Customer complaint list processing method based on big data

Abstract

The invention relates to the technical field of data processing, in particular to a customer complaint bill processing method based on big data, and the method comprises the steps: receiving a plurality of customer text complaint bills in a preset period, and dividing and sorting the plurality of customer text complaint bills based on a preset time period; analyzing a key complaint problem set corresponding to the plurality of customer text complaint lists in any initial classification result, so as to cluster the plurality of customer text complaint lists based on a key problem analysis result; analyzing the processing complexity corresponding to the plurality of initial clusters to determine an initial processing priority; judging the change trend of the same initial cluster based on the sorting sequence so as to adjust the initial processing priority; and determining an initial allocation transmission resource based on the adjustment processing priority, transmitting the initial allocation transmission resource to each corresponding processing terminal, obtaining a feedback result of any processing terminal, and adjusting the adjustment processing priority based on the feedback result. The customer complaint list processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a customer complaint sheet processing method based on big data. Background Art

[0002] With the rapid development of big data technology, some companies have begun to try to apply big data technology to the field of customer complaint handling, using natural language processing (NLP) technology to perform preliminary classification and keyword extraction of customer text complaint forms.

[0003] A patent document with Chinese patent publication number CN111274380A discloses a consultation complaint information processing method based on big data and related devices, the method comprising: obtaining work order information of a target customer, the work order information comprising a target customer identifier, a target work order content and a target business classification; determining a first customer classification label and a target user portrait corresponding to the target customer according to the target customer identifier; determining a second customer classification label corresponding to the target customer according to the target work order content; determining a target consultation complaint processing suggestion corresponding to the target customer according to the first customer classification label, the second customer classification label and the target business classification, and displaying the target user portrait and the target consultation complaint processing suggestion.

[0004] The existing technology is still at the basic classification and statistical level, lacking in-depth analysis of the complexity of complaint processing and a priority adjustment mechanism based on dynamic changes over time. This results in inaccurate allocation of processing resources and processing efficiency that still needs to be improved. Summary of the invention

[0005] To this end, the present invention provides a customer complaint form processing method based on big data, which can solve the problem of low efficiency in customer complaint form processing by performing real-time analysis on a number of customer complaint forms, continuously adjusting the processing priority, and adjusting the transmission resources according to the priority.

[0006] To achieve the above object, the present invention provides a method for processing customer complaint forms based on big data, the method comprising:

[0007] The service center platform receives a number of customer text complaint forms within a preset period, divides the number of customer text complaint forms based on a preset time period, obtains a number of initial classification results, and sorts the number of initial classification results based on a time sequence to obtain a sorting sequence;

[0008] Analyze the key complaint problem sets corresponding to the plurality of customer text complaint forms in any of the initial classification results to obtain key problem analysis results, and perform clustering processing on the plurality of customer text complaint forms based on the key problem analysis results to obtain a plurality of initial clusters;

[0009] Analyzing the processing complexity corresponding to the initial clusters, and determining the initial processing priority based on the processing complexity;

[0010] Determining a change trend of the same initial cluster based on the sorting sequence, so as to adjust the initial processing priority based on the change trend to obtain an adjusted processing priority;

[0011] Based on the adjustment processing priority, the initial allocation of transmission resources is determined, and based on the initial allocation of transmission resources, a number of the initial clusters are transmitted to the corresponding processing terminals, and feedback results of any processing terminal are obtained, so as to adjust the adjustment processing priority based on the feedback results to obtain the target processing priority.

[0012] Furthermore, the step of analyzing the key complaint problem sets corresponding to the several customer text complaint sheets in any of the initial classification results includes:

[0013] Perform word segmentation on the customer text complaint form to obtain a number of initial word segments;

[0014] Processing a number of the initial word segmentations to obtain a valid vocabulary set;

[0015] The effective vocabulary set is matched with a preset complaint text database for semantic similarity to obtain a similarity matching result, and the key complaint problem set is determined based on the similarity matching result.

[0016] Furthermore, the step of clustering the plurality of customer text complaint sheets based on the key problem analysis results includes:

[0017] Calculate the similarity between any two customer text complaint sheets based on the key complaint question set to obtain the calculated similarity;

[0018] Constructing a similarity matrix based on the several calculated similarities;

[0019] Based on the similarity matrix and a preset clustering algorithm, a plurality of the customer text complaint sheets are clustered to obtain a plurality of initial clusters.

[0020] Furthermore, the step of analyzing the processing complexity corresponding to the initial clusters includes:

[0021] Counting the number of the customer text complaint sheets corresponding to any of the initial clusters as the actual number value, and calculating the number complexity based on the actual number value;

[0022] Identify a cluster center problem set corresponding to any of the initial clusters, analyze the cluster center problem set, and determine the problem complexity based on the problem set analysis result;

[0023] The processing complexity is calculated based on the numerical complexity and the problem complexity.

[0024] Furthermore, the step of determining the complexity of the problem based on the problem set analysis result includes:

[0025] Determining the actual problem type based on the cluster center problem set;

[0026] Count the number of customer text complaint tickets corresponding to any of the actual problem types as the statistical number;

[0027] Determining calculation weights corresponding to a number of practical problem types based on a number of said statistical quantities;

[0028] The problem complexity is calculated based on the calculated weight and the statistical quantity.

[0029] Further, the step of determining the initial processing priority based on the processing complexity includes:

[0030] Sort the processing complexities from large to small to obtain a first sort;

[0031] The initial processing priority is determined based on the first ranking.

[0032] Furthermore, the step of determining the change trend of the same initial cluster based on the sorting sequence includes:

[0033] Determine, based on the sorting sequence, the number of a plurality of customer text complaint sheets corresponding to the same initial cluster in different time periods as a plurality of first numbers;

[0034] Determining an actual proportion of the initial cluster in the plurality of initial clusters based on any of the first numbers;

[0035] A change trend of the actual proportion is determined based on the sorting sequence.

[0036] Further, the step of adjusting the initial processing priority based on the change trend includes:

[0037] Analyze the change trend corresponding to any of the initial clusters to determine whether the change trend is an upward trend or a downward trend according to the analysis result;

[0038] An adjustment strategy is determined according to the trend determination result, and the initial processing priority is adjusted according to the adjustment strategy to obtain an adjusted processing priority.

[0039] Further, the step of determining the initial allocation of transmission resources based on the adjustment processing priority includes:

[0040] Determining a resource allocation ratio based on the adjustment processing priority;

[0041] The initial allocated transmission resources are determined based on the resource allocation ratio and the preset total transmission resources.

[0042] Furthermore, the step of adjusting the processing complexity corresponding to the initial clustering based on the feedback result includes:

[0043] Receive and analyze the processing results of the customer complaint form corresponding to any of the processing terminals to obtain feedback data;

[0044] Analyze the feedback data to identify the number of customer text complaint tickets that are successfully processed and the number of customer text complaint tickets that are unsuccessfully processed as the number of successes and the number of failures;

[0045] Based on the number of successes and the number of failures, calculating a processing success rate corresponding to any of the initial clusters;

[0046] According to the processing success rate, the processing complexity of the corresponding initial clustering is adjusted.

[0047] Compared with the prior art, the beneficial effects of the present invention are that it receives complaint tickets through a preset cycle and divides them based on preset time periods, ensuring that complaint processing can keep up with the time context and respond to customer needs in a timely manner. By chronologically sorting the initial classification results, a clear timeline is provided for subsequent analysis, which helps to identify the evolution trend of complaint issues. By analyzing the key complaint problem set, the customer's core demands and main problem points can be accurately identified, providing a clear direction for subsequent processing. Clustering processing is performed based on the key problem analysis results to classify similar complaint tickets, reducing duplication of work in the processing process and improving processing efficiency. By analyzing the processing complexity to determine the initial processing priority, high priority can be ensured. Priority is given to processing high-level and complex issues, thereby optimizing resource allocation and setting clear processing priorities for complaint tickets, which helps each processing terminal respond quickly and give priority to urgent or important issues. By analyzing the changing trends of the initial clusters and dynamically adjusting the processing priorities, it is able to flexibly respond to the suddenness and evolution of complaint issues, ensuring that the processing strategy always meets actual needs. Based on the adjusted processing priority, the initial clusters are allocated to each processing terminal to ensure that each terminal can receive the task that best suits its processing capabilities and resource conditions. By collecting feedback from the processing terminals, the processing priority is adjusted again, forming a closed-loop optimization mechanism that can continuously correct and optimize the processing strategy and improve the overall processing effect.

[0048] In particular, by performing word segmentation processing on customer text complaint forms and splitting long texts into several initial word segments, it is helpful to analyze the text content more carefully in subsequent processing and improve the accuracy of information processing. By processing the initial word segments, an effective vocabulary set is obtained, which improves the accuracy and efficiency of subsequent analysis and provides a more accurate and targeted vocabulary set for subsequent matching with the preset complaint text database. By matching the effective vocabulary set with the preset complaint text database for semantic similarity, the key complaint issues in the customer text complaint form can be accurately identified, which provides a clear classification basis for subsequent processing and improves the accuracy and efficiency of complaint processing.

[0049] In particular, by counting the number of customer text complaint forms in each initial cluster, that is, the actual quantity value, the processing burden represented by each cluster can be directly quantified, providing an intuitive numerical basis for subsequent resource allocation and priority setting. By identifying and analyzing the cluster center problem set, we can deeply understand the type and severity of problems represented by each cluster, which is helpful to formulate targeted processing strategies and improve processing efficiency and quality. Based on the comprehensive calculation of quantitative complexity and problem complexity, the calculation results of processing complexity are more comprehensive and accurate, ensuring the efficiency of the entire processing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flowchart of a method for processing customer complaint forms based on big data provided by an embodiment of the present invention;

[0051] Figure 2 A schematic diagram of a process for analyzing a key complaint problem set in a customer complaint form processing method based on big data provided in an embodiment of the present invention;

[0052] Figure 3 A schematic diagram of a process for calculating the complexity of processing in a method for processing customer complaint forms based on big data provided by an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of a flow chart for determining a change trend of a customer complaint form processing method based on big data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0056] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0057] See also Figure 1 As shown, an embodiment of the present invention provides a method for processing customer complaint forms based on big data, the method comprising:

[0058] Step S100: The service center platform receives a number of customer text complaint forms within a preset period, divides the number of customer text complaint forms based on a preset time period, obtains a number of initial classification results, and sorts the number of initial classification results based on a time sequence to obtain a sorting sequence;

[0059] Step S200, analyzing the key complaint problem sets corresponding to the plurality of customer text complaint sheets in any of the initial classification results to obtain key problem analysis results, and clustering the plurality of customer text complaint sheets based on the key problem analysis results to obtain a plurality of initial clusters;

[0060] Step S300, analyzing the processing complexity corresponding to the initial clusters, and determining the initial processing priority based on the processing complexity;

[0061] Step S400, determining a change trend of the same initial cluster based on the sorting sequence, so as to adjust the initial processing priority based on the change trend to obtain an adjusted processing priority;

[0062] Step S500, determine the initial allocation of transmission resources based on the adjustment processing priority, transmit the several initial clusters to the corresponding processing terminals based on the initial allocation of transmission resources, obtain the feedback result of any processing terminal, adjust the adjustment processing priority based on the feedback result, and obtain the target processing priority.

[0063] Specifically, the preset period in the embodiment of the present invention is one month;

[0064] The preset time period is one day.

[0065] Specifically, the embodiment of the present invention divides a number of customer text complaint tickets based on a preset time period, including:

[0066] Determine the receiving time corresponding to the plurality of customer text complaint forms;

[0067] Based on the preset time period, the customer text complaint sheets corresponding to the plurality of receiving moments in the same time period are divided to obtain a plurality of initial classification results.

[0068] Specifically, the embodiment of the present invention sorts a number of initial classification results based on time sequence, including:

[0069] The time periods corresponding to the several initial classification results are sorted from earliest to latest, and the initial classification result corresponding to the earliest time within the preset period is sorted as 1, and so on, to obtain the sorting sequence.

[0070] Specifically, the embodiments of the present invention receive complaint tickets through a preset cycle and divide them based on preset time periods, ensuring that complaint processing can keep up with the time context and respond to customer needs in a timely manner. By chronologically sorting the initial classification results, a clear timeline is provided for subsequent analysis, which helps to identify the evolution trend of complaint issues. By analyzing the key complaint problem set, the customer's core demands and main problem points can be accurately identified, providing a clear direction for subsequent processing. Clustering processing is performed based on the key problem analysis results to classify similar complaint tickets, reducing duplication of work in the processing process and improving processing efficiency. The initial processing priority is determined by analyzing the processing complexity, which can ensure that high priority and complex complaints are processed. Problems with high complexity are handled first, thereby optimizing resource allocation. Setting a clear processing priority for complaint tickets helps each processing terminal respond quickly and give priority to urgent or important issues. By analyzing the changing trends of the initial clusters and dynamically adjusting the processing priority, it is able to flexibly respond to the suddenness and evolution of complaint issues, ensuring that the processing strategy always meets actual needs. Based on the adjusted processing priority, the initial clusters are allocated to each processing terminal to ensure that each terminal can receive the task that best suits its processing capabilities and resource conditions. By collecting feedback from the processing terminals, the processing priority is adjusted again, forming a closed-loop optimization mechanism that can continuously correct and optimize the processing strategy and improve the overall processing effect.

[0071] See also Figure 2 As shown, the step of analyzing the key complaint problem set corresponding to a number of the customer text complaint sheets in any of the initial classification results includes:

[0072] Step S210, performing word segmentation processing on the customer text complaint form to obtain a number of initial word segments;

[0073] Step S220, processing a number of the initial word segmentations to obtain a valid vocabulary set;

[0074] Step S230, performing semantic similarity matching between the valid vocabulary set and a preset complaint text database to obtain a similarity matching result, and determining the key complaint problem set based on the similarity matching result.

[0075] Specifically, the preset complaint text library described in the embodiments of the present invention is constructed based on historical customer complaint data, covering the vocabulary and expression methods of common complaint problems. The preset complaint text library includes word vectors of complaint problems and corresponding problem tags.

[0076] Specifically, the processing of several of the initial word segmentations in the embodiments of the present invention includes filtering out stop words and irrelevant words in the initial word segmentations. Among them, stop words can be preset common but meaningless words, such as "de" (的), "le" (了), etc., and may also include some common phrases, such as "zai nale" (在那里), "shijishang" (实际上), etc. Stop words can be determined through a predefined stop word list. Irrelevant words may be commercial brand names, personal names, place names, etc. that are irrelevant to the complaint problems. By identifying several historical customer complaint texts, identifying the words that frequently appear but are irrelevant to the complaint problems, and using them as an irrelevant word library, the irrelevant words are determined through the irrelevant word library.

[0077] Specifically, the steps of the embodiments of the present invention for performing semantic similarity matching between the effective vocabulary set and the preset complaint text database include:

[0078] Converting each effective word in the effective vocabulary set into several effective word vectors;

[0079] Calculating the similarity between several of the effective word vectors and the corresponding preset word vectors in the preset complaint text database to obtain several similarities.

[0080] Specifically, the embodiments of the present invention calculate the similarity between several of the effective word vectors and the corresponding preset word vectors in the preset complaint text database by calculating the distance or angle between vectors to measure the similarity between words.

[0081] Specifically, the embodiments of the present invention may include:

[0082] Original complaint text: "The goods I reserved last week have not arrived yet. The logistics information shows that it has been waiting for delivery. I have contacted the customer service many times but without result. I am very dissatisfied about this.";

[0083] After word segmentation: "The goods I reserved last week have not arrived yet. The logistics information shows that it has been waiting for delivery. I have contacted the customer service many times but without result. I am very dissatisfied about this.";

[0084] Filter out stop words and irrelevant words, such as "wo" (我), "de" (的), "le" (了), ",", etc.

[0085] Remaining effective words: "last week", "reserve", "goods", "not arrived", "logistics information", "show", "一直", "wait", "delivery", "many times", "contact", "customer service", "without result", "very", "dissatisfied";

[0086] Convert valid vocabulary into word vectors through pre-trained word embedding models (pre-trained word embedding models may include Word2Vec, G loVe, etc.);

[0087] Find similar word vectors or phrases in the preset complaint text database. The preset database may contain word vectors and corresponding labels for complaint issues such as "delivery delay", "customer service unresponsive", "order not delivered", etc.

[0088] Calculate the similarity between the effective word vector and the word vector in the preset complaint text database (such as cosine similarity);

[0089] Assume that the word vectors of "not arrived" and "delivery delay" are very similar, and the word vector combination of "contacting customer service to no avail" and "customer service unresponsive" is also highly similar;

[0090] Based on the similarity matching results, it can be determined that the complaint ticket mainly involves two issues: one is "delivery delay" (corresponding to words such as "not yet arrived", "waiting", and "delivery"), and the other is "customer service is unresponsive" (corresponding to words such as "multiple contacts", "customer service", and "fruitless");

[0091] Find the labels corresponding to these two issues in the preset complaint text database, which are "logistics issue" and "service response issue" respectively;

[0092] The two labels "logistics problem" and "service response problem" are associated with the complaint ticket as the key complaint problem set of the complaint ticket.

[0093] Specifically, the embodiment of the present invention performs word segmentation processing on the customer text complaint form and splits the long text into several initial word segments, which helps to analyze the text content more carefully in subsequent processing and improve the accuracy of information processing. By processing the initial word segments, an effective vocabulary set is obtained, which improves the accuracy and efficiency of subsequent analysis and provides a more accurate and targeted vocabulary set for subsequent matching with a preset complaint text database. By matching the effective vocabulary set with the preset complaint text database for semantic similarity, the key complaint issues in the customer text complaint form can be accurately identified, which provides a clear classification basis for subsequent processing and improves the accuracy and efficiency of complaint processing.

[0094] Specifically, the step of clustering the plurality of customer text complaint sheets based on the key problem analysis results includes:

[0095] Calculate the similarity between any two customer text complaint sheets based on the key complaint question set to obtain the calculated similarity;

[0096] Constructing a similarity matrix based on the several calculated similarities;

[0097] Based on the similarity matrix and a preset clustering algorithm, a plurality of the customer text complaint sheets are clustered to obtain a plurality of initial clusters.

[0098] Specifically, the preset clustering algorithm described in the embodiment of the present invention may be K-means clustering or hierarchical clustering. When it is K-means clustering, it is necessary to pre-specify the number of cluster centers K. The K value can be determined based on actual conditions, such as the diversity of complaint issues, processing resource limitations, etc. When performing hierarchical clustering, you can choose a bottom-up aggregation method (such as AGNES) or a top-down splitting method (such as DIANA).

[0099] Specifically, the embodiment of the present invention constructs a similarity matrix based on several of the calculated similarities, wherein each element in the matrix represents a similarity value between two customer text complaint sheets.

[0100] Specifically, the embodiment of the present invention performs clustering processing on a plurality of customer text complaint sheets based on the similarity matrix and a preset clustering algorithm, including:

[0101] Preprocess the similarity matrix to ensure that the data in the matrix is ​​suitable for the selected clustering algorithm. For example, in K-means clustering, the similarity values ​​may need to be normalized to better calculate the distance during the clustering process.

[0102] Taking K-means clustering as an example, first randomly select K customer text complaint forms as the initial cluster centers. Then, for each customer text complaint form, calculate its similarity with each initial cluster center, and assign it to the cluster where the cluster center with the highest similarity is located. After completing a round of allocation, recalculate the center of each cluster, that is, the point corresponding to the mean similarity of all complaint forms in the cluster. This process is iterated continuously until a certain termination condition is met, such as the change in the cluster center is less than a preset threshold, or the preset number of iterations is reached, where the preset threshold can be 0.1 and the preset number of iterations can be 100 times.

[0103] In hierarchical clustering, if a bottom-up aggregation method is used, each customer text complaint form is initially considered as a separate cluster. Then, the similarity between all cluster pairs is calculated, and the two clusters with the highest similarity are merged. This process is repeated until the preset number of clusters is reached or other termination conditions are met. The preset number of clusters can be adjusted according to actual conditions. If it is necessary to divide customer text complaint forms into five main complaint categories, the preset number of clusters is set to five. If a top-down splitting method is used, all complaint forms are initially considered as one cluster, and then gradually split into smaller clusters until the conditions are met.

[0104] See also Figure 3 As shown, the step of analyzing the processing complexity corresponding to the initial clusters includes:

[0105] Step S310, counting the number of the customer text complaint forms corresponding to any of the initial clusters as the actual number value, and calculating the number complexity based on the actual number value;

[0106] Step S320, identifying a cluster center problem set corresponding to any of the initial clusters, analyzing the cluster center problem set, and determining the problem complexity based on the problem set analysis result;

[0107] Step S330: Calculate the processing complexity based on the quantity complexity and the problem complexity.

[0108] Specifically, the step of calculating the quantity complexity based on the actual quantity value in the embodiment of the present invention includes:

[0109] Setting quantity thresholds;

[0110] The ratio of the actual quantity value to the quantity threshold is taken as the quantity complexity.

[0111] Specifically, the quantity threshold in the embodiment of the present invention is the total number of the customer text complaint forms collected within the same preset time period divided by the total number of the initial clusters.

[0112] Specifically, the embodiment of the present invention can identify the cluster center problem set corresponding to any of the initial clusters by vectorizing each customer text complaint form, for example, using a bag-of-words model or a word vector model. Then, the centroid of all vectors in each cluster is calculated, that is, the average value on each dimension, as the vector representation of the cluster center, and the key complaint problem set corresponding to each customer text complaint form whose vector is closest to the cluster center is selected as the cluster center problem set.

[0113] Specifically, the embodiment of the present invention can directly quantify the processing burden represented by each cluster by counting the number of customer text complaint sheets in each initial cluster, that is, the actual number value, and provide an intuitive numerical basis for subsequent resource allocation and priority setting. By identifying and analyzing the cluster center problem set, it can deeply understand the type and severity of problems represented by each cluster, which is helpful to formulate targeted processing strategies and improve processing efficiency and quality. Based on the comprehensive calculation of quantitative complexity and problem complexity, the calculation results of processing complexity are more comprehensive and accurate, ensuring the efficiency of the entire processing process.

[0114] Specifically, the step of determining the complexity of a problem based on the problem set analysis result includes:

[0115] Determining the actual problem type based on the cluster center problem set;

[0116] Count the number of customer text complaint tickets corresponding to any of the actual problem types as the statistical number;

[0117] Determining calculation weights corresponding to a number of practical problem types based on a number of said statistical quantities;

[0118] The problem complexity is calculated based on the calculated weight and the statistical quantity.

[0119] Specifically, a possible example of the embodiment of the present invention is:

[0120] Determine the actual problem types as "logistics problem" and "service response problem";

[0121] The number of customer complaint text sheets is counted. The total number of customer complaint text sheets is 100, of which 60 are for "logistics issues" and 80 are for "service response issues". It can be seen that the number of customer complaint text sheets that repeatedly contain "logistics issues" and "service response issues" is 40;

[0122] The weight corresponding to "logistics problem" is (60-40 / 2) / 100=0.4;

[0123] The weight corresponding to "Service Response Issue" is (80-40 / 2) / 100=0.6;

[0124] Problem complexity = 0.4×60 / (60+80)+0.6×80 / (60+80)=0.17+0.34=0.51.

[0125] Specifically, the processing complexity described in the embodiment of the present invention = α×quantity complexity+β×problem complexity, wherein α is the weight corresponding to the quantity complexity, β is the weight corresponding to the problem complexity, and α+β=1.

[0126] Specifically, the steps for determining the initial processing priority based on processing complexity include:

[0127] Sort the processing complexities from large to small to obtain a first sort;

[0128] The initial processing priority is determined based on the first ranking.

[0129] Specifically, the embodiment of the present invention can clearly identify which clusters need to be processed first by sorting the processing complexity. Clear priority setting helps to reasonably allocate limited resources, ensuring that high-complexity and high-urgency problems can be solved first, avoiding wasting too many resources on low-complexity problems, thereby achieving optimal allocation and efficient utilization of resources.

[0130] See also Figure 4 As shown, the step of judging the change trend of the same initial cluster based on the sorting sequence includes:

[0131] Step S410, determining the number of a plurality of customer text complaint sheets corresponding to the same initial cluster in different time periods based on the sorting sequence as a plurality of first numbers;

[0132] Step S420, determining the actual proportion of the initial cluster in the plurality of initial clusters based on any of the first numbers;

[0133] Step S430: determining a change trend of the actual proportion based on the sorting sequence.

[0134] Specifically, the embodiment of the present invention provides a solid data foundation for subsequent analysis by counting the number of customer text complaint tickets corresponding to the same initial cluster in different time periods. By calculating the actual proportion of the initial cluster in the total, the relative importance of the clustering problem in the overall complaints can be intuitively understood, eliminating the comparison barriers between different clusters caused by the difference in absolute numbers, making the comparison between different clusters more fair and accurate, and providing strong decision-making support for adjusting resource allocation based on the changing trend of the actual proportion.

[0135] Specifically, the step of adjusting the initial processing priority based on the change trend includes:

[0136] Analyze the change trend corresponding to any of the initial clusters to determine whether the change trend is an upward trend or a downward trend according to the analysis result;

[0137] An adjustment strategy is determined according to the trend determination result, and the initial processing priority is adjusted according to the adjustment strategy to obtain an adjusted processing priority.

[0138] Specifically, the adjustment strategy in the embodiment of the present invention includes: when the change trend is an upward trend, increasing the processing priority of the corresponding initial cluster;

[0139] When the change trend is a downward trend, the processing priority of the corresponding initial cluster is reduced.

[0140] Specifically, if the actual proportion of a certain initial cluster in two consecutive time periods shows an upward trend, and the increase exceeds the preset increase threshold, the initial processing priority of the initial cluster is increased by one level;

[0141] If the actual proportion of a certain initial cluster in two consecutive time periods shows a downward trend, and the decline exceeds the preset decline threshold, the initial processing priority of the initial cluster is reduced by one level.

[0142] Specifically, in the embodiment of the present invention, the preset rising amplitude threshold is 5%, and the preset falling amplitude threshold is 3%.

[0143] Specifically, the embodiment of the present invention can determine whether the changing trend is an upward trend or a downward trend by calculating the difference in actual proportions in consecutive time periods. If the difference is greater than 0, the adjacent time periods are judged to be an upward trend; if the difference is less than 0, the adjacent time periods are judged to be a downward trend. The regional proportions corresponding to the upward trend or downward trend in the preset period are comprehensively judged. When the upward proportion or the downward proportion is greater than the preset proportion, the trend is judged to be an upward trend or a downward trend.

[0144] Specifically, the step of determining the initial allocation of transmission resources based on the adjustment processing priority includes:

[0145] Determining a resource allocation ratio based on the adjustment processing priority;

[0146] The initial allocated transmission resources are determined based on the resource allocation ratio and the preset total transmission resources.

[0147] Specifically, the embodiment of the present invention determines the resource allocation ratio based on the adjustment processing priority, including:

[0148] Normalizing the adjustment processing priority of each initial cluster to obtain a normalized priority value of each initial cluster;

[0149] According to the normalized priority value of each initial cluster, the corresponding resource ratio is allocated.

[0150] Specifically, the higher the normalized priority value of the initial cluster, the higher the proportion of resources allocated to it, to ensure efficient processing of high-priority complaints.

[0151] Specifically, the transmission resources in the embodiment of the present invention may be CPU and network bandwidth resources.

[0152] Specifically, the step of adjusting the processing complexity corresponding to the initial clustering based on the feedback result includes:

[0153] Receive and analyze the processing results of the customer complaint form corresponding to any of the processing terminals to obtain feedback data;

[0154] Analyze the feedback data to identify the number of customer text complaint tickets that are successfully processed and the number of customer text complaint tickets that are unsuccessfully processed as the number of successes and the number of failures;

[0155] Based on the number of successes and the number of failures, calculating a processing success rate corresponding to any of the initial clusters;

[0156] According to the processing success rate, the processing complexity of the corresponding initial clustering is adjusted.

[0157] Specifically, when adjusting the processing complexity, the embodiment of the present invention, if the processing success rate of a certain initial cluster is higher than a preset success rate threshold, the adjustment processing priority of the initial cluster is reduced by one level to release some resources for other clusters that may need processing more; conversely, if the processing success rate is lower than the preset success rate threshold, the adjustment processing priority of the initial cluster is increased by one level to improve the processing priority and allocated resources, thereby improving the processing effect.

[0158] Specifically, the preset success rate threshold in the embodiment of the present invention is 80%.

[0159] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0160] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for processing customer complaints based on big data, characterized in that: include: The service center platform receives a number of customer text complaint forms within a preset period, divides the number of customer text complaint forms based on a preset time period, obtains a number of initial classification results, and sorts the number of initial classification results based on a time sequence to obtain a sorting sequence; Analyze the key complaint problem sets corresponding to the plurality of customer text complaint forms in any of the initial classification results to obtain key problem analysis results, and perform clustering processing on the plurality of customer text complaint forms based on the key problem analysis results to obtain a plurality of initial clusters; Analyzing the processing complexity corresponding to the initial clusters, and determining the initial processing priority based on the processing complexity; Determining a change trend of the same initial cluster based on the sorting sequence, so as to adjust the initial processing priority based on the change trend to obtain an adjusted processing priority; Based on the adjustment processing priority, the initial allocation of transmission resources is determined, and based on the initial allocation of transmission resources, a number of the initial clusters are transmitted to the corresponding processing terminals, and feedback results of any processing terminal are obtained, so as to adjust the adjustment processing priority based on the feedback results to obtain the target processing priority.

2. The method for processing customer complaints based on big data according to claim 1 is characterized in that: The step of analyzing the key complaint problem set corresponding to the plurality of customer text complaint sheets in any of the initial classification results comprises: Perform word segmentation on the customer text complaint form to obtain a number of initial word segments; Processing a number of the initial word segmentations to obtain a valid vocabulary set; The effective vocabulary set is matched with a preset complaint text database for semantic similarity to obtain a similarity matching result, and the key complaint problem set is determined based on the similarity matching result.

3. The method for processing customer complaints based on big data according to claim 2 is characterized in that: The step of clustering the plurality of customer text complaint sheets based on the key problem analysis results comprises: Calculate the similarity between any two customer text complaint sheets based on the key complaint question set to obtain the calculated similarity; Constructing a similarity matrix based on the several calculated similarities; Based on the similarity matrix and a preset clustering algorithm, a plurality of the customer text complaint sheets are clustered to obtain a plurality of initial clusters.

4. The method for processing customer complaints based on big data according to claim 3 is characterized in that: The step of analyzing the processing complexity corresponding to the initial clusters comprises: Counting the number of the customer text complaint sheets corresponding to any of the initial clusters as the actual number value, and calculating the number complexity based on the actual number value; Identify a cluster center problem set corresponding to any of the initial clusters, analyze the cluster center problem set, and determine the problem complexity based on the problem set analysis result; The processing complexity is calculated based on the numerical complexity and the problem complexity.

5. The method for processing customer complaints based on big data according to claim 4 is characterized in that: The step of judging the complexity of the problem based on the problem set analysis result comprises: Determining the actual problem type based on the cluster center problem set; Count the number of customer text complaint tickets corresponding to any of the actual problem types as the statistical number; Determining calculation weights corresponding to a number of practical problem types based on a number of said statistical quantities; The problem complexity is calculated based on the calculated weight and the statistical quantity.

6. The method for processing customer complaints based on big data according to claim 5 is characterized in that: The steps to determine initial processing priorities based on processing complexity include: Sort the processing complexities from large to small to obtain a first sort; The initial processing priority is determined based on the first ranking.

7. The method for processing customer complaints based on big data according to claim 6 is characterized in that: The step of determining the change trend of the same initial cluster based on the sorting sequence comprises: Determine, based on the sorting sequence, the number of a plurality of customer text complaint sheets corresponding to the same initial cluster in different time periods as a plurality of first numbers; Determining an actual proportion of the initial cluster in the plurality of initial clusters based on any of the first numbers; A change trend of the actual proportion is determined based on the sorting sequence.

8. The method for processing customer complaints based on big data according to claim 7 is characterized in that: The step of adjusting the initial processing priority based on the change trend includes: Analyze the change trend corresponding to any of the initial clusters to determine whether the change trend is an upward trend or a downward trend according to the analysis result; An adjustment strategy is determined according to the trend determination result, and the initial processing priority is adjusted according to the adjustment strategy to obtain an adjusted processing priority.

9. The method for processing customer complaints based on big data according to claim 8 is characterized in that: The step of determining the initial allocation of transmission resources based on the adjustment processing priority includes: Determining a resource allocation ratio based on the adjustment processing priority; The initial allocated transmission resources are determined based on the resource allocation ratio and the preset total transmission resources.

10. The method for processing customer complaints based on big data according to claim 9 is characterized in that: The step of adjusting the processing complexity corresponding to the initial clustering based on the feedback result includes: Receive and analyze the processing results of the customer complaint form corresponding to any of the processing terminals to obtain feedback data; Analyze the feedback data to identify the number of customer text complaint tickets that are successfully processed and the number of customer text complaint tickets that are unsuccessfully processed as the number of successes and the number of failures; Based on the number of successes and the number of failures, calculating a processing success rate corresponding to any of the initial clusters; According to the processing success rate, the processing complexity of the corresponding initial clustering is adjusted.

Images