desk operator corresponding to the dialect location for front desk connection operation until the incoming call request for the user's wireless bandwidth is completely resolved.

[0021] Further, after the step of obtaining the voice data in the user's incoming call request and before the step of calling the dialect recognition model and inputting the voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution, the following steps are further included:

[0022] Perform a preprocessing operation on the voice data to obtain preprocessed voice data;

[0023] The step of calling the dialect recognition model, inputting the voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution specifically includes the following steps:

[0024] Input the preprocessed voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution.

[0025] Further, the step of calling the dialect recognition model, inputting the voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution specifically includes the following steps:

[0026] Adopt Mel Frequency Cepstral Coefficients and Linear Predictive Coding technology to obtain the spectral features and vocal tract features of the voice data;

[0027] Input the spectral features and the vocal tract features into a pre-trained dialect recognition model, and judge the dialect type used by the user according to the Convolutional Neural Network and Long Short-Term Memory Network;

[0028] Obtain the dialect attribution according to the dialect type.

[0029] To solve the above technical problems, an incoming call seat allocation management device is further provided in an embodiment of the present application, adopting the following technical solutions:

[0030] A request receiving module, configured to receive an incoming call request of the user's wireless bandwidth;

[0031] A robot connection module, configured to call an artificial intelligence robot to perform a robot connection operation on the incoming call request to obtain a robot connection result;

[0032] A centralized connection module, configured to transfer the incoming call request of the user's wireless bandwidth to a centralized seat for centralized connection operation to obtain a centralized connection result if the robot connection result does not solve the incoming call request of the user's wireless bandwidth;

[0033] A pre-connection module, configured to transfer the incoming call request of the user's wireless bandwidth to a pre-seat for pre-connection operation until the incoming call request of the user's wireless bandwidth is completely solved if the centralized connection result still does not solve the incoming call request of the user's wireless bandwidth.

[0034] Furthermore, the front wiring module includes:

[0035] The front-end connection submodule is used to obtain the mobile phone number location corresponding to the user's wireless bandwidth, and transfer the incoming call request of the user's wireless bandwidth to the front-end seat corresponding to the mobile phone number location for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

[0036] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0037] The system comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned incoming line seat allocation management method when executing the computer-readable instructions.

[0038] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0039] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the above-mentioned incoming line seat allocation management method are implemented.

[0040] The present application provides a method for managing the allocation of incoming call seats, including: receiving an incoming call request of a user's wireless bandwidth; calling an artificial intelligence robot to perform a robot connection operation on the incoming call request to obtain a robot connection result; if the robot connection result does not solve the incoming call request of the user's wireless bandwidth, then the incoming call request of the user's wireless bandwidth is transferred to a centralized seat for centralized connection operation to obtain a centralized connection result; if the centralized connection result still does not solve the incoming call request of the user's wireless bandwidth, then the incoming call request of the user's wireless bandwidth is transferred to a front seat for front connection operation until the incoming call request of the user's wireless bandwidth is completely solved. Compared with the prior art, the present application uses an incoming call task assignment scheme that matches the seat's native place with the user's mobile phone number location, which can not only greatly reduce the user's reporting communication time and communication costs; at the same time, because the communication time is reduced, the waiting time for other users to come in can be reduced, greatly improving the communication efficiency of the seat. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the solutions in this application, the following will briefly introduce the accompanying drawings required for the description of the embodiments of this application. Obviously, the accompanying drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0042] Figure 1 is an exemplary system architecture diagram to which this application can be applied;

[0043] Figure 2 is the implementation flowchart of the incoming call seat allocation management method provided by the embodiments of this application;

[0044] Figure 3 is the structural schematic diagram of the incoming call seat allocation management device provided by the embodiments of this application;

[0045] Figure 4 is the structural schematic diagram of an embodiment of a computer device according to this application. Detailed implementation manners

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above accompanying drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above accompanying drawings are used to distinguish different objects and not to describe a specific order.

[0047] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0048] To enable those skilled in the technical field to better understand the solutions of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings.

[0049] Such as Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102, and a server 103. The terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. The network 102 is a medium for providing a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0050] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications may be installed on the terminal device 101, such as a web browser application, a shopping application, a search application, an instant messaging tool, an email client, a social platform software, etc.

[0051] The terminal device 101 may be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012, or the mobile phone 1013, the terminal device 101 may also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop portable computer, a desktop computer, etc.

[0052] The server 103 may be a server providing various services, such as a background server supporting the pages displayed on the terminal device 101.

[0053] It should be noted that the incoming call seat allocation management method provided by the embodiments of the present application is generally executed by the server / terminal device. Correspondingly, the incoming call seat allocation management device is generally set in the server / terminal device.

[0054] It should be understood that Figure 1 the numbers of the terminal device, the network, and the server in

[0055] Continue to refer to Figure 2 , which shows a flowchart of an embodiment of the incoming call seat allocation management method according to the present application. The incoming call seat allocation management method includes: step S201, step S202, step S203, and step S204.

[0056] In step S201, receive an incoming call request for the user's wireless bandwidth.

[0057] In the embodiments of the present application, the system first receives wireless bandwidth service requests from users. These requests include, but are not limited to, opening, upgrading, reporting faults, and consulting fees for wireless bandwidth. Users initiate these requests through various channels such as telephone, online chat tools, and mobile applications. After receiving these requests, the system will make preliminary records and classifications to prepare for subsequent processing.

[0058] In step S202, an artificial intelligence robot is called to perform a robot connection operation on the incoming call request, and a robot connection result is obtained.

[0059] In the embodiments of the present application, when a user's IB makes an incoming call, a robot is directly used for connection during this process. During daily training, the robot will use artificial intelligence technology to self-learn languages from various regions. Although it cannot completely solve the communication barriers of dialects, it can divert some users who can communicate in standard Mandarin and can also undertake the communication tasks of some dialect users, reducing the workload of human agents.

[0060] In the embodiments of the present application, the system will automatically call a pre-trained artificial intelligence robot to perform a connection operation according to the type of user request. These robots have capabilities such as natural language processing, speech recognition, and machine learning, and can interact with users simply, answer some common questions, or perform some standardized operations. For example, for consulting the fees of wireless bandwidth, the robot can immediately provide accurate fee information. After the robot processes the request, a connection result will be generated, indicating whether the user's problem has been successfully solved.

[0061] In step S203, if the robot connection result does not solve the incoming call request for the user's wireless bandwidth, the incoming call request for the user's wireless bandwidth will be transferred to a centralized agent for centralized connection operation, and a centralized connection result is obtained.

[0062] In the embodiments of the present application, the robot is unable to communicate relevant claim information, and the user can choose to directly transfer to the centralized human agent. After the centralized human agent intervenes, the situation of the user's insured subject will be communicated in detail.

[0063] In the embodiments of the present application, if the robot cannot completely solve the user's problem (for example, the user's request involves complex fault troubleshooting or personalized service requirements), the system will transfer the user's request to the centralized agent. The centralized agent usually consists of a group of professional customer service personnel who have more in-depth knowledge of wireless bandwidth and more rich processing experience. These agent personnel will centrally process those requests that the robot cannot solve, and provide more professional solutions through further inquiries and diagnoses. After the centralized agent processes the request, a connection result will also be generated.

[0064] In step S204, if the centralized wiring result still fails to resolve the incoming call request for the user's wireless bandwidth, the incoming call request for the user's wireless bandwidth is transferred to the front-end seat for front-end wiring operation until the incoming call request for the user's wireless bandwidth is completely resolved.

[0065] In the embodiment of the present application, if the centralized human seat still cannot recognize, the incoming call information can be transferred to the front-end workplace seat with the same jurisdiction as the incoming call user, so as to quickly conduct effective communication. The following is the implementation plan on how to transfer:

[0066] 1) Two to three front-end IB seats are configured in each prefecture-level city. The front-end seats need to be local personnel. The purpose of this setting is to solve the problem of dialect communication;

[0067] 2) When encountering users with dialect communication barriers, the seat area will be matched according to the jurisdiction information of the user's mobile phone incoming call to maximize the communication efficiency;

[0068] 3) The front-end seats will also normally access other incoming report information during the daily process, thus avoiding waste of manpower. At the same time, setting up the front-end workplace can not only reduce the labor cost, but also reduce the potential risks caused by centralized office. For example, in the case where the centralized workplace becomes unavailable due to infrastructure failures and other factors, resulting in the unavailability of the IB seat team, the risks can be dispersed, achieving multiple benefits at one stroke.

[0069] If the centralized seat also cannot completely solve the user's problem (for example, the user's request involves high-level technical support or requires coordination with other departments), the system will transfer the user's request to the front-end seat. The front-end seats usually consist of higher-level customer service personnel or technical experts who have the ability to handle complex problems and coordinate resources. These seat personnel will communicate with the user in depth, understand the specific situation of the problem, and mobilize internal or external resources of the company to solve the problem. Through the efforts of the front-end seats, the user's problem will ultimately be completely solved, ensuring that the user obtains a satisfactory service experience.

[0070] In the embodiment of the present application, the entire process reflects a service processing strategy from automation to manual, from simple to complex, and from standardization to personalization, which can efficiently and accurately solve the service requests for the user's wireless bandwidth.

[0071] In an embodiment of the present application, a method for inbound seat allocation management is provided, including: receiving an inbound request for a user's wireless bandwidth; invoking an artificial intelligence robot to perform a robot connection operation on the inbound request for the wireless bandwidth to obtain a robot connection result; if the robot connection result fails to resolve the inbound request for the user's wireless bandwidth, then transferring the inbound request for the user's wireless bandwidth to a centralized seat for a centralized connection operation to obtain a centralized connection result; if the centralized connection result still fails to resolve the inbound request for the user's wireless bandwidth, then transferring the inbound request for the user's wireless bandwidth to a front-end seat for a front-end connection operation until the inbound request for the user's wireless bandwidth is completely resolved. Compared with the prior art, through the inbound task assignment scheme that matches the seat origin and the location of the user's mobile phone number, we can not only greatly reduce the reporting and communication time of users and lower the communication cost; at the same time, because the communication time is reduced, the waiting time for other users to enter the line can be reduced, and the communication efficiency of the seat is greatly improved.

[0072] In some alternative implementation manners of the embodiment of the present application, the step of, if the centralized connection result still fails to resolve the inbound request for the user's wireless bandwidth, then transferring the inbound request for the user's wireless bandwidth to a front-end seat for a front-end connection operation until the inbound request for the user's wireless bandwidth is completely resolved, specifically includes the following steps:

[0073] Obtain the location of the mobile phone number corresponding to the user's wireless bandwidth, and transfer the inbound request for the user's wireless bandwidth to the front-end seat corresponding to the location of the mobile phone number for a front-end connection operation until the inbound request for the user's wireless bandwidth is completely resolved.

[0074] In an embodiment of the present application, the system first extracts the associated mobile phone number from the user's wireless bandwidth service request. This mobile phone number is actively provided by the user when initiating the service request and is also automatically recognized and extracted by the system (for example, if the request is initiated through an application bound to the user's mobile phone number).

[0075] In an embodiment of the present application, after extracting the mobile phone number, the system uses a database or API to query the location information of the mobile phone number. This database or API usually contains the correspondence between the mobile phone number and the geographical location (such as province, city). Through the query, the system can obtain the precise location information of the user's mobile phone number.

[0076] In an embodiment of the present application, after obtaining the location information of the user's mobile phone number, the system allocates service resources according to this information. Specifically, the system transfers the user's wireless bandwidth service request to the front-end seat corresponding to the location of the mobile phone number.

[0077] In the embodiments of the present application, these front - end seats are usually customer service personnel who have received specialized training. They not only possess the professional knowledge to handle wireless bandwidth service requests but also are familiar with the policies, regulations, and customs of specific regions (such as the place of registration of the user's mobile phone number). Therefore, transferring the request to the front - end seat corresponding to the place of registration of the mobile phone number can ensure that users receive more accurate and professional services.

[0078] In the embodiments of the present application, after transferring the user's request to the front - end seat corresponding to the place of registration of the mobile phone number, these seat personnel will communicate deeply with the user to understand the specific situation of the problem and mobilize internal or external resources of the company to solve the problem. The front - end seat personnel will use their professional knowledge and understanding of local policies and regulations to provide personalized solutions for users. If the problem is relatively complex or requires coordination with other departments, the front - end seat personnel will actively contact the relevant departments to ensure that the problem is solved promptly and effectively.

[0079] In the embodiments of the present application, through the efforts of the front - end seat personnel, the system can ensure that the user's wireless bandwidth service request is completely solved, thereby providing a satisfactory service experience for the user.

[0080] In some optional implementation manners of the embodiments of the present application, the steps of obtaining the place of registration of the mobile phone number corresponding to the user's wireless bandwidth and transferring the incoming call request of the user's wireless bandwidth to the front - end seat corresponding to the place of registration of the mobile phone number for front - end connection operation until the incoming call request of the user's wireless bandwidth is completely solved specifically include the following steps:

[0081] In the matching process of the front - end seat, a weighted scoring mechanism is adopted in combination with the business capabilities and knowledge reserves of the front - end seat to evaluate the comprehensive capabilities of the front - end seat;

[0082] Send the comprehensive capabilities of the front - end seat to the call routing system and adjust the call distribution strategy in real - time according to the dynamic routing algorithm;

[0083] Allocate the best front - end seat for the incoming call request of the user's wireless bandwidth for front - end connection operation according to the call distribution strategy.

[0084] In the embodiments of the present application, the system first collects relevant information on the business capabilities and knowledge reserves of each front - end agent. This information includes, but is not limited to, the training records of the agent, historical service records, user feedback, professional skills test scores, etc. After collecting this information, the system uses a weighted scoring mechanism to evaluate the comprehensive capabilities of each front - end agent. This mechanism assigns different weights according to different evaluation indicators (such as the degree of professional knowledge mastery, problem - solving ability, user communication skills, work efficiency, etc.) and gives corresponding scores based on the performance of the agent in these indicators. Through the weighted scoring mechanism, the system can objectively evaluate the comprehensive capabilities of each front - end agent, thus providing a reliable basis for subsequent call distribution.

[0085] In the embodiments of the present application, after evaluating the comprehensive capabilities of the front - end agents, the system sends this information to the call routing system. The call routing system is the core component responsible for allocating users' call requests to different agents. After receiving the comprehensive capability information of the front - end agents, the call routing system uses a dynamic routing algorithm to adjust the call distribution strategy in real - time. This algorithm dynamically selects the best - suited agent for call distribution based on various factors such as the comprehensive capabilities of the agent, the current workload, and the type of user requests. Through the dynamic routing algorithm, the system can ensure that users' call requests are always allocated to the most suitable front - end agent to handle the request, thereby improving service efficiency and quality.

[0086] In the embodiments of the present application, after determining the call distribution strategy, the system allocates the best - suited front - end agent for the incoming call request of the user's wireless bandwidth for front - end connection operation. The allocated front - end agent immediately establishes contact with the user, understands the specific situation of the problem, and provides a personalized solution for the user based on their professional knowledge and experience. If the problem is relatively complex or requires coordination with other departments, the front - end agent will actively contact the relevant departments to ensure that the problem is resolved promptly and effectively.

[0087] In the embodiments of the present application, the system can ensure that the user's wireless bandwidth service requests are quickly and accurately responded to and processed, thereby improving user satisfaction and loyalty.

[0088] In some optional implementation manners of the embodiments of the present application, the above - mentioned step of, if the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth, then transferring the incoming call request of the user's wireless bandwidth to the front - end agent for front - end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved, specifically includes the following steps:

[0089] Obtain the voice data in the user's incoming call request;

[0090] Call the dialect recognition model, input the voice data into the dialect recognition model for dialect recognition operation, and obtain the dialect place of origin.

[0091] Transfer the incoming call request of the user's wireless bandwidth to the corresponding front-end seat according to the dialect place of origin for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

[0092] In the embodiment of the present application, the system will first receive the wireless bandwidth service request initiated by the user through a telephone or a voice chat tool. These requests contain the user's voice data, that is, the service requirements or problems expressed by the user in spoken language. The system will capture and save these voice data through voice recognition technology or a recording device for subsequent processing.

[0093] In the embodiment of the present application, after obtaining the user's voice data, the system will call a pre-trained dialect recognition model. This model has the ability to recognize multiple dialects and can judge the type of dialect used by the user according to the characteristics of the voice data. After the system inputs the voice data into the dialect recognition model, the model will process and analyze the voice data, extract the dialect features in the voice, and compare them with the dialect library in the model to determine the dialect place of origin of the user. The dialect recognition model can not only recognize the type of dialect used by the user, but also further determine the user's geographical location (such as province, city or region) according to the subtle differences of the dialect, so as to provide more accurate information for subsequent call allocation.

[0094] In the embodiment of the present application, after determining the dialect place of origin of the user, the system will allocate service resources according to this information. Specifically, the system will transfer the wireless bandwidth service request of the user to the corresponding front-end seat according to the dialect place of origin. These front-end seats are usually customer service personnel who have received special training. They not only have the professional knowledge to handle wireless bandwidth service requests, but also are familiar with the pronunciation and grammar of specific dialects. Therefore, transferring the request to the front-end seat corresponding to the dialect place of origin can ensure that the user receives more accurate and fluent service. The front-end seat personnel will communicate with the user in depth to understand the specific situation of the problem, and provide personalized solutions for the user according to their professional knowledge and experience. If the problem is more complex or requires coordination with other departments, the front-end seat will actively contact the relevant departments to ensure that the problem is solved in a timely and effective manner.

[0095] In the embodiment of the present application, it can ensure that the wireless bandwidth service request of the user is quickly and accurately responded to and processed, thereby improving the user's satisfaction and loyalty. At the same time, this also reflects the accurate identification of user needs and the precise allocation of service resources, aiming to improve service efficiency and quality.

[0096] In some alternative implementation manners of the embodiments of the present application, after the step of obtaining the voice data in the user incoming call request and before the step of calling the dialect recognition model and inputting the voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution, the following steps are further included:

[0097] Perform a preprocessing operation on the voice data to obtain preprocessed voice data;

[0098] The step of calling the dialect recognition model and inputting the voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution specifically includes the following steps:

[0099] Input the preprocessed voice data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution.

[0100] In the embodiments of the present application, the preprocessing operation may specifically be:

[0101] (1) Noise cancellation: The original voice data contains various background noises, such as wind noise, vehicle noise, human voice interference, etc. The purpose of noise cancellation is to reduce or remove these unnecessary noises to improve the clarity of the voice signal. This can be achieved by using filters, noise suppression algorithms, or machine learning-based noise cancellation techniques;

[0102] (2) Volume normalization: Due to differences in recording devices, environmental conditions, or the distance between the speaker and the microphone, the volume levels of the original voice data can vary greatly. Volume normalization aims to adjust the volume of the voice signal to a unified level to ensure consistency and stability in subsequent processing steps. This usually involves scaling the amplitude of the voice signal to conform to a specific volume range;

[0103] (3) Endpoint detection: Endpoint detection is the process of determining the start and end positions of the valid voice part in the voice signal. It helps to remove the silent parts and irrelevant noises, thereby reducing the computational amount and storage requirements in subsequent processing steps. Endpoint detection is usually implemented based on energy thresholds, spectral features, or machine learning algorithms;

[0104] (4) Pre-emphasis: Pre-emphasis is a technique for enhancing high-frequency components, which helps to improve the spectral characteristics of the voice signal. Since the voice signal is prone to noise and attenuation in the high-frequency part, pre-emphasis can compensate for this loss by increasing the amplitude of the high-frequency components. This is usually achieved by applying a high-pass filter;

[0105] (5) Framing and Windowing: The speech signal is continuously varying, but most speech processing algorithms are based on the short-term stationary assumption. Therefore, it is necessary to divide the speech signal into a series of short time segments (called frames) and process each frame. Framing usually involves dividing the speech signal into fixed-length or overlapping windows. Windowing is then to apply a window function (such as Hamming window, Hanning window, etc.) to each frame to reduce the discontinuity at the frame edges;

[0106] (6) Fast Fourier Transform (FFT): Although FFT itself is not a preprocessing step, in many speech processing tasks such as spectrum analysis, feature extraction, etc., FFT operation needs to be performed on the speech signal. FFT can convert the time-domain signal into a frequency-domain signal, thus revealing the spectral characteristics of the speech signal.

[0107] In the embodiments of the present application, through the above preprocessing operations, preprocessed speech data can be obtained, and these data have higher quality and consistency, and are more suitable for subsequent speech recognition, dialect recognition and other processing steps.

[0108] In some optional implementation manners of the embodiments of the present application, in the step of calling the dialect recognition model and inputting the speech data into the dialect recognition model for dialect recognition operation to obtain the dialect attribution, the following specific steps are included:

[0109] Adopt Mel Frequency Cepstral Coefficients and Linear Predictive Coding technology to obtain the spectral features and vocal tract features of the speech data;

[0110] Input the spectral features and vocal tract features into a pre-trained dialect recognition model, and judge the dialect type used by the user according to the convolutional neural network and long short-term memory network;

[0111] Obtain the dialect attribution according to the dialect type.

[0112] In the embodiments of this application, first, the voice data called in by the user is preprocessed, including removing noise, normalizing the volume, etc., to ensure the accuracy of subsequent analysis. Then, the Mel Frequency Cepstral Coefficient (MFCC) technology is used to extract the spectral features of the voice. MFCC is a feature widely used in speech and audio signal processing. It simulates the non-linear perception of frequency by the human ear and can effectively capture the pitch and timbre information in speech. By calculating the Short-Time Fourier Transform (STFT) of the speech signal, then mapping the spectrum to the Mel scale, and then through logarithmic transformation and Discrete Cosine Transform (DCT), the MFCC features are finally obtained. At the same time, the Linear Predictive Coding (LPC) technology is used to obtain the vocal tract features of the voice. LPC is a parametric method based on the speech generation model, which assumes that the speech signal is the convolution of the current glottal excitation signal and the vocal tract response. By solving the linear prediction equation, the transfer function parameters of the vocal tract can be obtained, and these parameters reflect the shape and formant characteristics of the vocal tract.

[0113] In the embodiments of this application, after extracting the spectral features and vocal tract features of the voice, these features are combined to form a multi-dimensional feature vector. This feature vector contains rich speech information and is sufficient for the recognition of dialect types. Next, this feature vector is input into a pre-trained dialect recognition model. This model adopts deep learning technology, especially the combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). CNN is good at capturing local features and spatial structure information, while LSTM is good at dealing with the time-dependent relationship in sequence data. Through the combination of these two networks, the model can efficiently learn and utilize the time and spatial information in the speech features, so as to accurately judge the dialect type used by the user.

[0114] In the embodiments of this application, the system can accurately identify the dialect type used by the user and determine the origin of the dialect, thus providing strong support for subsequent services.

[0115] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0116] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0117] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disc, a Read-Only Memory (ROM), or a Random Access Memory (RAM), etc.

[0118] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the indication of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order restriction, and they can be executed in other orders. Moreover, at least some of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages do not necessarily have to be executed at the same time, but can be executed at different times, and their execution order does not necessarily have to be sequential, but can be executed alternately or alternately with at least some of the other steps or sub-steps or stages of the other steps.

[0119] Further reference Figure 3 to Figure 2 As an implementation of the method shown above, an embodiment of an incoming call seat allocation management device is provided in this application. This device embodiment corresponds to the method embodiment shown in Figure 2 and can be specifically applied to various electronic devices.

[0120] As shown in Figure 3 , the incoming call seat allocation management device 200 in the embodiment of this application includes:

[0121] A request receiving module 210, configured to receive an incoming call request for the user's wireless bandwidth;

[0122] A robot connection module 220, configured to call an artificial intelligence robot to perform a robot connection operation on the incoming call request and obtain a robot connection result;

[0123] A centralized connection module 230, configured to transfer the incoming call request for the user's wireless bandwidth to a centralized seat for centralized connection operation and obtain a centralized connection result if the robot connection result fails to resolve the incoming call request for the user's wireless bandwidth;

[0124] The front-end connection module 240 is used to transfer the incoming call request of the user's wireless bandwidth to the front-end agent for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved if the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth.

[0125] In an embodiment of the present application, an incoming call agent allocation management device 200 is provided, including: a request receiving module 210 for receiving an incoming call request of the user's wireless bandwidth; a robot connection module 220 for calling an artificial intelligence robot to perform robot connection operation on the incoming call request to obtain a robot connection result; a centralized connection module 230 for transferring the incoming call request of the user's wireless bandwidth to a centralized agent for centralized connection operation to obtain a centralized connection result if the robot connection result fails to resolve the incoming call request of the user's wireless bandwidth; and a front-end connection module 240 for transferring the incoming call request of the user's wireless bandwidth to the front-end agent for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved if the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth. Compared with the prior art, in the present application, through the incoming call task assignment scheme of matching the agent's native place and the user's mobile phone number's location, we can not only greatly reduce the reporting and communication time of the user and lower the communication cost; at the same time, because the communication time is reduced, the waiting time for other users to make an incoming call can be reduced, and the communication efficiency of the agent is greatly improved.

[0126] In some optional implementation manners of the embodiment of the present application, the above-mentioned front-end connection module includes:

[0127] A front-end connection sub-module for obtaining the location of the mobile phone number corresponding to the user's wireless bandwidth and transferring the incoming call request of the user's wireless bandwidth to the front-end agent corresponding to the location of the mobile phone number for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

[0128] To solve the above technical problems, the embodiment of the present application also provides a computer device. For details, please refer to Figure 4 , Figure 4 which is the basic structural block diagram of the computer device in the embodiment of the present application.

[0129] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that communicate with each other via a system bus. It should be noted that only the computer device 300 with components 310 - 330 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of the present technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0130] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with the user through means such as a keyboard, a mouse, a remote control, a touchpad, or a voice control device.

[0131] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as the hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 300. Of course, the memory 310 can also include both the internal storage unit and the external storage device of the computer device 300. In the embodiments of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions for the incoming seat allocation management method. In addition, the memory 310 can also be used to temporarily store various types of data that have been output or will be output.

[0132] In some embodiments, the processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiments of the present application, the processor 320 is used to run the computer-readable instructions stored in the memory 310 or process data, such as running the computer-readable instructions of the incoming call agent allocation management method.

[0133] The network interface 330 may include a wireless network interface or a wired network interface, which is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0134] For the computer device provided in the present application, through the incoming call task assignment scheme that matches the native place of the agent and the location of the user's mobile phone number, we can not only greatly reduce the reporting communication time of users and lower the communication cost; at the same time, because the communication time is reduced, the waiting time for other users to make an incoming call can be reduced, greatly improving the communication efficiency of the agent.

[0135] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor, so that the at least one processor executes the steps of the incoming call agent allocation management method as described above.

[0136] For the computer-readable storage medium provided in the present application, through the incoming call task assignment scheme that matches the native place of the agent and the location of the user's mobile phone number, we can not only greatly reduce the reporting communication time of users and lower the communication cost; at the same time, because the communication time is reduced, the waiting time for other users to make an incoming call can be reduced, greatly improving the communication efficiency of the agent.

[0137] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0138] Obviously, the embodiments described above are only a part of the embodiments of this application, rather than all of them. The preferred embodiments of this application are shown in the accompanying drawings, but they do not limit the patent scope of this application. This application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of this application more thorough and comprehensive. Although this application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing specific embodiments, or perform equivalent replacements for some of the technical features. Any equivalent structure that makes use of the content of the specification and drawings of this application, directly or indirectly applied in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for managing incoming line seat allocation, characterized in that: The steps include: Receive incoming call requests from users’ wireless bandwidth; Invoke an artificial intelligence robot to perform a robot connection operation on the incoming call request to obtain a robot connection result; If the robot connection result does not solve the incoming call request of the user's wireless bandwidth, the incoming call request of the user's wireless bandwidth is transferred to a centralized seat for centralized connection operation to obtain a centralized connection result; If the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth, the incoming call request of the user's wireless bandwidth is transferred to the front seat for front connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

2. The method for managing incoming line seat allocation according to claim 1, characterized in that: If the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth, the incoming call request of the user's wireless bandwidth is transferred to the front seat for front connection operation until the incoming call request of the user's wireless bandwidth is completely resolved, the step specifically includes the following steps: The mobile phone number location corresponding to the user's wireless bandwidth is obtained, and the incoming call request of the user's wireless bandwidth is transferred to the front seat corresponding to the mobile phone number location for front connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

3. The method for managing incoming line seat allocation according to claim 2, characterized in that: The step of obtaining the mobile phone number location corresponding to the user's wireless bandwidth, and transferring the incoming call request of the user's wireless bandwidth to the front seat corresponding to the mobile phone number location for front connection operation until the incoming call request of the user's wireless bandwidth is completely resolved, specifically includes the following steps: In the matching process of the front seats, the comprehensive ability of the front seats is evaluated by using a weighted scoring mechanism in combination with the business ability and knowledge reserve of the front seats; Sending the comprehensive capabilities of the front-end agents to a call routing system and adjusting the call distribution strategy in real time according to a dynamic routing algorithm; According to the call distribution strategy, the best front-end seat is allocated for the incoming call request of the user's wireless bandwidth to perform the front-end connection operation.

4. The method for managing incoming line seat allocation according to claim 1, characterized in that: If the centralized connection result still fails to resolve the incoming call request of the user's wireless bandwidth, the incoming call request of the user's wireless bandwidth is transferred to the front seat for front connection operation until the incoming call request of the user's wireless bandwidth is completely resolved, the step specifically includes the following steps: Acquire the voice data in the incoming call request of the user; Calling a dialect recognition model, inputting the voice data into the dialect recognition model to perform a dialect recognition operation, and obtaining a dialect attribution; The incoming call request of the user's wireless bandwidth is transferred to the front-end seat corresponding to the dialect attribution place for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

5. The method for managing incoming line seat allocation according to claim 4, characterized in that: After the step of obtaining the voice data in the user's incoming call request and before the step of calling the dialect recognition model, inputting the voice data into the dialect recognition model for dialect recognition operation, and obtaining the dialect attribution, the following steps are also included: Performing a preprocessing operation on the voice data to obtain preprocessed voice data; The step of calling the dialect recognition model, inputting the voice data into the dialect recognition model to perform dialect recognition operation, and obtaining the dialect attribution specifically includes the following steps: The pre-processed speech data is input into the dialect recognition model to perform dialect recognition operation to obtain the dialect belonging place.

6. The method for managing incoming line seat allocation according to claim 4, characterized in that: The step of calling the dialect recognition model, inputting the voice data into the dialect recognition model to perform dialect recognition operation, and obtaining the dialect attribution specifically includes the following steps: Using Mel frequency cepstral coefficients and linear predictive coding technology to obtain the frequency spectrum characteristics and vocal tract characteristics of the speech data; Inputting the frequency spectrum features and the vocal tract features into a pre-trained dialect recognition model, and determining the type of dialect used by the user based on a convolutional neural network and a long short-term memory network; The dialect location is obtained according to the dialect type.

7. A line seat allocation management device, characterized in that: include: A request receiving module, used to receive an incoming call request for a user's wireless bandwidth; A robot connection module is used to call an artificial intelligence robot to perform a robot connection operation on the incoming call request and obtain a robot connection result; A centralized connection module, for transferring the incoming call request of the user's wireless bandwidth to a centralized seat for centralized connection operation to obtain a centralized connection result if the robot connection result fails to solve the incoming call request of the user's wireless bandwidth; The front-end connection module is used to transfer the incoming call request of the user's wireless bandwidth to the front-end seat for front-end connection operation if the centralized connection result still fails to solve the incoming call request of the user's wireless bandwidth, until the incoming call request of the user's wireless bandwidth is completely solved.

8. The incoming line seat allocation management device according to claim 7, characterized in that: The front wiring module comprises: The front-end connection submodule is used to obtain the mobile phone number location corresponding to the user's wireless bandwidth, and transfer the incoming call request of the user's wireless bandwidth to the front-end seat corresponding to the mobile phone number location for front-end connection operation until the incoming call request of the user's wireless bandwidth is completely resolved.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the incoming line seat allocation management method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the incoming line seat allocation management method according to any one of claims 1 to 6 are implemented.

Images