CN111143537A - Service method, device, equipment and medium based on intelligent customer service system - Google Patents
Service method, device, equipment and medium based on intelligent customer service system Download PDFInfo
- Publication number
- CN111143537A CN111143537A CN201911398196.3A CN201911398196A CN111143537A CN 111143537 A CN111143537 A CN 111143537A CN 201911398196 A CN201911398196 A CN 201911398196A CN 111143537 A CN111143537 A CN 111143537A
- Authority
- CN
- China
- Prior art keywords
- session
- customer
- manual
- target client
- service
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012549 training Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a service method, a service device, service equipment and a computer readable storage medium based on an intelligent customer service system, wherein the method comprises the following steps: acquiring real-time session information of a target client session in an intelligent client service system; wherein the target client session is a multi-turn session of the target client; inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result; when the judgment result is satisfactory, continuing to provide service for the target client by using the intelligent client service system, and entering the step of acquiring real-time session information of the target client session in the intelligent client service system; and when the judgment result is unsatisfactory, switching the target client session into a manual session in a manual session system, and providing service for the target client by using the manual session. Therefore, the method can reduce the pressure of manual customer service by using the intelligent customer service system, save human resources and improve the use experience of customers.
Description
Technical Field
The invention relates to the field of intelligent customer service systems, in particular to a service method, a service device, service equipment and a computer readable storage medium based on the intelligent customer service system.
Background
At present, in order to reduce the workload of manual customer service and reduce the consumption of manpower resources, many industries and units begin to use intelligent customer service systems. By presetting a knowledge base of intelligent question answering, when a client question is received, a standard question most similar to the client question is found from the knowledge base of intelligent question answering, a standard answer corresponding to the standard question is obtained, and then the client question is answered by using the standard answer. However, due to the influence of factors such as a sentence pattern of a customer problem or ambiguous words in a customer problem, some customer problems cannot be matched to a corresponding standard problem, or a plurality of customer problems are matched to the same standard problem, in this case, the actual problem of the customer may not be solved, thereby reducing the experience of the customer.
Therefore, how to reduce the consumption of manpower resources by using the intelligent customer service system and improve the use experience of customers is a technical problem to be solved by technical personnel in the field at present.
Disclosure of Invention
In view of the above, the present invention provides a service method based on an intelligent customer service system, which can not only reduce the consumption of manpower resources by using the intelligent customer service system, but also improve the user experience of the customer; another object of the present invention is to provide a service device, an apparatus and a computer-readable storage medium based on an intelligent customer service system, all of which have the above advantages.
In order to solve the technical problem, the invention provides a service method based on an intelligent customer service system, which comprises the following steps:
acquiring real-time session information of a target client session in an intelligent client service system; wherein the target client session is a multi-turn session of the target client;
inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
when the judgment result is satisfactory, continuing to provide service for the target customer by using the intelligent customer service system, and entering the step of acquiring real-time session information of the target customer session in the intelligent customer service system;
and when the judgment result is unsatisfactory, switching the target customer session into a manual session in a manual session system, and providing service for the target customer by using the manual session.
Preferably, when the determination result is unsatisfactory, the process of switching the target client session to a manual session in a manual session system and providing a service to the target client by using the manual session specifically includes:
and when the judgment result is unsatisfactory, switching the target client session into a manual session in a manual session system corresponding to the problem type according to the problem type of the client problem in the target client session, and providing service for the target client by using the manual session.
Preferably, the process of training the customer satisfaction judging model specifically includes:
acquiring sample session information; wherein the sample session information comprises session data information, session text information and type data;
and inputting the sample session information into a deep learning neural network for learning training to obtain the customer satisfaction judging model.
Preferably, after the obtaining of the sample session information, the method further includes:
and performing corresponding preprocessing operation on the sample session information according to the data type of the sample session information.
Preferably, the process of obtaining the sample session information specifically includes:
and acquiring the sample session information in the form of a time period sliding window of the season length.
Preferably, further comprising:
recording the issue type of the customer issue in the target customer session.
Preferably, further comprising:
and calculating the frequency of switching the target client session into the manual session.
In order to solve the above technical problem, the present invention further provides a service device based on an intelligent customer service system, including:
the acquisition module is used for acquiring real-time session information of a target client session in the intelligent client service system; wherein the target client session is a multi-turn session of the target client;
the judging module is used for inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
the first execution module is used for continuously utilizing the intelligent customer service system to provide service for the target customer and entering the step of acquiring real-time session information of the target customer session in the intelligent customer service system when the judgment result is satisfactory;
and the second execution module is used for switching the target client session into a manual session in a manual session system and providing service for the target client by using the manual session when the judgment result is unsatisfactory.
In order to solve the above technical problem, the present invention further provides a service device based on an intelligent customer service system, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of any one of the service methods based on the intelligent customer service system when executing the computer program.
In order to solve the above technical problem, the present invention further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program implements the steps of any one of the above service methods based on an intelligent customer service system.
Therefore, the service method based on the intelligent customer service system provided by the invention determines whether the target customer is satisfied with the target customer session of the intelligent customer service system or not by acquiring the real-time session information of the target customer session in the intelligent customer service system and utilizing the pre-trained customer satisfaction judging model to judge whether the target customer is satisfied with the target customer session of the intelligent customer service system or not according to the real-time session information so as to determine whether the switching to the manual session of the manual session system is required or not. Therefore, the method can not only utilize the intelligent customer service system to reduce the pressure of manual customer service and save manpower resources, but also utilize the manual conversation in the manual conversation system to continuously solve the actual requirements of the customers when judging that the intelligent customer service system cannot solve the actual requirements of the customers, thereby improving the use experience of the customers.
In order to solve the technical problems, the invention also provides a service device, equipment and a computer readable storage medium based on the intelligent customer service system, which have the beneficial effects.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a service method based on an intelligent customer service system according to an embodiment of the present invention;
fig. 2 is a structural diagram of a service device based on an intelligent customer service system according to an embodiment of the present invention;
fig. 3 is a structural diagram of a service device based on an intelligent customer service system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The core of the embodiment of the invention is to provide a service method based on an intelligent customer service system, which can not only reduce the consumption of manpower resources by using the intelligent customer service system, but also improve the use experience of customers; the other core of the invention is to provide a service device, equipment and a computer readable storage medium based on the intelligent customer service system, which have the beneficial effects.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of a service method based on an intelligent customer service system according to an embodiment of the present invention. As shown in fig. 1, a service method based on an intelligent customer service system includes:
s10: acquiring real-time session information of a target client session in an intelligent client service system;
wherein the target client session is a multi-turn session of the target client;
s20: inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
s30: when the judgment result is satisfactory, the intelligent customer service system is continuously utilized to provide service for the target customer, and the step S10 is carried out: acquiring real-time session information of a target client session in an intelligent client service system;
s40: and when the judgment result is unsatisfactory, switching the target client session into a manual session in a manual session system, and providing service for the target client by using the manual session.
In this embodiment, a customer satisfaction determination model is trained using sample session information. Then, real-time session information in a target client session of a target client in the intelligent customer service system is acquired, and the embodiment requires that the target client session is a multi-turn session of the target client, that is, the target client needs to perform multiple questioning, so that the questioning and answering service can be continuously provided for the target client corresponding to the target client session after the client distribution is performed.
And then, inputting the acquired real-time session information into a client satisfaction judging model, judging the satisfaction of the current target client session to obtain a satisfaction judging result of the target client on the target client session, and checking whether the result is satisfactory or unsatisfactory.
And then, according to the current judgment result, carrying out corresponding client shunting operation. Specifically, if the current judgment result is satisfactory, that is, the intelligent answer of the target client to the current intelligent client service system is satisfactory, the actual requirement of the target client can be solved, so that the next round of problem of the target client can be answered by continuously utilizing the intelligent client service system, that is, the target client is provided with service by continuously utilizing the intelligent client service system; if the current judgment result is unsatisfactory, that is, the intelligent answer of the target client to the current intelligent client service system is unsatisfactory, and the intelligent answer of the intelligent client service system cannot meet the actual requirement of the target client, the target client session needs to be switched to the manual session of the manual session system, and the manual session is used for providing services for the target client.
Therefore, the service method based on the intelligent customer service system provided by the embodiment of the invention determines whether to switch to the manual session of the manual session system by acquiring the real-time session information of the target customer session in the intelligent customer service system and judging whether the target customer session of the intelligent customer service system is satisfied with the target customer session of the target customer by utilizing the pre-trained customer satisfaction judging model according to the real-time session information. Therefore, the method can not only utilize the intelligent customer service system to reduce the pressure of manual customer service and save manpower resources, but also utilize the manual conversation in the manual conversation system to continuously solve the actual requirements of the customers when judging that the intelligent customer service system cannot solve the actual requirements of the customers, thereby improving the use experience of the customers.
On the basis of the foregoing embodiment, this embodiment further describes and optimizes the technical solution, and specifically, in this embodiment, when the determination result is unsatisfactory, the process of switching the target client session to a manual session in a manual session system and providing a service to the target client by using the manual session specifically includes:
and when the judgment result is unsatisfactory, switching the target client session into an artificial session in an artificial session system corresponding to the problem type according to the problem type of the client problem in the target client session, and providing service for the target client by using the artificial session.
Specifically, in this embodiment, the manual session of the manual session system corresponding to each question type is preset, then, when it is determined that the determination result is unsatisfactory, the question type of the customer question in the target customer session is further obtained, and then, according to the correspondence between the question type and the manual session of the manual session system, the target customer session is switched to the manual session in the manual session system corresponding to the question type.
Therefore, according to the method, when the intelligent customer service system cannot meet the actual requirements of the target customer and needs to perform customer distribution, the target customer is further allocated to the corresponding type of manual session according to the problem type of the target customer, so that the customer problem of the target customer can be solved more pertinently, and the use experience of the customer is further improved.
On the basis of the foregoing embodiment, the present embodiment further describes and optimizes the technical solution, and specifically, in the present embodiment, the process of training the customer satisfaction determination model specifically includes:
acquiring sample session information; the sample session information comprises session data information, session text information and type data;
and inputting the sample session information into a deep learning neural network for learning training to obtain a customer satisfaction judgment model.
Specifically, the sample session information includes session data information, session text information, and type data. More specifically, in this embodiment, the session data information includes: in each session, the client proposes the creation time of each client question; obtaining the number of conversation rounds corresponding to each conversation by the occurrence frequency of each conversation ID; average length of client questions under each session ID; in each session, the average length of the standard questions matched according to the customer questions; the session duration corresponding to each session; wherein, the conversation duration is obtained by sequencing each round of conversations from early to late according to the creation time, subtracting the earliest time (t1) from the latest time (t2), and converting the conversation duration into a numerical variable in seconds; determining the number of times of the same standard question in each session, namely the number of times of repetition of the standard question, wherein after the customer obtains a satisfactory answer, the customer does not put forward a new question and obtains the same standard question, and if the customer obtains the same standard answer in a new session, the customer question is not solved; a jaccard distance of a customer question and a corresponding standard question; and (5) carrying out the similarity of the data vectors with the standard problem after the bert fine adjustment is carried out on the client problem. The session text information mainly comprises client questions corresponding to a plurality of questions of the client in one session and standard questions corresponding to the client questions. The type data mainly comprises type variable data such as the region of a client, a product corresponding to a session and the like. It should be noted that, in actual operation, other sample session information may also be included, which is not limited in this embodiment.
As a preferred embodiment, the process of obtaining sample session information specifically includes:
sample session information is obtained in the form of a time period sliding window of the seasonal length.
In this embodiment, further considering the influence of seasonality on the customer problem, the sample session information is acquired in the form of a time period sliding window. It should be noted that, in this embodiment, the specific length of the time period sliding window is not limited, and may be specifically determined according to the actual customer problem change period.
As a preferred embodiment, after obtaining the sample session information, the method further includes:
and performing corresponding preprocessing operation on the sample session information according to the data type of the sample session information.
It should be noted that the session data information, the session text information, and the type data are divided according to data types, and may be divided into numerical data, text data, and type data. In this embodiment, according to different data types of the sample session information, a corresponding preprocessing operation is performed on the sample session information. The method comprises the following steps of carrying out data cleaning on text type data, and removing useless characters, html format, stop words, low-frequency words and the like; carrying out normalization processing on the numerical data; for type data, firstly, counting the occurrence frequency corresponding to different variables in each type of data respectively, accumulating the variables from high to low according to the occurrence frequency, and when the accumulated sum exceeds the total a quantile (for example, a is 0.8), classifying the rest of the variables into other variables, thereby reducing the number of the types of the variables in the same type.
In the embodiment, the sample session information is further preprocessed, so that the training speed of the deep learning neural network can be increased, and the judgment accuracy of the client satisfaction judgment model obtained by training can be improved.
Further, text type data and type data need to be converted into corresponding vectors, and particularly one-hot encoding can be adopted for vectorization; inputting the vectorized data of the text type data into an embedding layer (embedding layer) in the deep learning neural network to obtain a first output result; then inputting the first output result into a Bi-LSTM layer, and constructing a self-attention mechanism by utilizing a second output result of the Bi-LSTM (bidirectional long and short memory neural network) layer to obtain a third output result; combining the first output result and the second output result to obtain a fourth output result; convolving the fourth output result by using the sizes of the convolution kernels of 1-4 respectively, and outputting a fifth output result by using a preset pooling layer; the preset pooling layer can be an average pooling layer and/or a maximum pooling layer and/or a minimum pooling layer; inputting the corresponding vectors obtained by converting the session data information and the type data, a third output result corresponding to the self-attention mechanism and a fifth result output by the preset pooling layer into the full-connection layer for feature combination; and inputting the output result of the full connection layer into n hidden layers, thereby determining a customer satisfaction judgment model, wherein in the embodiment, n is 2.
It should be noted that, in actual operation, the satisfaction prediction of the customer satisfaction determination model can be further performed by using the test session data, so that the parameters of the customer satisfaction determination model are adjusted, and the determination accuracy of the customer satisfaction determination model is improved.
Therefore, the method for training the customer satisfaction judging model provided by the embodiment has the advantages that the operation mode is convenient and fast, and the customer satisfaction judging model obtained through training can accurately judge the real-time session information.
On the basis of the above embodiments, the present embodiment further describes and optimizes the technical solution, and specifically, the present embodiment further includes:
the question type of the customer question in the target customer session is recorded.
Specifically, in this embodiment, when the determination result is unsatisfactory, the client question in the target client session is acquired, the question type of the client question is determined, and then the client information, the question type, the corresponding recording time, and other information of the target client are recorded. It should be noted that, in an actual operation, the record may be performed in a preset database table, or may be performed in other forms, which is not limited in this embodiment.
According to the method and the device, the problem types of the client problems in the target client session are further recorded when the judgment result is unsatisfactory, so that the follow-up analysis of the places needing to be improved of the current intelligent client service system according to the recorded information can be facilitated, and the operation and maintenance of the intelligent client service system can be further facilitated.
On the basis of the above embodiments, the present embodiment further describes and optimizes the technical solution, and specifically, the present embodiment further includes:
the frequency of switching the target client session to a manual session is calculated.
In this embodiment, the frequency of switching the target client session to the manual session is calculated by counting the number of times of switching the target client session to the manual session within a preset time period and according to the total number of times of the target client session. It can be understood that the higher the frequency value is, the more effective and accurate answer of the customer questions cannot be realized by the current intelligent customer service system; correspondingly, the lower the frequency value is, the more effective and accurate the current intelligent customer service system can answer the customer questions.
It should be noted that, in actual operation, a frequency threshold may be further set, the currently calculated frequency value is compared with a preset frequency threshold, and when the frequency value exceeds the preset frequency threshold, corresponding prompt information may be further sent to prompt to update the knowledge base of the intelligent session system.
Therefore, in the embodiment, the reference information for performing operation and maintenance upgrading on the intelligent customer service system can be further provided by further calculating the frequency of switching the target customer session into the manual session.
The foregoing detailed description is directed to the embodiment of the service method based on the intelligent customer service system provided by the present invention, and the present invention further provides a service device, an apparatus and a computer-readable storage medium based on the intelligent customer service system corresponding to the method.
Fig. 2 is a structural diagram of a service device based on an intelligent customer service system according to an embodiment of the present invention, and as shown in fig. 2, the service device based on the intelligent customer service system includes:
the acquisition module 21 is used for acquiring real-time session information of a target client session in the intelligent client service system; wherein the target client session is a multi-turn session of the target client;
the judging module 22 is used for inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
the first execution module 23 is configured to, when the determination result is satisfactory, continue to use the intelligent customer service system to provide service for the target customer, and perform a step of acquiring real-time session information of a session of the target customer in the intelligent customer service system;
and the second execution module 24 is used for switching the target client session into a manual session in the manual session system and providing service for the target client by using the manual session when the judgment result is unsatisfactory.
The service device based on the intelligent customer service system provided by the embodiment of the invention has the beneficial effects of the service method based on the intelligent customer service system.
As a preferred embodiment, the second execution module specifically includes:
and the second execution unit is used for switching the target client session into a manual session in a manual session system corresponding to the problem type according to the problem type of the client problem in the target client session and providing service for the target client by using the manual session when the judgment result is unsatisfactory.
As a preferred embodiment, the determining module specifically includes:
an acquisition unit configured to acquire sample session information; the sample session information comprises session data information, session text information and type data;
and the training unit is used for inputting the sample session information into the deep learning neural network for learning training to obtain a customer satisfaction judging model.
As a preferred embodiment, the service device based on the intelligent customer service system further comprises:
and the preprocessing module is used for performing corresponding preprocessing operation on the sample session information according to the data type of the sample session information.
As a preferred embodiment, the acquiring unit specifically includes:
and the acquisition subunit is used for acquiring the sample session information in the form of a time period sliding window of the season length.
As a preferred embodiment, the service device based on the intelligent customer service system further comprises:
and the recording module is used for recording the problem types of the client problems in the target client session.
As a preferred embodiment, the service device based on the intelligent customer service system further comprises:
and the calculating module is used for calculating the frequency of switching the target client session into the manual session.
Fig. 3 is a structural diagram of a service device based on an intelligent customer service system according to an embodiment of the present invention, and as shown in fig. 3, a service device based on an intelligent customer service system includes:
a memory 31 for storing a computer program;
a processor 32 for implementing the steps of the intelligent customer service system based service method as described above when executing the computer program.
The service equipment based on the intelligent customer service system provided by the embodiment of the invention has the beneficial effects of the service method based on the intelligent customer service system.
In order to solve the above technical problem, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the service method based on the intelligent customer service system.
The computer-readable storage medium provided by the embodiment of the invention has the beneficial effects of the service method based on the intelligent customer service system.
The service method, device, equipment and computer readable storage medium based on the intelligent customer service system provided by the invention are described in detail above. The principles and embodiments of the present invention are explained herein using specific examples, which are set forth only to help understand the method and its core ideas of the present invention. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Claims (10)
1. A service method based on an intelligent customer service system is characterized by comprising the following steps:
acquiring real-time session information of a target client session in an intelligent client service system; wherein the target client session is a multi-turn session of the target client;
inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
when the judgment result is satisfactory, continuing to provide service for the target customer by using the intelligent customer service system, and entering the step of acquiring real-time session information of the target customer session in the intelligent customer service system;
and when the judgment result is unsatisfactory, switching the target customer session into a manual session in a manual session system, and providing service for the target customer by using the manual session.
2. The method according to claim 1, wherein the process of switching the target client session to a manual session in a manual session system and providing a service to the target client using the manual session when the determination result is unsatisfactory includes:
and when the judgment result is unsatisfactory, switching the target client session into a manual session in a manual session system corresponding to the problem type according to the problem type of the client problem in the target client session, and providing service for the target client by using the manual session.
3. The method according to claim 1, wherein the process of training the customer satisfaction determination model specifically comprises:
acquiring sample session information; wherein the sample session information comprises session data information, session text information and type data;
and inputting the sample session information into a deep learning neural network for learning training to obtain the customer satisfaction judging model.
4. The method of claim 3, after the obtaining sample session information, further comprising:
and performing corresponding preprocessing operation on the sample session information according to the data type of the sample session information.
5. The method according to claim 4, wherein the process of obtaining the sample session information specifically includes:
and acquiring the sample session information in the form of a time period sliding window of the season length.
6. The method of claim 2, further comprising:
recording the issue type of the customer issue in the target customer session.
7. The method of any one of claims 1 to 6, further comprising:
and calculating the frequency of switching the target client session into the manual session.
8. A service device based on an intelligent customer service system is characterized by comprising:
the acquisition module is used for acquiring real-time session information of a target client session in the intelligent client service system; wherein the target client session is a multi-turn session of the target client;
the judging module is used for inputting the real-time session information into a pre-trained customer satisfaction judging model to obtain a corresponding judging result;
the first execution module is used for continuously utilizing the intelligent customer service system to provide service for the target customer and entering the step of acquiring real-time session information of the target customer session in the intelligent customer service system when the judgment result is satisfactory;
and the second execution module is used for switching the target client session into a manual session in a manual session system and providing service for the target client by using the manual session when the judgment result is unsatisfactory.
9. A service device based on an intelligent customer service system, comprising:
a memory for storing a computer program;
processor for implementing the steps of the intelligent customer service system based service method according to any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the intelligent customer service system based service method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911398196.3A CN111143537A (en) | 2019-12-30 | 2019-12-30 | Service method, device, equipment and medium based on intelligent customer service system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911398196.3A CN111143537A (en) | 2019-12-30 | 2019-12-30 | Service method, device, equipment and medium based on intelligent customer service system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111143537A true CN111143537A (en) | 2020-05-12 |
Family
ID=70521961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911398196.3A Pending CN111143537A (en) | 2019-12-30 | 2019-12-30 | Service method, device, equipment and medium based on intelligent customer service system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111143537A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369080A (en) * | 2020-05-27 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Intelligent customer service solution rate prediction method and system and multi-service prediction model |
| CN111797418A (en) * | 2020-07-07 | 2020-10-20 | 中国建设银行股份有限公司 | Control method and device of online service, service terminal, server and storage medium |
| CN112543185A (en) * | 2020-11-23 | 2021-03-23 | 建信金融科技有限责任公司 | Customer service method, device and system |
| CN112668972A (en) * | 2020-12-30 | 2021-04-16 | 四川全网运通物流科技有限公司 | Logistics waybill server recommendation system |
| CN112686606A (en) * | 2020-12-30 | 2021-04-20 | 四川全网运通物流科技有限公司 | Waybill service party recommendation method |
| CN112801676A (en) * | 2021-02-04 | 2021-05-14 | 上海中通吉网络技术有限公司 | Express industry call center service method, device, equipment and system |
| CN113837323A (en) * | 2021-11-08 | 2021-12-24 | 中国联合网络通信集团有限公司 | Satisfaction prediction model training method and device, electronic equipment and storage medium |
| CN113887246A (en) * | 2021-10-19 | 2022-01-04 | 京东科技信息技术有限公司 | Method and device for detecting consistency of man-machine schemes in customer service field and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105701088A (en) * | 2016-02-26 | 2016-06-22 | 北京京东尚科信息技术有限公司 | Method and device for switching machine conversation to artificial conversation |
| 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 |
| CN108363745A (en) * | 2018-01-26 | 2018-08-03 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
| CN110059182A (en) * | 2019-03-21 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Art recommended method and device towards customer service |
| CN110309967A (en) * | 2019-06-27 | 2019-10-08 | 携程计算机技术（上海）有限公司 | Prediction technique, system, equipment and the storage medium of customer service session grading system |
| CN110533343A (en) * | 2019-09-04 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Data processing method, device and the electronic equipment of intelligent customer service system |
-
2019
- 2019-12-30 CN CN201911398196.3A patent/CN111143537A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105592237A (en) * | 2014-10-24 | 2016-05-18 | ***通信集团公司 | Method and apparatus for session switching, and intelligent customer service robot |
| CN105701088A (en) * | 2016-02-26 | 2016-06-22 | 北京京东尚科信息技术有限公司 | Method and device for switching machine conversation to artificial conversation |
| 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 |
| CN108363745A (en) * | 2018-01-26 | 2018-08-03 | 阿里巴巴集团控股有限公司 | The method and apparatus that robot customer service turns artificial customer service |
| CN110059182A (en) * | 2019-03-21 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Art recommended method and device towards customer service |
| CN110309967A (en) * | 2019-06-27 | 2019-10-08 | 携程计算机技术（上海）有限公司 | Prediction technique, system, equipment and the storage medium of customer service session grading system |
| CN110533343A (en) * | 2019-09-04 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Data processing method, device and the electronic equipment of intelligent customer service system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369080A (en) * | 2020-05-27 | 2020-07-03 | 支付宝(杭州)信息技术有限公司 | Intelligent customer service solution rate prediction method and system and multi-service prediction model |
| CN111797418A (en) * | 2020-07-07 | 2020-10-20 | 中国建设银行股份有限公司 | Control method and device of online service, service terminal, server and storage medium |
| CN111797418B (en) * | 2020-07-07 | 2023-06-06 | 建信金融科技有限责任公司 | Online service control method and device, service terminal, server and storage medium |
| CN112543185A (en) * | 2020-11-23 | 2021-03-23 | 建信金融科技有限责任公司 | Customer service method, device and system |
| CN112668972A (en) * | 2020-12-30 | 2021-04-16 | 四川全网运通物流科技有限公司 | Logistics waybill server recommendation system |
| CN112686606A (en) * | 2020-12-30 | 2021-04-20 | 四川全网运通物流科技有限公司 | Waybill service party recommendation method |
| CN112686606B (en) * | 2020-12-30 | 2023-05-12 | 四川全网运通物流科技有限公司 | Tab service side recommendation method |
| CN112668972B (en) * | 2020-12-30 | 2023-05-12 | 四川全网运通物流科技有限公司 | Logistics waybill service side recommendation system |
| CN112801676A (en) * | 2021-02-04 | 2021-05-14 | 上海中通吉网络技术有限公司 | Express industry call center service method, device, equipment and system |
| CN113887246A (en) * | 2021-10-19 | 2022-01-04 | 京东科技信息技术有限公司 | Method and device for detecting consistency of man-machine schemes in customer service field and storage medium |
| CN113837323A (en) * | 2021-11-08 | 2021-12-24 | 中国联合网络通信集团有限公司 | Satisfaction prediction model training method and device, electronic equipment and storage medium |
| CN113837323B (en) * | 2021-11-08 | 2023-07-04 | 中国联合网络通信集团有限公司 | Training method and device of satisfaction prediction model, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143537A (en) | Service method, device, equipment and medium based on intelligent customer service system | |
| CN107818798B (en) | Customer service quality evaluation method, device, equipment and storage medium | |
| CN110377911B (en) | Method and device for identifying intention under dialog framework | |
| CN112365894B (en) | AI-based composite voice interaction method and device and computer equipment | |
| EP0840975B1 (en) | Assessment of signal quality | |
| PH12020551830A1 (en) | Computerized systems and methods for determining authenticity using micro expressions | |
| CN111080109B (en) | Customer service quality evaluation method and device and electronic equipment | |
| CN111754336B (en) | Method and device for scheduling network points | |
| CN106847305B (en) | Method and device for processing recording data of customer service telephone | |
| CN114627863B (en) | Speech recognition method and device based on artificial intelligence | |
| CN110782962A (en) | Hearing language rehabilitation device, method, electronic equipment and storage medium | |
| CN110930989B (en) | Speech intention recognition method and device, computer equipment and storage medium | |
| CN110705309B (en) | Service quality evaluation method and system | |
| CN112925888B (en) | Training method and device for question-answer response and small sample text matching model | |
| CN111400466A (en) | Intelligent dialogue method and device based on reinforcement learning | |
| CN111161733B (en) | Control method and device for intelligent voice service | |
| CN112053205A (en) | Product recommendation method and device through robot emotion recognition | |
| CN111915111A (en) | Online classroom interaction quality evaluation method and device and terminal equipment | |
| CN116719984B (en) | Intelligent fuel gas data management method, internet of things system and storage medium | |
| CN113051386B (en) | Adjustment method and device for transferring manual service, electronic equipment and storage medium | |
| CN116386604A (en) | Self-adaptive outbound dialogue strategy configuration method and device based on user emotion state | |
| CN114038483A (en) | Speech quality detection method, device, equipment and medium based on emotion recognition | |
| CN108536811B (en) | Voice interaction path determining method and device based on machine learning, storage medium and terminal | |
| CN114372476A (en) | Semantic truncation detection method, device and equipment and computer readable storage medium | |
| CN110796364A (en) | Online classroom quality inspection method and device, electronic equipment and storage 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200512 |