CN109887525B - Intelligent customer service method and device and computer readable storage medium - Google Patents
Intelligent customer service method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN109887525B CN109887525B CN201910008833.5A CN201910008833A CN109887525B CN 109887525 B CN109887525 B CN 109887525B CN 201910008833 A CN201910008833 A CN 201910008833A CN 109887525 B CN109887525 B CN 109887525B
- Authority
- CN
- China
- Prior art keywords
- customer service
- client
- intelligent customer
- intelligent
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology, disclosing an intelligent customer service method, comprising: after a client telephone is accessed, a preset voice recognition model is adopted to recognize the voice of a client to obtain the attribute of the client, and intelligent customer service is distributed to the client according to the attribute of the client and a preset rule; recording voice data of a client in a conversation process between the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data; and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client. The invention also proposes an apparatus and a computer-readable storage medium.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an intelligent customer service method, an intelligent customer service device and a computer readable storage medium.
Background
In a traditional customer service system, a customer needs to face a complex, tedious and fussy navigation menu, the user needs to listen to menu prompts layer by layer, and key operation is performed step by step according to guidance to obtain services, so that poor experience is easily caused to the user, and the traditional key type automatic voice service faces more and more obvious challenges. Meanwhile, because a user cannot obtain convenient self-service, a large amount of service is rushed into manual seats, and valuable manual seat resources are greatly put into labor with simplicity, repeatability and low value, the overall working efficiency of the call center is difficult to improve, the operation cost is high, and the customer satisfaction is also influenced.
The intelligent customer service system is developed on the basis of large-scale knowledge processing, is applied to the industry and is suitable for the technical industries of large-scale knowledge processing, natural language understanding, knowledge management, automatic question and answer systems, reasoning and the like, and the intelligent customer service system not only provides a fine-grained knowledge management technology for enterprises, but also establishes a quick and effective technical means based on natural language for communication between the enterprises and mass users; meanwhile, statistical analysis information required by fine management can be provided for enterprises.
However, the conventional intelligent customer service system cannot solve all the problems of the customer, and when the customer problems are not satisfactorily solved, the customer satisfaction with the customer service system naturally decreases, which seriously affects the enterprise image.
Disclosure of Invention
The invention provides an intelligent customer service method, an intelligent customer service device and a computer readable storage medium, and mainly aims to provide an intelligent customer service scheme capable of enabling customers to be satisfied.
In order to achieve the above object, the intelligent customer service method of the present invention comprises:
after a customer telephone is accessed, a preset voice recognition model is adopted to recognize customer voice to obtain customer attributes, and intelligent customer service is distributed to the customer according to the customer attributes and preset rules;
recording voice data of a client in a conversation process between the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data; and
and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
Optionally, the preset speech recognition model is a continuous hidden markov speech recognition model, the client attribute includes a gender of the client, and the preset rule is that the client is assigned with a foreign-style customer service according to the gender of the client: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
Optionally, the intelligent customer service method further includes establishing the continuous hidden markov speech recognition model, including:
extracting Mel frequency cepstrum coefficients of voice data of a plurality of boys and girls as speaker identification characteristics;
and training the continuous hidden Markov speech recognition model by using the Mel frequency cepstrum coefficient and recognizing gender.
Optionally, the emotional state comprises: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or angry, the customer is judged to be unsatisfied with the service of the intelligent customer service, and the intelligent customer service is automatically switched to manual customer service.
Optionally, the intelligent customer service method further includes:
and recording the process of intelligent customer service as the history of the customer, and using the history as the input data of the optimization algorithm.
In addition, to achieve the above object, the present invention further provides an apparatus, which includes a memory and a processor, where the memory stores an intelligent customer service program that can run on the processor, and the intelligent customer service program implements the following steps when executed by the processor:
after a customer telephone is accessed, a preset voice recognition model is adopted to recognize customer voice to obtain customer attributes, and intelligent customer service is distributed to the customer according to the customer attributes and preset rules;
recording voice data of a client in a conversation process between the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data; and
and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
Optionally, the preset speech recognition model is a continuous hidden markov speech recognition model, the client attribute includes a gender of the client, and the preset rule is that the client is assigned with a foreign-style customer service according to the gender of the client: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
Optionally, the intelligent customer service program when executed by the processor further performs building the continuous hidden markov speech recognition model, including:
extracting Mel frequency cepstrum coefficients of voice data of a plurality of boys and girls as speaker identity characteristics;
training and gender recognition of the continuous hidden Markov speech recognition model using the Mel frequency cepstral coefficients.
Optionally, the emotional state comprises: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or angry, the customer is judged to be unsatisfied with the service of the intelligent customer service, and the intelligent customer service is automatically switched to manual customer service.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, which stores thereon an intelligent customer service program, which can be executed by one or more processors to implement the steps of the intelligent customer service method as described above.
After the intelligent customer service method, the intelligent customer service device and the computer readable storage medium provided by the invention are accessed to a customer telephone, a preset speech recognition model is adopted to recognize the speech of the customer to obtain the customer attribute, and the intelligent customer service is distributed to the customer according to the customer attribute and a preset rule; recording voice data of a client in a conversation process between the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data; and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client. Therefore, the invention can improve the satisfaction degree of customer service.
Drawings
Fig. 1 is a schematic flow chart of an intelligent customer service method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an internal structure of an apparatus according to an embodiment of the present invention;
FIG. 3 is a block diagram of an intelligent customer service program in the device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims of the present application and in the drawings described above, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the descriptions of "first," "second," etc. are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicit ly indicating a number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature.
Further, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In addition, technical solutions between the embodiments may be combined with each other, but must be based on the realization of the technical solutions by a person skilled in the art, and when the technical solutions are contradictory to each other or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention provides an intelligent customer service method.
In detail, referring to fig. 1, a flowchart of an intelligent customer service method according to an embodiment of the present invention is shown. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
S1, after a customer telephone is accessed, a preset voice recognition model is adopted to recognize customer voice to obtain customer attributes, and intelligent customer service is distributed to the customer according to the customer attributes and preset rules.
In a preferred embodiment of the present invention, the preset speech recognition model is a Continuous Hidden Markov speech recognition model (CHMM), the client attribute includes a gender of the client, and the preset rule is: and allocating special customer service to the customer according to the gender of the customer: when the client is identified to be female, pre-synthesized male voice intelligent customer service is distributed to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is distributed to the client.
Before automatically identifying the client attribute, the preferred embodiment of the invention firstly establishes the continuous hidden Markov speech recognition models according to the speech data of boys and girls respectively; in the speech recognition process, the speech uttered by the client is captured, as is the case when the telephone call is made, "feed? ", and recognizing the gender of the customer by using the continuous hidden Markov speech recognition model.
In the preferred embodiment of the present invention, when establishing the continuous hidden markov speech recognition model, mel Frequency Cepstrum Coefficients (MFCCs) of the speech data of a plurality of boys and girls are extracted as the characteristics of the speaker personality, and then the Mel frequency cepstrum coefficients are used to train and recognize the gender of the continuous hidden markov speech recognition model. The method is simple and easy to implement, and can achieve a high recognition rate of gender.
In the CHMM, mel frequency cepstrum coefficients of speaker voice data are input, a mixed Gaussian function is adopted as an output probability density function, the state number of a model is 6, the number of the mixed Gaussian functions of each state is 3, the model adopts a topological structure without skip from left to right, a Baum-Welch algorithm is used for CHMM parameter training, and a forward-backward algorithm is used for calculating the output probability of the CHMM.
And S2, recording voice data of the client in the conversation process of the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data.
In a preferred embodiment of the present invention, the emotion characteristic parameters include amplitude energy, pitch frequency, formant, and the like.
The amplitude energy characteristic of the speech data can be represented by a short-time average amplitude because the short-time average amplitude is an operation of an absolute value, is insensitive to a high level, and is simplified in calculation. Wherein, the amplitude energy of sadness is obviously less than that of other happy, angry and calm emotions, and the amplitude energy of happy and angry is relatively higher. Therefore, four types of emotions can be roughly distinguished by using the amplitude energy characteristics.
The following four parameters are calculated as characteristic parameters related to amplitude energy: let E = (E) 1 ,E 2 ,...,E k ) Is the amplitude energy of a segment of speech data, where k is the number of frames in the sentence. The four amplitude energy parameters include: maximum energy value E max ＝max(E 1 ,E 2 ,…,E k ) Minimum energy value E min ＝min(E 1 ,E 2 ,…,E k ) Energy mean value
And energy first order difference mean->
The pitch frequency is the frequency of vocal cord vibration when voiced sound occurs, and its reciprocal is the pitch period. The fundamental tone is related to physical quantities such as vocal cord length and mass of a person, and thus, is related to physiological states such as age, sex, and emotion of a person.
The following six parameters are calculated as characteristic parameters related to the fundamental tone frequency: let P = (P) 1 ,p 2 ,...,p m ) Is the pitch frequency of a segment of speech data, where m is the frame number of the pitch frequency of the sentence, i.e., the voiced frame number. The parameters of the six pitch frequencies include: minimum pitch frequency value P min ＝min(p 1 ,p 2 ,...,p m ) Pitch frequency variation range
Mean value of the pitch frequency->
Variance of fundamental frequency
Rate of change of fundamental frequency
Variance of first order difference of pitch frequency
Formants refer to regions where energy is relatively concentrated in the frequency spectrum of sound, and are not only determinants of sound quality but also reflect physical characteristics of the vocal tract (resonance cavity). Formant features may reflect emotional feature trends to some extent.
The scheme calculates the following threeThe parameters are taken as characteristic parameters related to formants: let F = (F) 1 ,f 2 ,...,f k ) Is the formant of a piece of speech data, where k is the number of frames of the sentence of speech. The three formant parameters include: mean value of resonance peak
Formant rate of change->
Formant first order difference mean->
And S3, judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
In a preferred embodiment of the present invention, the emotional state includes: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or anger, the customer is judged to be unsatisfied with the service of the intelligent customer service, the intelligent customer service is automatically switched to the manual customer service, and the service quality of the customer is kept.
In a preferred embodiment of the present invention, the predetermined determining method is a machine learning method, which includes a support vector machine.
The basic idea of the support vector machine is as follows: for the linear separable problem, the sample points of the input features are mapped to a high-dimensional feature space using a kernel function so that the corresponding sample space is linearly separable. And establishing a classification hyperplane as a decision surface, so that the isolation edge of the positive example and the negative example is maximized.
The invention firstly needs to train the support vector machine, and the training method comprises the following steps: and selecting three sentences of voice data of each emotion from a voice library as training samples. Due to the preferred implementation of the inventionFor example, four kinds of emotions of happiness, calmness, anger and sadness are identified, so that 12 sentences of voice data are selected in total to train the support vector machine, and the parameter w is solved, namely the solution
Wherein x is i For samples after extraction of speech emotion features, y i Is a sample label, and i is the number of samples. Further, the functions can be converted to ≦ based upon constructing the Lagrangian function, the KKT condition, and solving the dual problem>
K(x i ,x j )＝α i α j <x i ,x j >The kernel function is a Gaussian kernel function, namely K (x) i ,x j )＝exp(-γ||x i -x j || 2 ),γ>0. And after the parameter alpha is solved, the training of the support vector machine is finished.
In the preferred embodiment of the present invention, the extracted emotion feature parameters of the voice data are input into the trained support vector machine, so that the corresponding emotional state of the client can be output, and the client is judged to be happy, calm, angry or sad.
And S4, recording the process of the intelligent customer service as the history of the customer, and using the history as the input data of the optimization algorithm to optimize the service of the intelligent customer service.
If the history records show that the intelligent customer service cannot meet the preset proportion, such as 80% of customers, the method can optimize the machine algorithm in the intelligent customer service by adopting a characteristic parameter normalization optimization algorithm.
The invention also provides a device for executing the intelligent customer service. Fig. 3 is a schematic diagram of an internal structure of an apparatus according to an embodiment of the present invention.
In this embodiment, the apparatus 1 may be a terminal device such as a smart phone, a tablet Computer, or a portable Computer, a PC (Personal Computer), a server group, or the like. The apparatus 1 comprises at least a memory 11, a processor 12, a communication bus 13, and a network interface 14.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the apparatus 1, for example a hard disk of the apparatus 1. The memory 11 may in other embodiments also be an external storage device of the apparatus 1, such as a plug-in hard disk provided on the apparatus 1, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. Further, the memory 11 may also comprise both internal memory units of the apparatus 1 and external memory devices. The memory 11 may be used not only to store application software installed in the apparatus 1 and various types of data, such as a code of the smart customer service program 01, but also to temporarily store data that has been output or is to be output.
The processor 12 may be, in some embodiments, a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip, and is used for executing program codes stored in the memory 11 or Processing data, such as executing the smart customer service program 01.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), typically used to establish a communication link between the apparatus 1 and other electronic devices.
Optionally, the apparatus 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the apparatus 1 and for displaying a visual user interface.
While FIG. 3 shows only the apparatus 1 with the components 11-14 and the intelligent customer service program 01, those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of the apparatus 1, and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
In the embodiment of the apparatus 1 shown in fig. 3, the memory 11 stores an intelligent customer service program 01; the following steps are implemented when the processor 12 executes the intelligent customer service program 01 stored in the memory 11:
step one, after a customer telephone is accessed, automatically identifying the customer attribute by adopting a preset voice recognition model, and automatically distributing intelligent customer service to the customer according to the customer attribute and a preset rule.
In a preferred embodiment of the present invention, the preset speech recognition model is a Continuous Hidden Markov speech recognition model (CHMM), the client attribute includes a gender of the client, and the preset rule is: allocating special customer service to the customer according to the gender of the customer: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
Before automatically identifying the client attribute, the preferred embodiment of the invention firstly establishes the continuous hidden Markov speech recognition models respectively according to the speech data of boys and girls; in speech recognition, the speech uttered by the client is captured, as is the speech spoken by the client when the telephone is connected? ", and recognizing the gender of the customer by using the continuous hidden Markov speech recognition model.
In the preferred embodiment of the present invention, when establishing the continuous hidden markov speech recognition model, mel Frequency Cepstrum Coefficients (MFCC) of the speech data of a plurality of boys and girls are extracted as speaker characteristic features, and then the Mel frequency cepstrum coefficients are used to train and recognize the gender of the continuous hidden markov speech recognition model. The method is simple and easy to implement, and can achieve a high recognition rate of gender.
In the CHMM, mel frequency cepstrum coefficients of speaker voice data are input, a mixed Gaussian function is adopted as an output probability density function, the state number of a model is 6, the number of the mixed Gaussian functions of each state is 3, the model adopts a topological structure without skip from left to right, a Baum-Welch algorithm is used for CHMM parameter training, and a forward-backward algorithm is used for calculating the output probability of the CHMM.
And step two, recording voice data of the client in the conversation process of the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data.
In a preferred embodiment of the present invention, the emotion characteristic parameters include amplitude energy, pitch frequency, formant, and the like.
The amplitude energy characteristic of the speech data can be represented by a short-time average amplitude because the short-time average amplitude is an operation of an absolute value, is insensitive to a high level, and is simplified in calculation. Wherein, the amplitude energy of sadness is obviously less than that of other happy, angry and calm emotions, and the amplitude energy of happy and angry is relatively higher. Therefore, four types of emotions can be roughly distinguished by using the amplitude energy characteristics.
The following four parameters are calculated as characteristic parameters related to amplitude energy: let E = (E) 1 ,E 2 ,...,E k ) Is the amplitude energy of a segment of speech data, where k is the number of frames in the sentence. The four amplitude energy parameters include: maximum energy value E max＝ max(E 1 ,E 2 ,…,E k ) Minimum energy value E min ＝min(E 1 ,E 2 ,…,E k ) Energy mean value
And the first order difference mean->
The pitch frequency is the frequency of vocal cord vibration when voiced sound occurs, and its reciprocal is the pitch period. The fundamental tone is related to physical quantities such as vocal cord length and mass of a person, and thus, is related to physiological states such as age, sex, and emotion of a person.
The following six parameters are calculated as characteristic parameters related to the fundamental tone frequency: let P = (P) 1 ,p 2 ,...,p m ) Is the pitch frequency of a segment of speech data, where m is the number of frames of the pitch frequency of the sentence, i.e., the number of voiced frames. The parameters of the six pitch frequencies include: minimum pitch frequency value P min ＝min(p 1 ,p 2 ,...,p m ) Pitch frequency variation range
Mean value of the pitch frequency->
Variance of pitch frequency
Rate of change of fundamental frequency
Variance of first order difference of pitch frequency
Formants refer to regions where energy is relatively concentrated in the frequency spectrum of sound, and are not only determinants of sound quality but also reflect physical characteristics of the vocal tract (resonance cavity). Formant features may reflect emotional feature trends to some extent.
The following three parameters are calculated as characteristic parameters related to the formants in the scheme: let F = (F) 1 ,f 2 ,...,f k ) Is the formant of a piece of speech data, where k is the number of frames of the sentence of speech. The three formant parameters include:mean value of resonance peak
Formant rate of change->
Formant first order difference mean->
And thirdly, judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
In a preferred embodiment of the present invention, the emotional states include: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or anger, the customer is judged to be unsatisfied with the service of the intelligent customer service, the intelligent customer service is automatically switched to the manual customer service, and the service quality of the customer is kept.
In a preferred embodiment of the present invention, the predetermined determining method is a machine learning method, which includes a support vector machine.
The basic idea of the support vector machine is as follows: for the linear separable problem, the sample points of the input features are mapped to a high-dimensional feature space using a kernel function so that the corresponding sample space is linearly separable. And establishing a classification hyperplane as a decision surface, so that the isolation edge of the positive case and the negative case is maximized.
The invention firstly needs to train the support vector machine, and the training method comprises the following steps: and selecting three sentences of voice data of each emotion from a voice library as training samples. Because the preferred embodiment of the invention carries out the recognition of four types of emotions of happiness, calmness, anger and sadness, 12 sentences of voice data are selected in total to train the support vector machine, and the parameter w is solved, namely the solution is carried out
Wherein x is i For samples after extraction of speech emotion features, y i Is a sample label, and i is the number of samples. The function can be converted to ÷ by constructing a lagrangian function, a KKT condition, and a solution to the dual problem>
K(x i ,x j )＝α i α j <x i ,x j >The kernel function is a Gaussian kernel function, namely k (x) i ,x j )＝exp(-γ||x i -x j || 2 ),γ>0. After the parameter alpha is calculated, the training of the support vector machine is finished.
In the preferred embodiment of the present invention, the extracted emotion feature parameters of the voice data are input into the trained support vector machine, so that the corresponding emotional state of the client can be output, and the client is judged to be happy, calm, angry or sad.
And step four, recording the process of the intelligent customer service as the history of the customer, and using the history as the input data of the optimization algorithm to optimize the service of the intelligent customer service.
If the history records show that the intelligent customer service cannot meet the preset proportion, such as 80% of customers, the method can optimize the machine algorithm in the intelligent customer service by adopting a characteristic parameter regular optimization algorithm.
Optionally, in the embodiment of the present invention, the intelligent customer service program 01 may also be divided into one or more modules, and one or more modules are stored in the memory 11 and executed by one or more processors (in this embodiment, the processor 12) to implement the present invention, where a module referred to in the present invention refers to a series of computer program instruction segments capable of performing a specific function, and is used for describing an execution process of the intelligent customer service program in the apparatus.
For example, referring to fig. 3, which is a schematic diagram illustrating program modules of an intelligent customer service program in an embodiment of the apparatus of the present invention, in this embodiment, the intelligent customer service program 01 can be divided into a customer service distribution module 10, an emotional feature extraction module 20, and a satisfaction degree determination module 30. Preferably, the intelligent customer service program 01 further comprises an optimization module 40.
Exemplarily, the following steps are carried out:
the customer service distribution module 10 is configured to: after a customer telephone is accessed, a preset speech recognition model is adopted to recognize the speech of the customer to obtain the customer attribute, and intelligent customer service is distributed to the customer according to the customer attribute and a preset rule.
Optionally, the preset speech recognition model is a continuous hidden markov speech recognition model, the client attribute includes a gender of the client, and the preset rule is that the client is assigned with a foreign-style customer service according to the gender of the client: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
Optionally, the intelligent customer service method further includes establishing the continuous hidden markov speech recognition model, including:
extracting Mel frequency cepstrum coefficients of voice data of a plurality of boys and girls as speaker identification characteristics;
training and gender recognition of the continuous hidden Markov speech recognition model using the Mel frequency cepstral coefficients.
The emotion feature extraction module 20 is configured to: and recording voice data of the client in the conversation process of the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data.
Optionally, the emotional state comprises: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or anger, the customer is judged to be unsatisfied with the service of the intelligent customer service, and the intelligent customer service is automatically switched to manual customer service.
The satisfaction judging module 30 is configured to: and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
Optionally, in a preferred embodiment of the present invention, the emotional state of the client includes: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or angry, the customer is inferred to be unsatisfied with the service attitude of the intelligent customer service, and the intelligent customer service is quickly switched to the manual customer service.
Preferably, the preset judgment method is a machine learning method, and includes a support vector machine.
The optimization module 40 is configured to: and recording the process of intelligent customer service as the history of the customer, and using the history as the input data of the optimization algorithm.
The functions or operation steps of the aforementioned program modules such as the customer service distribution module 10, the emotional characteristic extraction module 20, the satisfaction degree judgment module 30, and the optimization module 40 when executed are substantially the same as those of the aforementioned embodiment, and are not described herein again.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores an intelligent customer service program, and the intelligent customer service program is executable by one or more processors to implement the following operations:
after a customer telephone is accessed, a preset voice recognition model is adopted to recognize customer voice to obtain customer attributes, and intelligent customer service is distributed to the customer according to the customer attributes and preset rules;
recording voice data of a client in a conversation process between the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data; and
and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
The specific implementation of the computer-readable storage medium of the present invention is substantially the same as the embodiments of the intelligent customer service device and the method, and will not be described herein again.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one of 8230, and" comprising 8230does not exclude the presence of additional like elements in a process, apparatus, article, or method comprising the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. An intelligent customer service method, characterized in that the method comprises:
after a client telephone is accessed, a preset voice recognition model is adopted to recognize the voice of a client to obtain the attribute of the client, and intelligent customer service is distributed to the client according to the attribute of the client and a preset rule;
recording voice data of a client in a conversation process of the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data, wherein the emotional characteristic parameters comprise amplitude energy, fundamental tone frequency and formants; and
and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
2. The intelligent customer service method of claim 1 wherein the predetermined speech recognition model is a continuous hidden markov speech recognition model, the customer attributes include a gender of the customer, and the predetermined rules are for assigning a foreign customer service to the customer based on the gender of the customer: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
3. The intelligent customer service method of claim 1 or 2 further comprising building the continuous hidden markov speech recognition model comprising:
extracting Mel frequency cepstrum coefficients of voice data of a plurality of boys and girls as speaker identity characteristics;
training and gender recognition of the continuous hidden Markov speech recognition model using the Mel frequency cepstral coefficients.
4. The intelligent customer service method of claim 1 wherein the emotional state comprises: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or anger, the customer is judged to be unsatisfied with the service of the intelligent customer service, and the intelligent customer service is automatically switched to manual customer service.
5. The intelligent customer service method of claim 1 wherein the intelligent customer service method further comprises:
and recording the process of intelligent customer service as the history of the customer, and using the history as the input data of the optimization algorithm.
6. An intelligent customer service device, comprising a memory and a processor, wherein the memory has stored thereon an intelligent customer service program operable on the processor, the intelligent customer service program when executed by the processor implementing the steps of:
after a client telephone is accessed, a preset voice recognition model is adopted to recognize the voice of a client to obtain the attribute of the client, and intelligent customer service is distributed to the client according to the attribute of the client and a preset rule;
recording voice data of a client in a conversation process of the distributed intelligent customer service and the client, and extracting emotional characteristic parameters of the client from the voice data, wherein the emotional characteristic parameters comprise amplitude energy, fundamental tone frequency and formants; and
and judging the current emotional state of the client by adopting a preset judgment method according to the emotional characteristic parameters of the voice data, and judging whether to switch the intelligent customer service into the artificial customer service according to the current emotional state of the client.
7. The intelligent customer service device of claim 6 wherein the predetermined speech recognition model is a continuous hidden markov speech recognition model, the customer attributes include a gender of the customer, and the predetermined rules are for assigning a foreign customer service to the customer based on the gender of the customer: when the client is identified to be female, pre-synthesized male voice intelligent customer service is allocated to the client, and when the client is identified to be male, pre-synthesized female voice intelligent customer service is allocated to the client.
8. The intelligent customer service device of claim 6 or 7 wherein the intelligent customer service program when executed by the processor further performs building the continuous hidden Markov speech recognition model comprising:
extracting Mel frequency cepstrum coefficients of voice data of a plurality of boys and girls as speaker identity characteristics;
training and gender recognition of the continuous hidden Markov speech recognition model using the Mel frequency cepstral coefficients.
9. The intelligent customer service device of claim 6 wherein the emotional state comprises: sadness, happiness, anger and calmness, if the current emotional state of the customer is judged to be sadness or angry, the customer is judged to be unsatisfied with the service of the intelligent customer service, and the intelligent customer service is automatically switched to manual customer service.
10. A computer-readable storage medium, having stored thereon, a smart customer service program executable by one or more processors to perform the steps of the smart customer service method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008833.5A CN109887525B (en) | 2019-01-04 | 2019-01-04 | Intelligent customer service method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008833.5A CN109887525B (en) | 2019-01-04 | 2019-01-04 | Intelligent customer service method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109887525A CN109887525A (en) | 2019-06-14 |
| CN109887525B true CN109887525B (en) | 2023-04-07 |
Family
ID=66925546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910008833.5A Active CN109887525B (en) | 2019-01-04 | 2019-01-04 | Intelligent customer service method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109887525B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335313B (en) | 2019-06-17 | 2022-12-09 | 腾讯科技（深圳）有限公司 | Audio acquisition equipment positioning method and device and speaker identification method and system |
| CN110472023A (en) * | 2019-07-10 | 2019-11-19 | 深圳追一科技有限公司 | Customer service switching method, device, computer equipment and storage medium |
| CN110428267B (en) * | 2019-07-31 | 2023-01-06 | 联想(北京)有限公司 | Content processing method and device, computer system and readable storage medium |
| CN110874394A (en) * | 2019-10-12 | 2020-03-10 | 中国平安财产保险股份有限公司 | Intelligent answering method, electronic device and storage medium |
| CN111225115B (en) * | 2019-11-25 | 2021-06-25 | 中国银行股份有限公司 | Information providing method and device |
| CN113099043A (en) * | 2019-12-23 | 2021-07-09 | 中国电信股份有限公司 | Customer service control method, apparatus and computer-readable storage medium |
| CN111510566B (en) * | 2020-03-16 | 2021-05-28 | 深圳追一科技有限公司 | Method and device for determining call label, computer equipment and storage medium |
| CN111739516A (en) * | 2020-06-19 | 2020-10-02 | 中国—东盟信息港股份有限公司 | Speech recognition system for intelligent customer service call |
| CN112509574B (en) * | 2020-11-26 | 2022-07-22 | 上海济邦投资咨询有限公司 | Investment consultation service system based on big data |
| CN112671984B (en) * | 2020-12-01 | 2022-09-23 | 长沙市到家悠享网络科技有限公司 | Service mode switching method and device, robot customer service and storage medium |
| CN113035240B (en) * | 2021-02-25 | 2024-02-02 | 平安普惠企业管理有限公司 | Voice broadcasting method, device, equipment and storage medium |
| CN113314112A (en) * | 2021-04-21 | 2021-08-27 | 北京三快在线科技有限公司 | Dialogue method, dialogue device, electronic equipment and storage medium |
| CN113342960A (en) * | 2021-07-07 | 2021-09-03 | 上海华客信息科技有限公司 | Client appeal processing method, system, device and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872792A (en) * | 2016-03-25 | 2016-08-17 | 乐视控股（北京）有限公司 | Voice-based service recommending method and device |
| CN107590159A (en) * | 2016-07-08 | 2018-01-16 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
| CN106503275A (en) * | 2016-12-30 | 2017-03-15 | 首都师范大学 | The tone color collocation method of chat robots and device |
-
2019
- 2019-01-04 CN CN201910008833.5A patent/CN109887525B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109887525A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887525B (en) | Intelligent customer service method and device and computer readable storage medium | |
| US10991366B2 (en) | Method of processing dialogue query priority based on dialog act information dependent on number of empty slots of the query | |
| US10896428B1 (en) | Dynamic speech to text analysis and contact processing using agent and customer sentiments | |
| US9742912B2 (en) | Method and apparatus for predicting intent in IVR using natural language queries | |
| US8170866B2 (en) | System and method for increasing accuracy of searches based on communication network | |
| CN109313892B (en) | Robust speech recognition method and system | |
| CN109767765A (en) | Talk about art matching process and device, storage medium, computer equipment | |
| WO2022178969A1 (en) | Voice conversation data processing method and apparatus, and computer device and storage medium | |
| CN111710337B (en) | Voice data processing method and device, computer readable medium and electronic equipment | |
| CN112966082A (en) | Audio quality inspection method, device, equipment and storage medium | |
| CN113223560A (en) | Emotion recognition method, device, equipment and storage medium | |
| CN113160819B (en) | Method, apparatus, device, medium, and product for outputting animation | |
| CN112233680A (en) | Speaker role identification method and device, electronic equipment and storage medium | |
| CN114138960A (en) | User intention identification method, device, equipment and medium | |
| KR20220071059A (en) | Method for evaluation of emotion based on emotion analysis model and device using the same | |
| CN115497465A (en) | Voice interaction method and device, electronic equipment and storage medium | |
| CN114817478A (en) | Text-based question and answer method and device, computer equipment and storage medium | |
| CN109727091A (en) | Products Show method, apparatus, medium and server based on dialogue robot | |
| Jia et al. | A deep learning system for sentiment analysis of service calls | |
| CN108899016B (en) | Voice text normalization method, device and equipment and readable storage medium | |
| US20240005911A1 (en) | Systems and methods to improve trust in conversations with deep learning models | |
| KR101891495B1 (en) | Method and computer device for controlling a display to display conversational response candidates to a user utterance input, and computer readable recording medium | |
| CN115687934A (en) | Intention recognition method and device, computer equipment and storage medium | |
| CN114925159A (en) | User emotion analysis model training method and device, electronic equipment and storage medium | |
| CN115495541B (en) | Corpus database, corpus database maintenance method, apparatus, device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |