An intelligent customer service system, method, medium and device based on emotion recognition

Abstract

The present disclosure relates to an intelligent customer service system and method based on emotion recognition, equipment and medium, the system comprises: a voice data extraction module for extracting voice data of a user based on a conversation between the system and the user and storing; a word segmentation processing module for performing word segmentation processing on the voice data to obtain word vector data; an entity recognition module for extracting entity keywords in the word vector data and performing first sorting on the word frequency of the entity keywords; an emotion recognition module for extracting emotion keywords in the word vector data and performing second sorting according to the word frequency of the emotion keywords; a decision module for selecting a corresponding response strategy based on a decision algorithm according to the first sorting and the second sorting; a voice module for generating a reply voice statement based on the response strategy. The system and method of the present disclosure recognize user emotions, assist in decision-making, and ultimately improve user service quality.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent customer service technology, and more specifically, to an intelligent customer service system, method, medium, and device based on emotion recognition. Background Technology

[0002] An online customer service system is a service system that supports dialogue through multiple channels, allowing customer service personnel to provide unified responses on the platform and answer questions from customers who encounter problems during use.

[0003] As the business grows, the number of customers will increase, and the number of customers requiring online customer service will also increase. This will bring about the following issues:

[0004] Online customer service is very busy, or there may be a shortage of human agents, resulting in a large number of customers being in a queue.

[0005] To solve these problems, a powerful, 24 / 7 online intelligent customer service system is needed to replace human agents. However, current intelligent customer service technologies lack self-learning capabilities and cannot meet the demand. Summary of the Invention

[0006] To address the technical problem that existing intelligent customer service technologies lack self-learning capabilities and cannot meet demand.

[0007] To achieve the above technical objectives, this disclosure provides an intelligent customer service system based on emotion recognition, comprising:

[0008] A voice data extraction module is used to extract and store the user's voice data based on the dialogue between the system and the user.

[0009] The word segmentation processing module is used to segment the speech data to obtain word vector data;

[0010] An entity recognition module is used to extract entity keywords from the word vector data and to perform a first sorting on the word frequency of the entity keywords.

[0011] An emotion recognition module is used to extract emotion keywords from the word vector data and sort them in a second order according to the frequency of occurrence of the emotion keywords.

[0012] The decision module is used to select the corresponding response strategy based on the first sorting and the second sorting according to the decision algorithm;

[0013] A voice module is used to generate a response voice statement based on the response strategy.

[0014] Furthermore, the emotion recognition module is specifically used for:

[0015] Extract emotion keywords from the word vector data and perform emotion keyword matching in a pre-built emotion lexicon;

[0016] The frequency of emotional keywords is corrected based on the frequency correction coefficient of the preset emotional keywords in the emotional lexicon;

[0017] The frequency of the corrected emotion keywords is ranked in a third order, and the result of the second order is replaced by the third order.

[0018] Furthermore, the decision-making module is specifically used for:

[0019] Based on the decision tree and historical response decision strategy, the corresponding response strategy is selected according to the first sort and the second sort, and the response strategy for this time is stored.

[0020] Furthermore, the decision-making module is specifically used for:

[0021] Determine whether the top-ranked entity keyword in the first sort and the top-ranked sentiment keyword in the second sort can be found in the historical response strategy. If they can, select the corresponding historical response strategy as the current response strategy and store the current response strategy.

[0022] If not, perform keyword similarity matching between the top-ranked entity keyword in the first ranking and the top-ranked sentiment keyword in the second ranking, and select the three historical response strategies with the highest similarity matching results as the response strategy for this time.

[0023] Furthermore, the word segmentation module is specifically used for:

[0024] The speech data is segmented using a conditional random field to obtain word vector data.

[0025] To achieve the above technical objectives, this disclosure also provides an intelligent customer service response method based on emotion recognition, applicable to the aforementioned intelligent customer service system based on emotion recognition, comprising:

[0026] Extract and store voice data based on the dialogue between the system and the user;

[0027] The speech data is segmented to obtain word vector data;

[0028] Extract entity keywords from the word vector data, and sort the word frequencies of the entity keywords in a first order;

[0029] Extract emotion keywords from the word vector data, and perform a second sorting based on the frequency of occurrence of the emotion keywords;

[0030] Based on the first and second sorting, the historical response strategies are traversed, and the historical response strategy with the highest matching degree is selected as the response strategy for this time.

[0031] A response voice statement is generated based on the aforementioned response strategy.

[0032] Furthermore, after extracting the sentiment keywords from the word vector data and performing a second sorting of the frequency of the sentiment keywords, the method further includes:

[0033] Matching emotional keywords in a pre-built emotional lexicon;

[0034] The frequency of emotional keywords is corrected based on the frequency correction coefficient of the preset emotional keywords in the emotional lexicon;

[0035] The frequency of the corrected emotion keywords is ranked in a third order, and the result of the second order is replaced by the third order.

[0036] Furthermore, the specific steps of performing word segmentation on the speech data to obtain word vector data are as follows:

[0037] The speech data is segmented using a conditional random field to obtain word vector data.

[0038] To achieve the above technical objectives, this disclosure also provides a computer storage medium storing a computer program thereon, which, when executed by a processor, is used to implement the steps of the alarm method described above.

[0039] To achieve the above-mentioned technical objectives, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the alarm method described above.

[0040] The beneficial effects of this disclosure are as follows:

[0041] 1. By continuously enriching the intelligent customer service system with more knowledge, its ability to identify and respond to customer service requests can be improved. This can reduce the workload of human customer service representatives and allow more customers to have a satisfactory service experience. Furthermore, because the intelligent customer service system can monitor customer emotions in real time and take timely measures to soothe customers based on their emotional state, it can reduce the risk of customer complaints and improve customer satisfaction.

[0042] 2. Business management can also analyze the underlying emotions of users' voices to reflect their subjective feelings and experiences, which can assist management decisions and ultimately improve the quality of user service. Attached Figure Description

[0043] Figure 1 A schematic diagram of the system structure of Embodiment 1 of this disclosure is shown;

[0044] Figure 2 A flowchart illustrating the method of Embodiment 2 of this disclosure is shown;

[0045] Figure 3 A flowchart illustrating the method of Embodiment 2 of this disclosure is shown;

[0046] Figure 4 A schematic diagram of the structure of Embodiment 4 of this disclosure is shown. Detailed Implementation

[0047] Embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0048] The accompanying drawings illustrate various structural schematics according to embodiments of the present disclosure. These drawings are not to scale, and some details have been enlarged and may have been omitted for clarity. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0049] Example 1:

[0050] like Figure 1 As shown:

[0051] An intelligent customer service system 100 based on emotion recognition includes:

[0052] The voice data extraction module 101 is used to extract and store the user's voice data based on the dialogue between the system and the user;

[0053] The word segmentation processing module 102 is used to perform word segmentation processing on the speech data to obtain word vector data;

[0054] The entity recognition module 103 is used to extract entity keywords from the word vector data and to sort the word frequencies of the entity keywords in a first order.

[0055] The emotion recognition module 104 is used to extract emotion keywords from the word vector data and sort them in a second order according to the frequency of occurrence of the emotion keywords.

[0056] Decision module 105 is used to select the corresponding response strategy based on the first sorting and the second sorting according to the decision algorithm;

[0057] The voice module 106 is used to generate a response voice statement based on the response strategy.

[0058] The emotion-based intelligent customer service system described in this disclosure differs from commonly used intelligent customer service systems in the prior art. It not only identifies entity keywords in the user's question and matches them, but also integrates an emotion recognition module to identify the current user's emotions. Based on the user's current emotions, it selects corresponding response strategies and response scripts, which can better improve the quality of service to users and enhance the user experience.

[0059] It should be noted that the intelligent customer service system based on emotion recognition described in this disclosure identifies entity keywords and emotion keywords in user questions during user conversations.

[0060] For example: "How can I withdraw the balance from my Alipay account?"

[0061] Therefore, the keywords "extract", "Alipay", and "balance" after word segmentation are all entity keywords that are substantially related to the problem to be solved;

[0062] The keyword "how" implies the user's current mood or emotion.

[0063] Furthermore, the emotion recognition module 104 is specifically used for:

[0064] Extract emotion keywords from the word vector data and perform emotion keyword matching in a pre-built emotion lexicon;

[0065] The frequency of emotional keywords is corrected based on the frequency correction coefficient of the preset emotional keywords in the emotional lexicon;

[0066] The frequency of the corrected emotion keywords is ranked in a third order, and the result of the second order is replaced by the third order.

[0067] The above-mentioned further solutions mainly involve assigning certain correction coefficients to emotional keywords that can express strong user emotions, in order to improve the accuracy of emotion recognition for users currently in a conversation.

[0068] The emotion recognition module 104 described in this disclosure identifies the current emotion of the user in the conversation. If the keywords indicating the user's emotion as loss or anger rank higher in the second or corrected third ranking results, then some soothing words should be incorporated into the subsequent response strategy, or the user should be directly transferred to human customer service to improve service quality.

[0069] For example, if keywords indicating the user's emotions of disappointment or anger rank higher in the second or corrected third ranking results, then some reassuring phrases can be used, such as: "I'm very sorry, I will help you as soon as possible" or "I'm very sorry, the intelligent customer service cannot answer your question at the moment. We will transfer you to human customer service. Is that alright?"

[0070] Furthermore, the decision module 105 is specifically used for:

[0071] Based on the decision tree and historical response decision strategy, the corresponding response strategy is selected according to the first sort and the second sort, and the response strategy for this time is stored.

[0072] Based on decision trees, and by using historical response strategies as a reference for the response strategy in the current user session, we can continuously learn and improve to generate better response strategies.

[0073] Furthermore, the decision module 105 is specifically used for:

[0074] Determine whether the top-ranked entity keyword in the first sort and the top-ranked sentiment keyword in the second sort can be found in the historical response strategy. If they can, select the corresponding historical response strategy as the current response strategy and store the current response strategy.

[0075] If not, perform keyword similarity matching between the top-ranked entity keyword in the first ranking and the top-ranked sentiment keyword in the second ranking, and select the three historical response strategies with the highest similarity matching results as the response strategy for this time.

[0076] Furthermore, the word segmentation processing module 102 is specifically used for:

[0077] The speech data is segmented using a conditional random field to obtain word vector data.

[0078] Conditional random fields (CRFs) are discriminative probabilistic models, a type of random field, commonly used for labeling or analyzing sequential data, such as natural language text or biological sequences. A CRF is a conditional probability distribution model P(Y|X), representing a Markov random field where, given a set of input random variables X, the output random variables Y are assumed to form a Markov random field. In other words, a key characteristic of CRFs is the assumption that the output random variables constitute a Markov random field. CRFs can be seen as a generalization of the maximum entropy Markov model to the labeling problem.

[0079] Like Markov random fields, conditional random fields (CRFs) are undirected graphical models. In a CRF, the distribution of random variable Y is a conditional probability, and the given observations are random variables X. In principle, the graphical model layout of a CRF can be arbitrarily given. A commonly used layout is a chained architecture, which offers efficient algorithms for training, inference, and decoding. A CRF is a typical discriminative model, and its joint probability can be written as a product of several potential functions, with linear-chained CRFs being the most common.

[0080] For example, assuming the obtained voice information is "I went to the bank to handle business", by performing word segmentation on the name of the business, we can obtain multiple words that make up the name of the business, namely "I", "go", "bank", "handle", and "business".

[0081] Optionally, the word segmentation processing module disclosed herein uses a rule-based word segmentation algorithm. It combines the analysis of the information provided above to delimit words. The core of the word segmentation algorithm is the bidirectional maximum matching method, that is, it traverses both forward and backward. Then, based on the principle that the more large-granular words the better, and the fewer non-dictionary words and single-character words the better, it selects one point to output the word segmentation result.

[0082] This disclosed system continuously enriches the intelligent customer service system with more knowledge, thereby enhancing its ability to identify and respond to customer service requests. This reduces the workload of human customer service representatives and allows more customers to have a satisfactory service experience. Furthermore, because the intelligent customer service system can monitor customer emotions in real time and take timely measures to soothe customers based on their emotional state, it reduces the risk of customer complaints and improves customer satisfaction. The system's business management can also analyze the underlying emotions in user voice messages to reflect customers' subjective experiences and feelings, supporting management decisions and ultimately improving the quality of user service.

[0083] The system disclosed herein will count the top(n) most frequent words of a day, assign the corresponding customer questions and answers to the intelligent customer service system. The intelligent customer service system will be trained using machine learning predictive modeling algorithms such as decision trees. It will learn the standard question formats in the language of these most frequent words and intelligently match the customer service system with the answers corresponding to those formats.

[0084] Example 2:

[0085] like Figure 2 As shown, to achieve the above-mentioned technical objectives, this disclosure also provides an intelligent customer service response method based on emotion recognition, applied in the aforementioned intelligent customer service system 100 based on emotion recognition, including:

[0086] S201: Extract and store voice data based on the dialogue between the system and the user;

[0087] S202: Perform word segmentation on the speech data to obtain word vector data;

[0088] S203: Extract entity keywords from the word vector data and sort the word frequencies of the entity keywords in the first order;

[0089] S204: Extract emotion keywords from the word vector data and perform a second sorting on the word frequency of the emotion keywords;

[0090] S205: Based on the first sorting and the second sorting, traverse the historical response strategies and select the historical response strategy with the highest matching degree as the response strategy for this time;

[0091] S206: Generate a response voice statement based on the current response strategy.

[0092] like Figure 3 As shown:

[0093] Furthermore, after extracting the sentiment keywords from the word vector data and performing a second sorting of the frequency of the sentiment keywords, the method further includes:

[0094] S2041: Match emotional keywords in a pre-built emotional lexicon;

[0095] S2042: Correct the frequency of emotional keywords based on the preset frequency correction coefficient of emotional keywords in the emotional lexicon;

[0096] S2043: Perform a third sort on the word frequency of the corrected emotion keywords and replace the result of the second sort with the third sort.

[0097] Furthermore, the specific steps of performing word segmentation on the speech data to obtain word vector data are as follows:

[0098] The speech data is segmented using a conditional random field to obtain word vector data.

[0099] Optionally, the word segmentation process disclosed herein uses a rule-based word segmentation algorithm, which combines the analysis of the information provided above to delimit words. The core of the word segmentation algorithm is the bidirectional maximum matching method, that is, it traverses both forward and backward. Then, based on the principle that the more large-granular words the better, and the fewer non-dictionary words and single-character words the better, one point of word segmentation result is selected and output.

[0100] The publicly available method continuously enriches the knowledge base of intelligent customer service systems, thereby enhancing their ability to identify and address customer service needs. This reduces the workload of human customer service representatives and improves customer satisfaction. Furthermore, because intelligent customer service systems can monitor customer emotions in real time and take timely measures to soothe customers based on their emotional state, the risk of customer complaints is reduced, increasing customer satisfaction. The business management aspects of this method can also be improved by analyzing the underlying emotions in user voice messages to reflect customers' subjective experiences and feelings, thus supporting management decisions and ultimately enhancing the quality of customer service.

[0101] The method disclosed herein will identify the top(n) most frequent words of a day, assign the corresponding customer questions and answers to the intelligent customer service system. The intelligent customer service system will be trained using machine learning predictive modeling algorithms such as decision trees. It will learn the standard question formats in the language and mathematical expressions of these most frequent words and intelligently match the customer service system with the answers corresponding to those questions.

[0102] Example 3:

[0103] This disclosure also provides a computer storage medium storing a computer program thereon, which, when executed by a processor, is used to implement the steps of the above-described intelligent customer service response method based on emotion recognition.

[0104] The computer storage medium disclosed herein can be implemented using semiconductor memory, magnetic core memory, magnetic drum memory, or disk memory.

[0105] Semiconductor memory, primarily used in computers, mainly consists of two types of semiconductor storage elements: MOSFETs and bipolar transistors. MOSFETs offer high integration density and simple manufacturing processes but are relatively slow. Bipolar transistors have complex manufacturing processes, high power consumption, and low integration density but are fast. The advent of NMOS and CMOS technologies led to MOSFETs becoming the dominant type of semiconductor memory. NMOS is fast; for example, Intel's 1K-bit static random access memory (SRAM) has an access time of 45ns. CMOS, on the other hand, consumes less power; a 4K-bit CMOS SRAM has an access time of 300ns. The semiconductor memories mentioned above are all random access memories (RAM), meaning they can be randomly read from and written to during operation. Semiconductor read-only memories (ROMs), however, can be randomly read from but not written to during operation; they are used to store pre-programmed programs and data. ROMs are further divided into two types: non-rewritable fuse-type ROMs (PROMs) and rewritable EPROMs (EPROMs).

[0106] Magnetic core memory is characterized by low cost and high reliability, and has over 20 years of practical application experience. Before the mid-1970s, magnetic core memory was widely used as main memory. Its storage capacity could reach 10 bits or more, with the fastest access time being 300 ns. Typical international magnetic core memory capacities ranged from 4 MS to 8 MB, with access cycles of 1.0 to 1.5 μs. Even after the rapid development of semiconductor memory replaced magnetic core memory as the main memory, magnetic core memory can still be used as a large-capacity expansion memory.

[0107] Magnetic drum memory is a type of external storage device that records magnetic data. Due to its fast data access speed and stable, reliable operation, although its capacity is relatively small and it is gradually being replaced by disk storage, it is still used as external storage for real-time process control computers and medium- to large-scale computers. To meet the needs of small and microcomputers, ultra-miniature magnetic drums have emerged, which are small in size, lightweight, highly reliable, and easy to use.

[0108] Disk storage is a type of external storage device that records magnetic data. It combines the advantages of magnetic drums and magnetic tapes: its storage capacity is larger than that of magnetic drums, its access speed is faster than that of magnetic tapes, and it can be stored offline. Therefore, disks are widely used as high-capacity external storage in various computer systems. Disks are generally divided into two main categories: hard disks and floppy disks.

[0109] There are many types of hard disk storage devices. Structurally, they are divided into two types: replaceable and fixed. Replaceable disks have interchangeable platters, while fixed disks have fixed platters. Both replaceable and fixed disks have multi-platter and single-platter structures, and can be further divided into fixed-head and movable-head types. Fixed-head disks have smaller capacities, lower recording densities, and higher access speeds, but are more expensive. Movable-head disks have higher recording densities (up to 1000-6250 bits / inch), resulting in larger capacities, but their access speeds are relatively lower than fixed-head disks. Disk products can have storage capacities of several hundred megabytes, with a bit density of 6250 bits / inch and a track density of 475 tracks / inch. Multi-platter replaceable disk storage devices, due to their replaceable platters, offer very large independent capacity, and with high speeds, can store large amounts of information and are widely used in online information retrieval systems and database management systems.

[0110] Example 4:

[0111] This disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described intelligent customer service response method based on emotion recognition.

[0112] Figure 4 This is a schematic diagram of the internal structure of an electronic device in one embodiment. For example... Figure 4 As shown, the electronic device includes a processor, storage medium, memory, and network interface connected via a system bus. The storage medium stores an operating system, a database, and computer-readable instructions. The database may store control information sequences. When executed by the processor, the computer-readable instructions enable the processor to implement a communication method. The processor provides computing and control capabilities, supporting the operation of the entire computer device. The memory stores computer-readable instructions, which, when executed by the processor, enable the processor to execute an intelligent customer service response method based on emotion recognition. The network interface of the computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0113] This electronic device includes, but is not limited to, smartphones, computers, tablets, wearable smart devices, artificial intelligence devices, and power banks.

[0114] In some embodiments, the processor may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory (e.g., executing remote data read / write programs) and calls data stored in the memory to perform various functions of the electronic device and process data.

[0115] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory and at least one processor, etc.

[0116] Figure 4 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 4 The structure shown does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0117] For example, although not shown, the electronic device may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor via a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be elaborated further here.

[0118] Furthermore, the electronic device may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device and other electronic devices.

[0119] Optionally, the electronic device may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device and to display a visual user interface.

[0120] Furthermore, the computer's usable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store the operating system, applications required for at least one function, etc.; and the data storage area may store data created based on the use of blockchain nodes, etc.

[0121] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0122] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0124] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An intelligent customer service system based on emotion recognition, characterized in that, The method comprises the following steps: extracting voice data of a user based on a conversation between the system and the user and storing the voice data; performing word segmentation processing on the voice data to obtain word vector data; extracting entity keywords in the word vector data and performing first sorting on word frequencies of the entity keywords; extracting emotion keywords in the word vector data and performing second sorting on word frequencies of the emotion keywords; selecting a corresponding response strategy based on a decision algorithm according to the first sorting and the second sorting by using a decision module; generating a reply voice sentence based on the response strategy by using a voice module; The decision module is specifically configured to: select a corresponding response strategy based on the first sorting and the second sorting by using a decision tree combined with historical response decision strategies and store the current response strategy; The decision module is specifically configured to: determine whether the most leading entity keyword in the first sorting and the most leading emotion keyword in the second sorting can be found in historical response strategies, if yes, select a corresponding historical response strategy as the current corresponding response strategy and store the current response strategy; if not, perform keyword similarity matching on the most leading entity keyword in the first sorting and the most leading emotion keyword in the second sorting, and select the three historical response strategies with the highest similarity matching results as the current response strategies; The emotion recognition module is specifically configured to:

2. The system of claim 1, wherein, correct the word frequencies of the emotion keywords based on a word frequency correction coefficient of the preset emotion keywords in an emotion keyword library, so as to give a correction coefficient to the emotion keywords capable of expressing strong emotions of the user. The emotion recognition module is specifically configured to: extract the emotion keywords in the word vector data and perform emotion keyword matching in a pre-constructed emotion keyword library; 3. The system of any of claims 1-2, wherein, perform third sorting on the word frequencies of the corrected emotion keywords and replace the result of the second sorting with the third sorting. The word segmentation processing module is specifically configured to:

4. An emotion recognition-based intelligent customer service response method applied in the emotion recognition-based intelligent customer service system according to any one of claims 1-3, characterized in that, perform word segmentation processing on the voice data based on a conditional random field to obtain the word vector data. The method comprises the following steps: extracting voice data based on a conversation between the system and the user and storing the voice data; performing word segmentation processing on the voice data to obtain word vector data; extracting entity keywords in the word vector data and performing first sorting on word frequencies of the entity keywords; extracting emotion keywords in the word vector data and performing second sorting on word frequencies of the emotion keywords; traversing historical response strategies based on the first sorting and the second sorting, and selecting a historical response strategy with the highest matching degree as a current response strategy; 5. The method of claim 4, wherein, generating a reply voice sentence based on the current response strategy. After the step of extracting emotion keywords in the word vector data and performing second sorting on word frequencies of the emotion keywords, the method further comprises the following steps: performing emotion keyword matching in a pre-constructed emotion keyword library; correcting the word frequencies of the emotion keywords based on a word frequency correction coefficient of the preset emotion keywords in the emotion keyword library; The third sorting is performed on the word frequency of the modified emotional keywords, and the third sorting replaces the second sorting.

6. The method according to claim 4 or 5, characterized in that, The word segmentation processing of the voice data to obtain the word vector data is specifically: The word segmentation processing of the voice data to obtain the word vector data is specifically: 7.An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the emotion recognition based intelligent customer service response method in any one of claims 4-6 when executing the computer program.

8. A computer storage medium having stored thereon computer program instructions, wherein the computer program instructions are executable by a computer to cause the computer to perform the method according to any one of claims 1 to 7. The program instructions are executed by the processor to implement the steps of the emotion recognition based intelligent customer service response method in any one of claims 4-6. The program instructions are executed by the processor to implement the steps of the emotion recognition based intelligent customer service response method in any one of claims 4-6.

Images