Intelligent customer service scheduling method based on live codes and user characteristics

Abstract

The invention relates to an intelligent customer service scheduling method based on live codes and user features, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining user demands through the description of a user at a client, extracting the feature information of the user, generating live codes according to the user demands and features, enabling each live code to correspond to a virtual customer service session, and enabling the virtual customer service session to be a virtual customer service session. A user enters a customer service session in a live code scanning mode to initiate consultation, user feature data and customer service load data are collected in the code scanning process, the idle and busy degree of customer service is judged according to the collected customer service load data, feature construction is conducted on the collected user feature data and customer service load data, and feature vectors are obtained; and predicting the feature vector by using a prediction model to obtain a prediction score of a customer service processing request, selecting an optimal customer service representative to process the user request by integrating the customer service idle / busy degree and the feature prediction score, interacting the customer service representative with the customer through an online platform, collecting feedback data after the service is completed, and updating the model according to the feedback data.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to an intelligent customer service scheduling method based on live codes and user characteristics. Background Art

[0002] In traditional QR code-based customer service, one QR code is fixedly associated with a unique customer service staff. This scheduling method has the problem that the assigned customer service staff cannot accurately solve customer problems, and may cause uneven workloads among customer service staff and cause customers to wait too long to solve their problems.

[0003] However, with the development of artificial intelligence and big data technologies, intelligent customer service scheduling methods based on live codes and user characteristics have gradually attracted attention. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides an intelligent customer service scheduling method based on active codes and user characteristics to solve the problems raised in the above background technology.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: an intelligent customer service scheduling method based on active codes and user characteristics, specifically comprising the following steps:

[0006] Step 101: Obtain user needs through the user's description on the client, extract user feature information, generate corresponding live codes according to the user needs and features, and correspond each live code to a virtual customer service session;

[0007] Step 102: The user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process;

[0008] Step 103: pre-process and construct features of the collected user feature data and customer service load data to obtain a feature vector, use the prediction model to predict the feature vector, obtain the prediction score of each customer service request processing, and determine the busyness of each customer service;

[0009] Step 104: Select the best customer service representative to handle the user request based on the customer service busyness and feature prediction score. The selected customer service representative interacts with the customer through an online platform. After the service is completed, feedback data is collected and the model is updated based on the feedback data.

[0010] In a preferred embodiment, in step 101, the user's needs are obtained through the user's description on the client, and the user's characteristic information is extracted. A corresponding live code is generated according to the user's needs and characteristics, and each live code corresponds to a virtual customer service session. The specific steps are as follows:

[0011] Step A1, user feature extraction: The user inputs text, voice, or picture descriptions on the client to obtain the user's needs, and extracts the user's feature information while the user puts forward the needs;

[0012] Step A2, live code generation: dynamically generate live codes according to user needs and feature information, each live code corresponds to a virtual customer service session, and the live code contains an identifier based on user needs and features, and customer service representative identification information;

[0013] Step A3, live code distribution: the generated live code is distributed to users by generating a QR code, and a link is provided to be displayed on the website or App of the user;

[0014] Among them, in the step A3 of distributing the live code, the generated live code is distributed to the user by generating a QR code, and a link is provided to be displayed on the website or App of the user, further comprising the following steps:

[0015] Step A301: Use a QR code tool to convert the active code information into a QR code image and save it as an image file, and generate a link that can be accessed online, display the QR code on the website or App, and allow users to obtain the active code by scanning the QR code;

[0016] Step A302, providing a link: embed the live code information into a link, ensure that the link can directly access the virtual customer service session represented by the live code, publish content with the link on the website, App, and social media platform, and let the user click the link to directly enter the customer service session.

[0017] In a preferred embodiment, in step 102, the user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process. Based on the collected customer service load data, the busyness of each customer service is determined. The specific steps are as follows:

[0018] Step B1: After the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session;

[0019] Step B2, collecting user characteristic data: when a user enters a customer service session, the user's characteristic data is obtained through the user's login status, past interaction records, and personal information provided;

[0020] Step B3, collecting customer service load data: collecting the current workload data of each customer service representative, including the number of tasks being processed and the number of tasks waiting to be processed, and judging the busyness of each customer service representative based on the collected workload data;

[0021] Among them, in the step B1, after the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session, further comprising the following steps:

[0022] Step B101, live code identification: after receiving a request from a user to scan a live code, the system identifies and parses the live code, and determines the relevant information of the virtual customer service session represented by the live code according to the code or identifier of the live code;

[0023] Step B102: Connect the user to the corresponding virtual customer service session according to the information contained in the live code. After receiving the user's connection request, the virtual customer service session obtains the user's request information, including the user's problem description, specific needs, and personal information. According to the user's request information, the virtual customer service session system processes and responds through artificial intelligence technology.

[0024] In a preferred embodiment, in step 103, the collected user feature data and customer service load data are preprocessed and feature constructed to obtain a feature vector, and the feature vector is predicted using a prediction model to obtain a prediction score for each customer service processing request. The specific steps are as follows:

[0025] Step C1, feature engineering: extract key features from user feature data and customer service load data, and perform feature construction;

[0026] Step C2, feature vector construction: combine the cleaned and feature-engineered feature data into a feature vector as the input of the prediction model;

[0027] Step C3, model establishment: Select the linear regression model as the prediction model, and predict the target value by fitting a linear function. Set the predicted target value to be the waiting time of the customer service request, where the features include user features and request features. The specific calculation formula is as follows:

[0028]

[0029] in, is the predicted waiting time for customer service requests, ω0,ω1,ω2,...,ω n are the parameters of the model, representing the intercept and feature weights, x0,x1,x2,...,x n is the input feature, n is the number of samples;

[0030] Step C4: Use the mean square error loss function to measure the prediction error of the model, and train the model by minimizing the loss function. The specific calculation formula is as follows:

[0031]

[0032] Among them, MSE is the mean square error, which represents the mean of the squared error between the predicted value and the actual value, n is the number of samples, is the predicted value of the i-th sample, y i is the actual value of the i-th sample;

[0033] Step C5, prediction score calculation: After the model is trained, it is used to predict the waiting time of new customer service requests. Given a new input feature x, it is substituted into the model to obtain the predicted waiting time, which is expressed as the prediction score for processing the request.

[0034] In a preferred embodiment, in step 104, the best customer service representative is selected to handle the user request based on the customer service busyness and feature prediction score, and the selected customer service representative interacts with the customer through an online platform. After the service is completed, feedback data is collected and the model is updated according to the feedback data. The specific steps are as follows:

[0035] Step D1, comprehensive score: define a weight coefficient to balance the importance of the customer service's busyness and feature prediction score, and use the weighted average method to calculate the customer service's comprehensive score. The specific calculation formula is as follows:

[0036]

[0037] Among them, S i is the comprehensive rating of customer service i, is the feature prediction score, which indicates the score calculated by customer service i based on the features of the user request. i is the busyness score, which indicates the busyness score of customer service i. α is the weight coefficient, which is used to balance the importance of feature prediction score and busyness score.

[0038] Step D2: based on the comprehensive score, select the customer service representative with the highest score to handle the user request, assign the selected customer service representative to the user, and interact with the user through the online platform. After the service is completed, collect customer feedback data;

[0039] Step D3, model update: Use the collected feedback data in combination with the original training data to update and retrain the model. Use supervised learning methods, use the feedback data as labels, and adjust the model parameters to improve the model's prediction accuracy and generalization ability. Deploy the updated model to the production environment for use in the next round of customer service request processing.

[0040] The beneficial effects of the present invention are as follows: through the description of the user on the client, the user's needs are obtained, and the user's characteristic information is extracted; a live code is generated according to the user's needs and characteristics, and each live code corresponds to a virtual customer service session. The user enters the customer service session to initiate a consultation by scanning the live code, and collects user characteristic data and customer service load data during the scanning process; the busyness of the customer service is judged according to the collected customer service load data; the collected user characteristic data and customer service load data are subjected to feature construction to obtain a characteristic vector; the characteristic vector is predicted using a prediction model to obtain a prediction score for the customer service processing request; the best customer service representative is selected to process the user request based on the busyness of the customer service and the characteristic prediction score; the customer service representative interacts with the customer through an online platform; after the service is completed, feedback data is collected, and the model is updated according to the feedback data. The present invention improves the matching degree between the customer and the required customer service, and solves the problems of uneven customer service workload and low service efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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 those skilled in the art without creative work are within the scope of protection of this application.

[0043] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0044] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0045] Example 1

[0046] This embodiment provides Figure 1 An intelligent customer service scheduling method based on active codes and user characteristics is shown, which specifically includes the following steps:

[0047] Step 101: Obtain user needs through the user's description on the client, extract user feature information, generate corresponding live codes according to the user needs and features, and correspond each live code to a virtual customer service session;

[0048] Step 102: The user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process. Based on the collected customer service load data, the busyness of each customer service is determined;

[0049] Step 103: pre-process and construct features of the collected user feature data and customer service load data to obtain a feature vector, and use the prediction model to predict the feature vector to obtain a prediction score for each customer service processing request;

[0050] Step 104: Select the best customer service representative to handle the user request based on the customer service busyness and feature prediction score. The selected customer service representative interacts with the customer through an online platform. After the service is completed, feedback data is collected and the model is updated based on the feedback data.

[0051] Preferably, in step 101, the user's needs are obtained through the user's description on the client, and the user's characteristic information is extracted. A corresponding live code is generated according to the user's needs and characteristics, and each live code corresponds to a virtual customer service session. The specific steps are as follows:

[0052] Step A1, user feature extraction: The user inputs text, voice, or picture descriptions on the client to obtain the user's needs. When the user puts forward the needs, the user's feature information is extracted. The feature information includes: the user's historical consultation records, geographic location, language preference, and the user's current consultation purpose description;

[0053] Step A2, live code generation: based on the user's needs and feature information, a live code is dynamically generated. Each live code corresponds to a virtual customer service session. The live code contains an identifier based on the user's needs and features and customer service representative identification information. The identifier based on the user's needs and features is used to identify the user's request; the customer service representative identification information is used to connect the user to the correct customer service resource.

[0054] Step A3, live code distribution: the generated live code is distributed to users by generating a QR code, and a link is provided to be displayed on the website or App of the user;

[0055] Among them, in the step A3 of distributing the live code, the generated live code is distributed to the user by generating a QR code, and a link is provided to be displayed on the website or App of the user, further comprising the following steps:

[0056] Step A301: Use a QR code tool to convert the active code information into a QR code image and save it as an image file, and generate a link that can be accessed online, display the QR code on the website or App, and allow users to obtain the active code by scanning the QR code;

[0057] Step A302, providing a link: embed the live code information into a link, ensure that the link can directly access the virtual customer service session represented by the live code, publish content with the link on the website, App, and social media platform, and let the user click the link to directly enter the customer service session.

[0058] Preferably, in step 102, the user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process. Based on the collected customer service load data, the busyness of each customer service is determined. The specific steps are as follows:

[0059] Step B1: After the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session;

[0060] Step B2, collecting user characteristic data: when a user enters a customer service session, the user's characteristic data is obtained through the user's login status, past interaction records, and personal information provided, including historical records, user portraits, and consultation content information;

[0061] Step B3, collecting customer service load data: collecting the current workload data of each customer service representative, including the number of tasks being processed and the number of tasks waiting to be processed, and judging the busyness of each customer service representative based on the collected workload data;

[0062] Among them, in the step B1, after the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session, further comprising the following steps:

[0063] Step B101, live code identification: after receiving a request from a user to scan a live code, the system identifies and parses the live code, and determines relevant information of the virtual customer service session represented by the live code according to the code or identifier of the live code;

[0064] Step B102: Connect the user to the corresponding virtual customer service session according to the information contained in the live code. After receiving the user's connection request, the virtual customer service session obtains the user's request information, including the user's problem description, specific needs, and personal information. According to the user's request information, the virtual customer service session system processes and responds through artificial intelligence technology.

[0065] Preferably, in step 103, the collected user feature data and customer service load data are preprocessed and feature constructed to obtain a feature vector, and the feature vector is predicted using a prediction model to obtain a prediction score for each customer service processing request. The specific steps are as follows:

[0066] Step C1, feature engineering: extract key features from user feature data and customer service load data, and perform feature construction. The user key features include the user's historical average waiting time, user type, historical consultation times, consultation type, and the time interval between the last consultation; the customer service load key features include the number of tasks being processed, the number of tasks waiting to be processed, and the customer service working hours;

[0067] Step C2, feature vector construction: combine the cleaned and feature-engineered feature data into a feature vector as the input of the prediction model;

[0068] Step C3, model establishment: Select the linear regression model as the prediction model, and predict the target value by fitting a linear function. Set the predicted target value to be the waiting time of the customer service request, where the features include user features and request features. The specific calculation formula is as follows:

[0069]

[0070] in, is the predicted waiting time for customer service requests, ω0,ω1,ω2,...,ω nare the parameters of the model, representing the intercept and feature weights, x0,x1,x2,...,x n is the input feature, n is the number of samples;

[0071] Step C4: Use the mean square error loss function to measure the prediction error of the model, and train the model by minimizing the loss function. The specific calculation formula is as follows:

[0072]

[0073] Among them, MSE is the mean square error, which represents the mean of the squared error between the predicted value and the actual value, n is the number of samples, is the predicted value of the i-th sample, y i is the actual value of the i-th sample;

[0074] Step C5, prediction score calculation: After the model is trained, it is used to predict the waiting time of new customer service requests. Given a new input feature x, it is substituted into the model to obtain the predicted waiting time, which is expressed as the prediction score for processing the request.

[0075] Preferably, in step 104, the best customer service representative is selected to handle the user request based on the customer service busyness and feature prediction score, and the selected customer service representative interacts with the customer through an online platform. After the service is completed, feedback data is collected and the model is updated according to the feedback data. The specific steps are as follows:

[0076] Step D1, comprehensive score: define a weight coefficient to balance the importance of the customer service's busyness and feature prediction score, and use the weighted average method to calculate the customer service's comprehensive score. The specific calculation formula is as follows:

[0077]

[0078] Among them, S i is the comprehensive rating of customer service i, is the feature prediction score, which indicates the score calculated by customer service i based on the features of the user request. i is the busyness score, which indicates the busyness score of customer service i. α is the weight coefficient, which is used to balance the importance of feature prediction score and busyness score.

[0079] Step D2: based on the comprehensive score, select the customer service representative with the highest score to handle the user request, assign the selected customer service representative to the user, and interact with the user through the online platform. After the service is completed, collect customer feedback data;

[0080] Step D3, model update: Use the collected feedback data in combination with the original training data to update and retrain the model. Use supervised learning methods, use the feedback data as labels, and adjust the model parameters to improve the model's prediction accuracy and generalization ability. Deploy the updated model to the production environment for use in the next round of customer service request processing.

[0081] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0082] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0086] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0087] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent customer service scheduling method based on live codes and user characteristics, characterized in that: The specific steps include: Step 101: Obtain user needs through the user's description on the client, extract user feature information, generate corresponding live codes according to the user needs and features, and correspond each live code to a virtual customer service session; Step 102: The user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process. Based on the collected customer service load data, the busyness of each customer service is determined; Step 103: pre-process and construct features of the collected user feature data and customer service load data to obtain a feature vector, and use the prediction model to predict the feature vector to obtain a prediction score for each customer service processing request; Step 104: Select the best customer service representative to handle the user request based on the customer service busyness and feature prediction score. The selected customer service representative interacts with the customer through an online platform. After the service is completed, feedback data is collected and the model is updated based on the feedback data.

2. According to claim 1, an intelligent customer service scheduling method based on active codes and user characteristics is characterized by: In step 101, the user's needs are obtained through the user's description on the client, and the user's characteristic information is extracted. A corresponding live code is generated according to the user's needs and characteristics, and each live code corresponds to a virtual customer service session. The specific steps are as follows: Step A1, user feature extraction: The user inputs text, voice, or picture descriptions on the client to obtain the user's needs, and extracts the user's feature information while the user puts forward the needs; Step A2, live code generation: dynamically generate live codes according to user needs and feature information, and each live code corresponds to a virtual customer service session; Step A3, live code distribution: the generated live code is distributed to users by generating a QR code, and a link is provided to be displayed on the user's website or App.

3. According to claim 1, the intelligent customer service scheduling method based on active code and user characteristics is characterized in that: In step 102, the user enters the customer service session by scanning the live code, initiates a consultation, and collects user feature data and customer service load data during the code scanning process. Based on the collected customer service load data, the busyness of each customer service is determined. The specific steps are as follows: Step B1: After the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session; Step B2, collecting user characteristic data: when a user enters a customer service session, the user's characteristic data is obtained through the user's login status, past interaction records, and personal information provided; Step B3, collect customer service load data: collect the current workload data of each customer service representative, including the number of tasks being processed and the number of tasks waiting to be processed, and determine the busyness of each customer service representative based on the collected workload data.

4. The intelligent customer service scheduling method based on active codes and user characteristics according to claim 3 is characterized in that: In the step B1, after the user scans the live code, the live code is identified and connected to the corresponding virtual customer service session, and the user's request is routed to the correct customer service session, further comprising the following steps: Step B101, live code identification: after receiving a request from a user to scan a live code, the system identifies and parses the live code, and determines relevant information of the virtual customer service session represented by the live code according to the code or identifier of the live code; Step B102: Connect the user to the corresponding virtual customer service session according to the information contained in the live code. After receiving the user's connection request, the virtual customer service session obtains the user's request information. According to the user's request information, the virtual customer service session system processes and responds through artificial intelligence technology.

5. The intelligent customer service scheduling method based on active codes and user characteristics according to claim 1 is characterized in that: In step 103, the collected user feature data and customer service load data are preprocessed and feature constructed to obtain a feature vector, and the feature vector is predicted using a prediction model to obtain a prediction score for each customer service processing request. The specific steps are as follows: Step C1, feature engineering: extract key features from user feature data and customer service load data, and perform feature construction; Step C2, feature vector construction: combine the cleaned and feature-engineered feature data into a feature vector as the input of the prediction model; Step C3, model building: Select the linear regression model as the prediction model, and predict the target value by fitting a linear function. Set the predicted target value as the waiting time of the customer service request. The features include user features and request features. The specific calculation formula is as follows: in, is the predicted waiting time for customer service requests, ω0,ω1,ω2,...,ω n are the parameters of the model, representing the intercept and feature weights, x0,x1,x2,...,x n is the input feature, n is the number of samples; Step C4: Use the mean square error loss function to measure the prediction error of the model, and train the model by minimizing the loss function. The specific calculation formula is as follows: Among them, MSE is the mean square error, which represents the mean of the squared error between the predicted value and the actual value, n is the number of samples, is the predicted value of the i-th sample, y i is the actual value of the i-th sample; Step C5, prediction score calculation: After the model is trained, it is used to predict the waiting time of new customer service requests. Given a new input feature x, it is substituted into the model to obtain the predicted waiting time, which is expressed as the prediction score for processing the request.

6. The intelligent customer service scheduling method based on active codes and user characteristics according to claim 1 is characterized in that: In step 104, the best customer service representative is selected to handle the user request based on the customer service busyness and feature prediction score. The selected customer service representative interacts with the customer through the online platform. After the service is completed, feedback data is collected and the model is updated according to the feedback data. The specific steps are as follows: Step D1, comprehensive score: define a weight coefficient to balance the importance of the customer service's busyness and feature prediction score, and use the weighted average method to calculate the customer service's comprehensive score. The specific calculation formula is as follows: Among them, S i is the comprehensive rating of customer service i, is the feature prediction score, P i is the busyness score, α is the weight coefficient; Step D2: based on the comprehensive score, select the customer service representative with the highest score to handle the user request, assign the selected customer service representative to the user, and interact with the user through the online platform. After the service is completed, collect customer feedback data; Step D3, model update: Use the collected feedback data in combination with the original training data to update and retrain the model, use the feedback data as labels, adjust the model parameters, and deploy the updated model to the production environment for use in the next round of customer service request processing.

Images