Data detection method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to a data detection method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining pre-collected dialogue text data corresponding to a target service; preprocessing the dialogue text data to obtain a target dialogue text; performing association rule mining on the target dialogue text based on an association rule mining algorithm to obtain an initial association rule; screening out specified association rules related to emotion detection from the initial association rules; constructing a corresponding association rule set based on a specified association rule; performing emotion rule mining on the association rule set based on a multi-target particle swarm optimization algorithm to obtain an emotion rule; and performing emotion violation detection on the dialogue text of the target customer service based on the emotion rule to obtain a corresponding emotion violation detection result. In addition, the emotion violation detection result can be stored in the block chain. Based on the use of the emotion rules, the processing efficiency and the processing accuracy of emotion violation detection processing are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to data detection methods, devices, computer equipment and storage media. Background Art

[0002] In today's digital transformation, cloud communications, as an enterprise-level communications service based on cloud computing technology concepts and service models, is gradually becoming a key tool for financial companies to improve operational efficiency and optimize customer experience. Cloud communications services widely cover traditional business areas of operators, such as SMS and voice services, and also penetrate into the core of Internet business, including instant messaging IM, real-time audio and video communications, call center management, cloud customer service systems, and enterprise converged communications UC and other diversified functions. This development trend has not only greatly enriched the communication methods of financial companies, but also significantly improved the flexibility and efficiency of communications.

[0003] It is particularly noteworthy that with the rapid development of AI technology, its deep integration with the customer service field is leading the transformation of the customer service industry. A large number of repetitive and boring tasks undertaken by traditional customer service personnel are now increasingly undertaken by intelligent customer service systems. These intelligent systems can accurately convert users' voice information into text through advanced speech recognition (ASR) technology; then, use natural language processing (NLP) technology to identify and match the user's speech intent; finally, through text-to-speech (TTS) technology, intelligent customer service can convey the matched reply content to the user in voice form, thereby achieving smooth, multi-round voice interaction with the user. This technological advancement not only significantly improves the efficiency of customer service work, but also brings a more personalized and intelligent user experience.

[0004] However, while intelligent customer service is widely used in telemarketing scenarios, it has also exposed some problems that need to be solved urgently. Among them, the quality of customer service attitude has a crucial impact on the success of telemarketing business. Traditional quality inspection methods often rely on manual analysis of customer service call recordings to identify whether their emotions are in violation of regulations. However, this method is not only inefficient and difficult to cope with large-scale, high-intensity telemarketing business needs, but also has great uncertainty in terms of accuracy. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a data detection method, device, computer equipment and storage medium to solve the technical problems that the existing customer service emotion quality inspection method often relies on manual analysis of customer service call recordings, which is inefficient and has low accuracy.

[0006] In order to solve the above technical problems, the present application provides a data detection method, which adopts the following technical solution:

[0007] Acquire pre-collected conversation text data corresponding to the target business;

[0008] Preprocessing the dialogue text data to obtain a corresponding target dialogue text;

[0009] Performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules;

[0010] Filtering out designated association rules related to emotion detection from the initial association rules;

[0011] Constructing a corresponding association rule set based on the specified association rule;

[0012] Based on a multi-objective particle swarm optimization algorithm, sentiment rules are mined on the association rule set to obtain corresponding sentiment rules;

[0013] Based on the emotion rule, emotion violation detection is performed on the conversation text of the target customer service to obtain an emotion violation detection result corresponding to the target customer service.

[0014] Furthermore, the step of performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules specifically includes:

[0015] Building a corresponding transaction database based on the target dialogue text;

[0016] Performing frequent item set mining processing on the transaction database based on the association rule mining algorithm to obtain corresponding frequent item sets;

[0017] Generating a first association rule that meets a preset confidence threshold based on the frequent item set;

[0018] The first association rule is used as the initial association rule.

[0019] Furthermore, the step of filtering out the designated association rules related to emotion detection from the initial association rules specifically includes:

[0020] Get the preset indicator calculation strategy;

[0021] Calculate the target indicators of all the initial association rules based on the indicator calculation strategy;

[0022] Screening all the initial association rules based on the target index to obtain a second association rule that meets the emotion detection condition;

[0023] The second association rule is used as the designated association rule.

[0024] Furthermore, the step of constructing a corresponding association rule set based on the specified association rule specifically includes:

[0025] Get the preset target form;

[0026] Adjusting the specified association rule based on the target form to obtain a corresponding third association rule;

[0027] The third association rules are integrated to obtain the corresponding association rule set.

[0028] Furthermore, the step of performing emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service specifically includes:

[0029] Obtaining the conversation text of the target customer service;

[0030] Extracting attribute tags from the conversation text to obtain corresponding attribute tags;

[0031] Extracting emotion tags from the conversation text to obtain corresponding emotion tags;

[0032] Based on the emotion rule, the attribute label and the emotion label are matched to obtain a corresponding matching result;

[0033] generating a score corresponding to the sentiment rule based on the matching result;

[0034] Determining whether the score is greater than a preset score threshold;

[0035] If the score is greater than the score threshold, a first emotion violation detection result is generated indicating that the target customer service has an emotion violation in the conversation text; otherwise, a second emotion violation detection result is generated indicating that the target customer service has no emotion violation in the conversation text.

[0036] Furthermore, the step of preprocessing the dialogue text data to obtain the corresponding target dialogue text specifically includes:

[0037] Performing word segmentation processing on the dialogue text data to obtain a corresponding first dialogue text;

[0038] removing irrelevant information from the first dialogue text to obtain a corresponding second dialogue text;

[0039] performing standardization processing on the second dialogue text to obtain a corresponding third dialogue text;

[0040] The third dialogue text is used as the target dialogue text.

[0041] Further, after the step of performing emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service, the method further includes:

[0042] Determine whether the content of the emotion violation detection result indicates that the target customer service has an emotion violation in the conversation text;

[0043] If so, obtain the violation information corresponding to the target customer service;

[0044] Generate a corresponding violation report based on the violation information;

[0045] Send said violation report to the appropriate personnel.

[0046] In order to solve the above technical problems, the embodiment of the present application further provides a data detection device, which adopts the following technical solution:

[0047] A first acquisition module, used to acquire pre-collected conversation text data corresponding to the target business;

[0048] A preprocessing module, used for preprocessing the dialogue text data to obtain a corresponding target dialogue text;

[0049] A first mining module is used to perform association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules;

[0050] A screening module, used to screen out designated association rules related to emotion detection from the initial association rules;

[0051] A construction module, used to construct a corresponding association rule set based on the specified association rule;

[0052] The second mining module is used to mine sentiment rules on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain corresponding sentiment rules;

[0053] The detection module is used to perform emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service.

[0054] 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:

[0055] Acquire pre-collected conversation text data corresponding to the target business;

[0056] Preprocessing the dialogue text data to obtain a corresponding target dialogue text;

[0057] Performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules;

[0058] Filtering out designated association rules related to emotion detection from the initial association rules;

[0059] Constructing a corresponding association rule set based on the specified association rule;

[0060] Based on a multi-objective particle swarm optimization algorithm, sentiment rules are mined on the association rule set to obtain corresponding sentiment rules;

[0061] Based on the emotion rule, emotion violation detection is performed on the conversation text of the target customer service to obtain an emotion violation detection result corresponding to the target customer service.

[0062] 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:

[0063] Acquire pre-collected conversation text data corresponding to the target business;

[0064] Preprocessing the dialogue text data to obtain a corresponding target dialogue text;

[0065] Performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules;

[0066] Filtering out designated association rules related to emotion detection from the initial association rules;

[0067] Constructing a corresponding association rule set based on the specified association rule;

[0068] Based on a multi-objective particle swarm optimization algorithm, sentiment rules are mined on the association rule set to obtain corresponding sentiment rules;

[0069] Based on the emotion rule, emotion violation detection is performed on the conversation text of the target customer service to obtain an emotion violation detection result corresponding to the target customer service.

[0070] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0071] The present application first obtains pre-collected conversation text data corresponding to the target business; and pre-processes the conversation text data to obtain the corresponding target conversation text; then performs association rule mining on the target conversation text based on a preset association rule mining algorithm to obtain the corresponding initial association rules; then screens out designated association rules related to emotion detection from the initial association rules; subsequently constructs a corresponding association rule set based on the designated association rules; further performs emotion rule mining on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain the corresponding emotion rules; finally, performs emotion violation detection on the conversation text of the target customer service based on the emotion rules to obtain an emotion violation detection result corresponding to the target customer service. The present application obtains the target conversation text by pre-processing the pre-collected conversation text data corresponding to the target business, and then obtains the initial association rules by performing association rule mining on the target conversation text based on the use of an association rule mining algorithm. Thereafter, the specified association rules related to emotion detection are screened out from the initial association rules and an association rule set is constructed. Then, emotion rule mining is performed on the association rule set based on the use of a multi-objective particle swarm optimization algorithm to obtain emotion rules, so that the subsequent use of emotion rules can realize efficient and accurate emotion violation detection processing for the conversation text of the target customer service, effectively improving the processing efficiency and processing accuracy of the emotion violation detection processing, and ensuring the accuracy of the obtained emotion violation detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0073] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0074] Figure 2 A flow chart of an embodiment of a data detection method according to the present application;

[0075] Figure 3 is a structural schematic diagram of an embodiment of a data detection device according to the present application;

[0076] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0078] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0079] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0080] like Figure 1 As 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 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for 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 optical fiber cables, etc.

[0081] 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 can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0082] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can 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), a laptop computer, a desktop computer, etc.

[0083] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0084] It should be noted that the data detection method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data detection device is generally arranged in the server / terminal device.

[0085] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0086] Continue to refer Figure 2 , shows a flow chart of an embodiment of the data detection method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The data detection method provided in the embodiment of the present application can be applied to any scenario where data detection is required, and the data detection method can be applied to products in these scenarios, for example, data detection of customer service emotions in the financial insurance field. The data detection method comprises the following steps:

[0087] Step S201, obtaining pre-collected dialogue text data corresponding to the target business.

[0088] In this embodiment, the electronic device (eg Figure 1The server / terminal device shown in the figure) can obtain the conversation text data corresponding to the target business through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or developed in the future. The executor of the present application may specifically be an intelligent customer service system, or simply referred to as a system. The above-mentioned target business may specifically be an electric sales business. Specifically, a log file containing the content of the conversation between the customer service and the user can be exported through the background interface of the intelligent customer service system. These files generally include the timestamp of the conversation, the customer service ID, the user ID, and the specific conversation text. The exported log files are then sorted to remove invalid data (such as empty conversations, system prompts, etc.) to ensure the accuracy and completeness of the data, thereby obtaining the corresponding conversation text data.

[0089] Step S202, preprocessing the dialogue text data to obtain a corresponding target dialogue text.

[0090] In this embodiment, the above-mentioned specific implementation process of preprocessing the dialogue text data to obtain the corresponding target dialogue text will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0091] Step S203: performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules.

[0092] In this embodiment, the above-mentioned specific implementation process of performing association rule mining on the target dialogue text based on the preset association rule mining algorithm to obtain the corresponding initial association rules will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0093] Step S204: Filter out designated association rules related to emotion detection from the initial association rules.

[0094] In this embodiment, the specific implementation process of filtering out the specified association rules related to emotion detection from the initial association rules will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0095] Step S205: construct a corresponding association rule set based on the specified association rule.

[0096] In this embodiment, the specific implementation process of constructing the corresponding association rule set based on the specified association rule will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0097] Step S206, performing sentiment rule mining on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain corresponding sentiment rules.

[0098] In this embodiment, the above-mentioned process of mining the sentiment rules for the association rule set based on the multi-objective particle swarm optimization algorithm to obtain the corresponding sentiment rules includes the steps of initializing the particle swarm, defining the fitness function, updating the particle speed and position, iterative search, and forming the sentiment rules. Specifically, initializing the particle swarm includes: setting the size of the particle swarm, each particle represents a set of possible sentiment rule parameters. These parameters may include the antecedent conditions in the association rules (such as the sentiment words mentioned by the user), the result conditions (such as the emotional state shown by the customer service), and the weight of the rules. Defining the fitness function includes: the fitness function is used to evaluate the pros and cons of the sentiment rules represented by the particles. Based on the historical conversation data, the accuracy, recall rate and other indicators of the rules represented by each particle in detecting sentiment violations can be calculated, and these indicators are combined to form the fitness value. Updating the particle speed and position includes: updating the particle speed and position according to the historical best position (individual best and global best) and the current particle speed and position. This process simulates the process of particles looking for the optimal solution in the search space. Iterative search includes: iteratively searching for the optimal parameters in the search space until the stop condition is met (such as reaching the maximum number of iterations or finding a solution that meets the requirements). During the iteration process, the global optimal solution and individual optimal solution are continuously recorded and updated. The formation of emotional rules includes: forming multiple specific emotional rules based on the final particles (i.e., the optimal solution). These emotional rules can include the emotional states that customer service may show in specific situations and the correlation between these emotional states and user feedback.

[0099] Step S207: performing emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain an emotion violation detection result corresponding to the target customer service.

[0100] In the present embodiment, the above-mentioned specific implementation process of performing emotional violation detection on the conversation text of the target customer service based on the emotional rules to obtain the emotional violation detection result corresponding to the target customer service will be described in further details in the subsequent specific embodiments of the present application and will not be elaborated in detail here.

[0101] The present application first obtains pre-collected conversation text data corresponding to the target business; and pre-processes the conversation text data to obtain the corresponding target conversation text; then performs association rule mining on the target conversation text based on a preset association rule mining algorithm to obtain the corresponding initial association rules; then screens out designated association rules related to emotion detection from the initial association rules; subsequently constructs a corresponding association rule set based on the designated association rules; further performs emotion rule mining on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain the corresponding emotion rules; finally, performs emotion violation detection on the conversation text of the target customer service based on the emotion rules to obtain an emotion violation detection result corresponding to the target customer service. The present application obtains the target conversation text by pre-processing the pre-collected conversation text data corresponding to the target business, and then obtains the initial association rules by performing association rule mining on the target conversation text based on the use of an association rule mining algorithm. Thereafter, the specified association rules related to emotion detection are screened out from the initial association rules and an association rule set is constructed. Then, emotion rule mining is performed on the association rule set based on the use of a multi-objective particle swarm optimization algorithm to obtain emotion rules, so that the subsequent use of emotion rules can realize efficient and accurate emotion violation detection processing for the conversation text of the target customer service, effectively improving the processing efficiency and processing accuracy of the emotion violation detection processing, and ensuring the accuracy of the obtained emotion violation detection results.

[0102] In some optional implementations, step S203 includes the following steps:

[0103] A corresponding transaction database is constructed based on the target dialogue text.

[0104] In this embodiment, the dialogue text is divided into sentences or dialogue turns, each sentence or dialogue turn is regarded as a transaction, and the words in the transaction are regarded as items to construct a corresponding transaction database, wherein each transaction includes a group of items (i.e., words).

[0105] Based on the association rule mining algorithm, frequent item sets are mined on the transaction database to obtain corresponding frequent item sets.

[0106] In this embodiment, the above association rule mining algorithm may specifically adopt the Apriori algorithm or the FP-Growth algorithm. After determining the selection of the association rule mining algorithm, the frequent item sets in the transaction database may be mined by using the association rule mining algorithm.

[0107] A first association rule satisfying a preset confidence threshold is generated based on the frequent item set.

[0108] In this embodiment, there is no specific limitation on the value of the confidence threshold, which can be set according to actual business needs. The first association rule that meets the confidence threshold represents a meaningful association rule.

[0109] The first association rule is used as the initial association rule.

[0110] The present application constructs a corresponding transaction database based on the target conversation text; then performs frequent item set mining processing on the transaction database based on the association rule mining algorithm to obtain the corresponding frequent item set; then generates a first association rule that meets a preset confidence threshold based on the frequent item set; and subsequently uses the first association rule as the initial association rule. The present application constructs a corresponding transaction database based on the target conversation text; then performs frequent item set mining processing on the transaction database based on the use of an association rule mining algorithm to obtain the corresponding frequent item set, and then based on the frequent item set, it is possible to efficiently and accurately generate the initial association rule that meets the confidence threshold, thereby improving the efficiency of generating the initial association rule and ensuring the accuracy of the obtained initial association rule.

[0111] In some optional implementations of this embodiment, step S204 includes the following steps:

[0112] Get the preset indicator calculation strategy.

[0113] In this embodiment, the above-mentioned indicator calculation strategy includes a strategy for calculating the indicators corresponding to the confidence, coverage and interest of the association rules. The association rules are stated in the form of "if-then". The conditions associated in the "if" part are called antecedent conditions, and the conditions associated in the "then" part are called result conditions, which are called A and C respectively. The association rule is expressed as R:A→C. The support count of the association rule is represented by SUP(A→C). SUP(A→C) is the number of transactions that are compatible with both A and C, that is, the number of transactions containing an A∪C, SUP(A→C)=SUP(A∪C). Similarly, SUP(A) and SUP(C) are the number of transactions that are only compatible with A and C, respectively.

[0114] Specifically, the confidence of an association rule is used to measure specificity or consistency, indicating the probability of creating a rule based on the antecedent part, and is defined as follows:

[0115] The coverage of association rules is the extent to which the result part is covered by the association rules, which shows the possibility of creating rules based on the result part. The definition of coverage is as follows:

[0116] The interest of an association rule is a measure of how surprising the association rule is to the user. The definition of interest is as follows: Wherein, N is a natural number, and the specific value can be adjusted according to historical data, expert experience or actual needs.

[0117] The target indicators of all the initial association rules are calculated based on the indicator calculation strategy.

[0118] In this embodiment, the target indicators of all initial association rules may be calculated according to the policy content of the above-mentioned indicator calculation policy, that is, including the confidence, coverage and interest of all initial association rules.

[0119] All the initial association rules are screened based on the target index to obtain second association rules that meet the emotion detection conditions.

[0120] In this embodiment, confidence thresholds, coverage thresholds, and interest thresholds corresponding to confidence, coverage, and interest are pre-set. Then, all the mined initial association rules are traversed, and each initial association rule is screened according to the calculated target index of each initial association rule to retain the rules that meet all the index thresholds (confidence threshold, coverage threshold, and interest threshold) at the same time, so as to obtain the second association rule that meets the emotion detection condition.

[0121] The second association rule is used as the designated association rule.

[0122] The present application obtains a preset indicator calculation strategy; then calculates the target indicators of all the initial association rules based on the indicator calculation strategy; then screens all the initial association rules based on the target indicators to obtain a second association rule that meets the emotion detection conditions; and subsequently uses the second association rule as the designated association rule. The present application calculates the target indicators of all the initial association rules based on the use of an indicator calculation strategy, and then screens all the initial association rules based on the use of the target indicators, so that the designated association rules related to emotion detection can be quickly and accurately screened out, thereby improving the screening efficiency of the designated association rules and ensuring the accuracy of the obtained designated association rules.

[0123] In some optional implementations, step S205 includes the following steps:

[0124] Gets the preset target form.

[0125] In this embodiment, the above target form may specifically include an "if-then" form of expression, wherein the "if" part represents the antecedent condition (A), and the "then" part represents the result condition (C), forming a rule R:A→C.

[0126] The designated association rule is adjusted based on the target form to obtain a corresponding third association rule.

[0127] In this embodiment, the specified association rule obtained after screening may be represented to obtain the adjusted third association rule.

[0128] The third association rules are integrated to obtain the corresponding association rule set.

[0129] In this embodiment, the above association rule set is a set consisting of all third association rules.

[0130] The present application obtains a preset target form; then adjusts the specified association rule based on the target form to obtain a corresponding third association rule; and subsequently integrates the third association rule to obtain the corresponding association rule set. The present application obtains a corresponding third association rule based on the obtained target form, and then integrates the third association rule, so that the corresponding association rule set can be constructed quickly and accurately, thereby improving the construction efficiency and accuracy of the association rule set.

[0131] In some optional implementations, step S207 includes the following steps:

[0132] Get the conversation text of the target customer service.

[0133] In this embodiment, the conversation text of the target customer service is a conversation text that needs to be processed for emotional violation.

[0134] Attribute tags are extracted from the dialogue text to obtain corresponding attribute tags.

[0135] In this embodiment, the conversation text of the target customer service can be classified by using a text classification algorithm to extract attribute labels corresponding to the conversation text (such as customer service attitude, user feedback, etc.).

[0136] Emotional tags are extracted from the dialogue text to obtain corresponding emotional tags.

[0137] In this embodiment, sentiment analysis may be performed on the conversation text of the target customer service by using a pre-trained sentiment analysis model or a custom sentiment dictionary to extract the sentiment label corresponding to the conversation text.

[0138] The attribute label and the emotion label are matched based on the emotion rule to obtain a corresponding matching result.

[0139] In this embodiment, the number of the above-mentioned emotion rules may include multiple. The above-mentioned matching process includes: traversing all emotion rules. For each emotion rule, checking whether its antecedent condition matches the extracted emotion tag and attribute tag. If the match is successful, the emotion rule and its related information are recorded, and the matching result of the emotion rule is a successful match.

[0140] A score corresponding to the sentiment rule is generated based on the matching result.

[0141] In this embodiment, each successfully matched rule can be screened out according to the matching results, and the rule score of the rule can be calculated according to the rule weight, and then all the rule scores are weighted summed or calculated by a more complex calculation method (such as weighted product, weighted average, etc.), so as to obtain the summary score of all successfully matched rules, that is, the above score. The rule weight can be set according to actual business needs.

[0142] Determine whether the score is greater than a preset score threshold.

[0143] In this embodiment, a threshold of the sentiment rule score can be set according to actual needs. This threshold can be adjusted according to historical data, expert experience or actual needs.

[0144] If the score is greater than the score threshold, a first emotion violation detection result is generated indicating that the target customer service has an emotion violation in the conversation text; otherwise, a second emotion violation detection result is generated indicating that the target customer service has no emotion violation in the conversation text.

[0145] In this embodiment, the total score of the emotion rules of the conversation text, that is, the score, is compared with the score threshold. If the score exceeds the score threshold, it is considered that the target customer service may have an emotion violation in the conversation, and then a first emotion violation detection result is generated, indicating that the target customer service has an emotion violation in the conversation text. If the score does not exceed the score threshold, it is considered that the target customer service does not have an emotion violation in the conversation, and then a second emotion violation detection result is generated, indicating that the target customer service does not have an emotion violation in the conversation text.

[0146] This application obtains the conversation text of the target customer service; then extracts attribute tags from the conversation text to obtain corresponding attribute tags; and extracts sentiment tags from the conversation text to obtain corresponding sentiment tags; then based on the sentiment rules, performs matching processing on the attribute tags and the sentiment tags to obtain corresponding matching results; subsequently generates a score corresponding to the sentiment rules based on the matching results; finally determines whether the score is greater than a preset score threshold; if the score is greater than the score threshold, generates a first sentiment violation detection result indicating that the target customer service has a sentiment violation in the conversation text, otherwise generates a second sentiment violation detection result indicating that the target customer service does not have a sentiment violation in the conversation text. This application extracts attribute tags and sentiment tags from the obtained conversation text of the target customer service to obtain corresponding attribute tags and sentiment tags, then performs matching processing on the attribute tags and the sentiment tags based on the use of sentiment rules to obtain a matching result, and generates a score corresponding to the sentiment rules based on the matching result. Furthermore, by numerically comparing the score with the preset score threshold, it is possible to quickly and accurately complete the sentiment violation detection processing for the conversation text of the target customer service according to the obtained numerical comparison result, effectively ensuring the accuracy and reliability of the sentiment violation detection processing.

[0147] In some alternative implementation manners of this embodiment, step S202 includes the following steps:

[0148] Perform word segmentation processing on the conversation text data to obtain a corresponding first conversation text.

[0149] In this embodiment, the word segmentation processing of the conversation text data can be performed by using a natural language processing library to obtain the corresponding first conversation text.

[0150] Perform irrelevant information removal processing on the first conversation text to obtain a corresponding second conversation text.

[0151] In this embodiment, the above-mentioned irrelevant information removal processing includes removing stop words and removing punctuation marks. Among them, the above-mentioned removing stop words includes: according to the stop word list, removing common but meaningless words (such as "de", "le", etc.) in the conversation text. The above-mentioned removing punctuation marks includes: using regular expressions or string processing methods to remove punctuation marks in the conversation text.

[0152] Perform standardization processing on the second conversation text to obtain a corresponding third conversation text.

[0153] In this embodiment, the above-mentioned standardization processing includes converting uppercase letters to lowercase, unifying punctuation marks, etc. to convert to a standardized word sequence.

[0154] The third dialogue text is used as the target dialogue text.

[0155] The present application performs word segmentation processing on the dialogue text data to obtain the corresponding first dialogue text; then performs irrelevant information removal processing on the first dialogue text to obtain the corresponding second dialogue text; then performs standardization processing on the second dialogue text to obtain the corresponding third dialogue text; and subsequently uses the third dialogue text as the target dialogue text. The present application performs word segmentation processing, irrelevant information removal processing and standardization processing on the dialogue text data, thereby efficiently and accurately completing the preprocessing of the dialogue text data, and ensuring the accuracy of the obtained target dialogue text.

[0156] In some optional implementations of this embodiment, after step S207, the electronic device may further perform the following steps:

[0157] Determine whether the content of the emotion violation detection result indicates that the target customer service has an emotion violation in the conversation text.

[0158] In this embodiment, the content of the above-mentioned emotion violation detection result may include that the target customer service has an emotion violation in the conversation text, or that the target customer service has no emotion violation in the conversation text.

[0159] If so, obtain the violation information corresponding to the target customer service.

[0160] In this embodiment, the above-mentioned violation information includes information such as the ID of the target customer service, the violation time, and the violation content.

[0161] A corresponding violation report is generated based on the violation information.

[0162] In this embodiment, a preset violation report template can be obtained, and then the violation information can be filled into the corresponding position in the violation report template, thereby generating a corresponding violation report. The content of the violation report template can be constructed according to actual business needs. Exemplarily, the violation report template can include an ID area, a time area, and a content area.

[0163] Send said violation report to the appropriate personnel.

[0164] In this embodiment, the above-mentioned relevant personnel may be customer service management personnel, or may also be personnel responsible for investigation work.

[0165] This application determines whether the content of the emotional violation detection result indicates that the target customer service has an emotional violation in the conversation text; if so, obtains the violation information corresponding to the target customer service; then generates a corresponding violation report based on the violation information; and subsequently sends the violation report to relevant personnel. This application automatically obtains the violation information corresponding to the target customer service when it is detected that the content of the emotional violation detection result indicates that the target customer service has an emotional violation in the conversation text, and generates a corresponding violation report based on the violation information, thereby improving the efficiency and intelligence of generating the violation report. And subsequently, by sending the violation report to relevant personnel, the relevant personnel can conduct corresponding internal investigations and processing on the target customer service according to the violation report, which is conducive to improving the user experience of the relevant personnel.

[0166] In some optional implementations, the user information obtained is subject to the user's consent and complies with relevant laws and policies.

[0167] In addition, the non-Company software tools or components that appear in the embodiments of the present application are merely examples and do not represent actual use.

[0168] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0169] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned emotional violation detection results, the above-mentioned emotional violation detection results can also be stored in a node of a blockchain.

[0170] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0171] The embodiments of the present 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.

[0172] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the 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-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0174] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0175] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a data detection device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0176] like Figure 3 As shown, the data detection device 300 described in this embodiment includes: a first acquisition module 301, a preprocessing module 302, a first mining module 303, a screening module 304, a construction module 305, a second mining module 306 and a detection module 307. Among them:

[0177] The first acquisition module 301 is used to acquire pre-collected conversation text data corresponding to the target business;

[0178] A preprocessing module 302 is used to preprocess the dialogue text data to obtain a corresponding target dialogue text;

[0179] A first mining module 303 is used to perform association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules;

[0180] A screening module 304 is used to screen out designated association rules related to emotion detection from the initial association rules;

[0181] A construction module 305 is used to construct a corresponding association rule set based on the specified association rule;

[0182] The second mining module 306 is used to perform sentiment rule mining on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain corresponding sentiment rules;

[0183] The detection module 307 is used to perform emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain an emotion violation detection result corresponding to the target customer service.

[0184] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0185] In some optional implementations of this embodiment, the first mining module 303 includes:

[0186] A construction submodule, used to construct a corresponding transaction database based on the target dialogue text;

[0187] A mining submodule, used for performing a frequent itemset mining process on the transaction database based on the association rule mining algorithm to obtain corresponding frequent itemsets;

[0188] A first generating submodule, configured to generate a first association rule satisfying a preset confidence threshold based on the frequent item set;

[0189] The first determining submodule is configured to use the first association rule as the initial association rule.

[0190] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0191] In some optional implementations of this embodiment, the screening module 304 includes:

[0192] The first acquisition submodule is used to obtain a preset indicator calculation strategy;

[0193] A calculation submodule, used for calculating target indicators of all the initial association rules based on the indicator calculation strategy;

[0194] A first processing submodule is used to screen all the initial association rules based on the target index to obtain a second association rule that meets the emotion detection condition;

[0195] The second determining submodule is configured to use the second association rule as the designated association rule.

[0196] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0197] In some optional implementations of this embodiment, the construction module 305 includes:

[0198] The second acquisition submodule is used to acquire a preset target form;

[0199] An adjustment submodule, configured to adjust the specified association rule based on the target form to obtain a corresponding third association rule;

[0200] The integration submodule is used to integrate the third association rules to obtain the corresponding association rule set.

[0201] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0202] In some optional implementations of this embodiment, the detection module 307 includes:

[0203] A third acquisition submodule is used to acquire the conversation text of the target customer service;

[0204] A first extraction submodule is used to extract attribute labels from the conversation text to obtain corresponding attribute labels;

[0205] The second extraction submodule is used to extract emotion tags from the dialogue text to obtain corresponding emotion tags;

[0206] A matching submodule, used for matching the attribute label with the emotion label based on the emotion rule to obtain a corresponding matching result;

[0207] A second generating submodule, configured to generate a score corresponding to the sentiment rule based on the matching result;

[0208] A judgment submodule, used to judge whether the score is greater than a preset score threshold;

[0209] The third generating submodule is used to generate a first emotion violation detection result indicating that the target customer service has an emotion violation in the conversation text if the score is greater than the score threshold; otherwise, generate a second emotion violation detection result indicating that the target customer service has no emotion violation in the conversation text.

[0210] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0211] In some optional implementations of this embodiment, the preprocessing module 302 includes:

[0212] A second processing submodule is used to perform word segmentation processing on the dialogue text data to obtain a corresponding first dialogue text;

[0213] A third processing submodule, configured to remove irrelevant information from the first dialogue text to obtain a corresponding second dialogue text;

[0214] A fourth processing submodule, configured to perform standardization processing on the second dialogue text to obtain a corresponding third dialogue text;

[0215] The third determining submodule is used to use the third dialogue text as the target dialogue text.

[0216] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0217] In some optional implementations of this embodiment, the data detection device further includes:

[0218] A judgment module, used to judge whether the content of the emotion violation detection result indicates that the target customer service has an emotion violation in the conversation text;

[0219] A second acquisition module, for obtaining violation information corresponding to the target customer service;

[0220] A generating module, used for generating a corresponding violation report based on the violation information;

[0221] The sending module is used to send the violation report to relevant personnel.

[0222] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the data detection method in the aforementioned implementation mode, and are not described in detail here.

[0223] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4This is a basic structural block diagram of the computer device in this embodiment.

[0224] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art 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 (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0225] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0226] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the data detection method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0227] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the data detection method.

[0228] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0229] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0230] In an embodiment of the present application, the target conversation text is obtained by preprocessing the pre-collected conversation text data corresponding to the target business, and then the initial association rules are obtained by performing association rule mining on the target conversation text based on the use of an association rule mining algorithm. Thereafter, the specified association rules related to emotion detection are screened out from the initial association rules and an association rule set is constructed. Then, based on the use of a multi-objective particle swarm optimization algorithm, emotion rule mining is performed on the association rule set to obtain emotion rules, so that subsequent use based on the emotion rules can realize efficient and accurate emotion violation detection processing of the conversation text of the target customer service, effectively improving the processing efficiency and processing accuracy of the emotion violation detection processing, and ensuring the accuracy of the obtained emotion violation detection results.

[0231] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the data detection method as described above.

[0232] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0233] In an embodiment of the present application, the target conversation text is obtained by preprocessing the pre-collected conversation text data corresponding to the target business, and then the initial association rules are obtained by performing association rule mining on the target conversation text based on the use of an association rule mining algorithm. Thereafter, the specified association rules related to emotion detection are screened out from the initial association rules and an association rule set is constructed. Then, based on the use of a multi-objective particle swarm optimization algorithm, emotion rule mining is performed on the association rule set to obtain emotion rules, so that subsequent use based on the emotion rules can realize efficient and accurate emotion violation detection processing of the conversation text of the target customer service, effectively improving the processing efficiency and processing accuracy of the emotion violation detection processing, and ensuring the accuracy of the obtained emotion violation detection results.

[0234] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0235] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data detection method, characterized in that: The steps include: Acquire pre-collected conversation text data corresponding to the target business; Preprocessing the dialogue text data to obtain a corresponding target dialogue text; Performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules; Filtering out designated association rules related to emotion detection from the initial association rules; Constructing a corresponding association rule set based on the specified association rule; Based on a multi-objective particle swarm optimization algorithm, sentiment rules are mined on the association rule set to obtain corresponding sentiment rules; Based on the emotion rule, emotion violation detection is performed on the conversation text of the target customer service to obtain an emotion violation detection result corresponding to the target customer service.

2. The data detection method according to claim 1, characterized in that: The step of performing association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules specifically includes: Building a corresponding transaction database based on the target dialogue text; Performing frequent item set mining processing on the transaction database based on the association rule mining algorithm to obtain corresponding frequent item sets; Generating a first association rule that meets a preset confidence threshold based on the frequent item set; The first association rule is used as the initial association rule.

3. The data detection method according to claim 1, characterized in that: The step of selecting the designated association rules related to emotion detection from the initial association rules specifically includes: Get the preset indicator calculation strategy; Calculate the target indicators of all the initial association rules based on the indicator calculation strategy; Screening all the initial association rules based on the target index to obtain a second association rule that meets the emotion detection condition; The second association rule is used as the designated association rule.

4. The data detection method according to claim 1, characterized in that: The step of constructing a corresponding association rule set based on the specified association rule specifically includes: Get the preset target form; Adjusting the specified association rule based on the target form to obtain a corresponding third association rule; The third association rules are integrated to obtain the corresponding association rule set.

5. The data detection method according to claim 1, characterized in that: The step of performing emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service specifically includes: Obtaining the conversation text of the target customer service; Extracting attribute tags from the conversation text to obtain corresponding attribute tags; Extracting emotion tags from the conversation text to obtain corresponding emotion tags; Based on the emotion rule, the attribute label and the emotion label are matched to obtain a corresponding matching result; generating a score corresponding to the sentiment rule based on the matching result; Determining whether the score is greater than a preset score threshold; If the score is greater than the score threshold, a first emotion violation detection result is generated indicating that the target customer service has an emotion violation in the conversation text; otherwise, a second emotion violation detection result is generated indicating that the target customer service has no emotion violation in the conversation text.

6. The data detection method according to claim 1, characterized in that: The step of preprocessing the dialogue text data to obtain the corresponding target dialogue text specifically includes: Performing word segmentation processing on the dialogue text data to obtain a corresponding first dialogue text; removing irrelevant information from the first dialogue text to obtain a corresponding second dialogue text; performing standardization processing on the second dialogue text to obtain a corresponding third dialogue text; The third dialogue text is used as the target dialogue text.

7. The data detection method according to claim 1, characterized in that: After the step of performing emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service, the method further includes: Determine whether the content of the emotion violation detection result indicates that the target customer service has an emotion violation in the conversation text; If so, obtain the violation information corresponding to the target customer service; Generate a corresponding violation report based on the violation information; Send said violation report to the appropriate personnel.

8. A data detection device, characterized in that: include: A first acquisition module, used to acquire pre-collected conversation text data corresponding to the target business; A preprocessing module, used for preprocessing the dialogue text data to obtain a corresponding target dialogue text; A first mining module is used to perform association rule mining on the target dialogue text based on a preset association rule mining algorithm to obtain corresponding initial association rules; A screening module, used to screen out designated association rules related to emotion detection from the initial association rules; A construction module, used to construct a corresponding association rule set based on the specified association rule; The second mining module is used to mine sentiment rules on the association rule set based on a multi-objective particle swarm optimization algorithm to obtain corresponding sentiment rules; The detection module is used to perform emotion violation detection on the conversation text of the target customer service based on the emotion rule to obtain the emotion violation detection result corresponding to the target customer service.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the data detection method according to any one of claims 1 to 7 when executing the computer-readable instructions.

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 a processor, the steps of the data detection method according to any one of claims 1 to 7 are implemented.

Images