CN116628163A - Customer service processing method, customer service processing device, customer service processing equipment and storage medium - Google Patents
Customer service processing method, customer service processing device, customer service processing equipment and storage medium Download PDFInfo
- Publication number
- CN116628163A CN116628163A CN202310605880.4A CN202310605880A CN116628163A CN 116628163 A CN116628163 A CN 116628163A CN 202310605880 A CN202310605880 A CN 202310605880A CN 116628163 A CN116628163 A CN 116628163A
- Authority
- CN
- China
- Prior art keywords
- model
- customer service
- data
- data set
- training
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 27
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012512 characterization method Methods 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000013136 deep learning model Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 63
- 230000003993 interaction Effects 0.000 claims description 24
- 230000011218 segmentation Effects 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000013461 design Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- 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
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application provides a customer service processing method, a customer service processing device, customer service processing equipment and a storage medium. Relates to the technical field of artificial intelligence. The method comprises the following steps: receiving problem data sent by a user terminal, wherein the problem data is generated in response to input operation of a user; extracting keywords in the problem data; carrying out intention analysis on each keyword to obtain intention information of the problem data; the intention information of the question data is used as target question data to be input into a pre-trained customer service model, so that the pre-trained customer service model obtains reply content corresponding to the target question information according to the target question information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model; and sending the reply content to the user side. The method solves the problems that the prior intelligent customer service of the bank has ambiguity or uncertainty for some complex or special problems in the prior art when answering the problems of the customers.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a customer service processing method, apparatus, device, and storage medium.
Background
In the financial system, the intelligent customer service system is a customer service mode realized by utilizing an artificial intelligence technology, and can help banks to automatically process a large number of customer service requests within 24 hours, so that the efficiency and quality of customer service are improved.
The conventional intelligent customer service system for financial repair generally inputs problems through websites, APP, public numbers and other channels, and intelligent customer service automatically judges customer intention and carries out corresponding solutions according to the problems presented by the customers.
However, the inventor finds that there is a fuzzy or uncertain situation in answering the customer's questions for some complex or special questions in the existing intelligent customer service of the bank.
Disclosure of Invention
The application provides a customer service processing method, device, equipment and storage medium, which are used for solving the problems that the existing intelligent customer service of a bank in the prior art has ambiguity or uncertainty for some complex or special problems and answers the problems of customers.
In a first aspect, the present application provides a customer service processing method, including: receiving problem data sent by a user side, wherein the problem data is generated in response to input operation of a user; extracting keywords in the problem data; carrying out intention analysis on each keyword to obtain intention information of the problem data; the intention information of the question data is used as target question data to be input into a pre-trained customer service model, so that the pre-trained customer service model obtains reply content corresponding to the target question information according to the target question information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model; and sending the reply content to the user side.
In one possible design, the performing intent analysis on each keyword to obtain intent information of the problem data includes: semantic labeling is carried out on each keyword; and aggregating the marked semantics to obtain the intention information of the problem data.
In one possible design, the training process of the pre-trained customer service model includes: acquiring an original customer service data set; preprocessing the original customer service data set to obtain a model training data set and a model testing data set; pre-training the language characterization model by adopting the model training data set to obtain a pre-training model; and fine tuning the pre-training model by adopting the model test data set to obtain the pre-trained customer service model.
In one possible design, the acquiring the original customer service data set includes: acquiring historical interaction data of a financial system, wherein the historical interaction data comprises call data, text data of communication software and image data; acquiring real-time interaction data of a financial system and a user; acquiring third party data of a third party data source; and summarizing the historical interaction data, the real-time interaction data and the third party data to obtain an original customer service data set.
In one possible design, the preprocessing the original customer service data set to obtain a model training data set and a model testing data set includes: performing word segmentation on the original customer service data set to obtain a word segmentation data set; converting the word segmentation data set into vector representation containing context semantic information through a GPT-4 pre-training language model to obtain a model data set; and classifying the model data set according to a preset duty ratio to obtain a model training data set and a model testing data set.
In one possible design, the model test data set includes a plurality of test data and labels corresponding to the test data; the fine tuning of the pre-training model by using the model test data set to obtain the pre-trained customer service model comprises the following steps: inputting each test data into the pre-training model to obtain a test result; according to the comparison result of the test result and the label corresponding to the test data, adjusting parameters of a pre-training model; and when the error of the comparison result of the test result and the label corresponding to the test data reaches a set value, taking the adjusted pre-training model as the pre-trained customer service model.
In a second aspect, the present application provides a customer service processing apparatus, including: the receiving module is used for receiving problem data sent by a user side, wherein the problem data is generated in response to input operation of a user; the extraction module is used for extracting keywords in the problem data; the analysis module is used for carrying out intention analysis on each keyword to obtain intention information of the problem data; the acquisition module is used for inputting intention information of the problem data as target problem data into a pre-trained customer service model so that the pre-trained customer service model acquires reply content corresponding to the target problem information according to the target problem information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model; and the sending module is used for sending the reply content to the user side.
In a third aspect, an embodiment of the present application provides an electronic device, including: at least one processor and memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, such that the at least one processor performs the customer service processing method as described above in the first aspect and the various possible designs of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where computer executable instructions are stored, and when executed by a processor, to implement the customer service processing method according to the first aspect and the various possible designs of the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product, comprising a computer program, which when executed by a processor, implements the customer service processing method according to the first aspect and the various possible designs of the first aspect.
According to the customer service processing method, device and equipment and the storage medium, the target questions are obtained by processing the question data sent by the user side, and the target questions are input into the pre-trained customer service model, so that the pre-trained customer service model obtains the reply content corresponding to the target question information according to the target question information, and sends the reply content to the user side, the questions of the user are replied through the customer service model, and more accurate semantic understanding and more accurate reply can be made to the questions provided by the user.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is an application scenario diagram of a customer service processing method provided by an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for handling customer service according to an embodiment of the present application;
FIG. 3 is a second flowchart of a customer service processing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a customer service processing device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
Interpretation of the terms
Artificial intelligence: artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence, research in this field including robotics, language recognition, image recognition, natural language processing, and expert systems.
Pre-training model: a pre-trained model is a model trained on large scale unlabeled data, intended to capture features of the underlying language, such as grammar, semantics, and context.
Intelligent customer service: intelligent customer service is a customer service mode realized by utilizing an artificial intelligence technology. It can help financial institution to automatically process a large number of customer service requests within 24 hours, and improve the efficiency and quality of customer service.
In the financial system, the intelligent customer service system is a customer service mode realized by utilizing an artificial intelligence technology, and can help a financial institution to automatically process a large number of customer service requests within 24 hours, so that the efficiency and quality of customer service are improved. The existing intelligent customer service system for financial repair generally inputs problems through websites, APP, public numbers and other channels, the intelligent customer service automatically judges the intention of the customer according to the problems presented by the customer and carries out corresponding solutions, the method can only match and extract answers related to the problems of the customer according to an inherent semantic model, and if the problems of the customer asking questions are not presented in the semantic model, the problems of the customer cannot be solved. For some complex or special questions, there is a fuzzy or uncertain situation when answering the questions of the clients, and the user experience is poor.
Aiming at the technical problems, the application provides the following technical conception: after processing the question data sent by the user side, inputting the question data into a pre-trained customer service model, and obtaining a response corresponding to the question of the user through the model, so that the problem that the existing intelligent customer service has ambiguity or uncertainty for some complex or special questions when answering the questions of the customer can be solved.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is an application scenario diagram of a customer service processing method provided by an embodiment of the present application. As shown in fig. 1, the application scenario includes: the client 101 and the server 102, the client 101 sends the question data to the server 102, the server 102 obtains the reply content corresponding to the question data sent by the client 101 through the pre-trained customer service model, and sends the reply content to the client 101. The communication between the client 101 and the server 102 may be performed through a communication network, optionally a wired network or a wireless network.
The user terminal 101 may be a personal computer, a mobile phone, a tablet computer, a notebook, an e-book reader, or other computer devices used by a user. The server 102 may be a physical server or a cloud server.
Based on the application scenario shown in fig. 1, the embodiment of the application further provides a customer service processing method. Fig. 2 is a flowchart of a customer service processing method according to an embodiment of the present application. The main execution body of the method of the present embodiment may be the server 102 shown in fig. 1. As shown in fig. 2, the customer service processing method includes:
s201, receiving problem data sent by a user side, wherein the problem data is generated in response to input operation of a user.
In this embodiment, a user inputs a question to a user terminal, and the user terminal generates question data according to the question input by the user. For example, the user inputs "please report the bank card for loss", the user side receives the voice or text input of the user, and generates corresponding problem data from the received problem "please report the bank card for loss".
S202, extracting keywords in the problem data.
In this embodiment, taking the problem data mentioned in the above step as an example, the keywords in "please report the bankcard" are extracted, so that the keywords "report the bankcard" and "report the bankcard" can be obtained.
S203, carrying out intention analysis on each keyword to obtain intention information of the problem data.
In this embodiment, semantic labeling is performed on each keyword; and aggregating the marked semantics to obtain the intention information of the problem data.
Specifically, taking each keyword in the steps as an example, semantic marking is performed on the keywords 'loss report' and 'bank card', and the intent information of the problem data can be obtained after the marked semantics are aggregated to be the loss report bank card.
S204, the intention information of the question data is used as target question data to be input into a pre-trained customer service model, so that the pre-trained customer service model obtains reply content corresponding to the target question information according to the target question information.
In this embodiment, the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model, and accurate reply content can be generated according to intention information of problem data through the model, for example, aiming at intention information of a loss reporting bank card, and reply content of 'good, i.e. about to report loss to the bank card' is output.
S205, the reply content is sent to the user side.
In this embodiment, after the pre-trained customer service model outputs the reply content, the server sends the reply content to the client, so that the client can obtain a timely and accurate reply.
In summary, the customer service processing method of the embodiment obtains the target problem by processing the problem data sent by the user side, inputs the target problem into the pre-trained customer service model, so that the pre-trained customer service model obtains the reply content corresponding to the target problem information according to the target problem information, and sends the reply content to the user side, thereby realizing reply to the problem of the user through the customer service model, and being capable of giving more accurate semantic understanding and more accurate reply to the problem presented by the user.
Fig. 3 is a flowchart of a customer service process according to an embodiment of the present application. In the embodiment of the present application, specific steps are provided for the training process of the pre-trained customer service model based on the embodiment provided in fig. 2. As shown in fig. 3, the customer service processing method includes the following steps:
s301, acquiring an original customer service data set.
In this embodiment, obtaining the original customer service data set includes: acquiring historical interaction data of a financial system, wherein the historical interaction data comprises call data, text data of communication software and image data; acquiring real-time interaction data of a financial system and a user; acquiring third party data of a third party data source; and summarizing the historical interaction data, the real-time interaction data and the third party data to obtain an original customer service data set.
Specifically, the collection of the raw customer service data set may include the following three aspects: collecting from historical data: and collecting historical interaction data of a financial system, wherein the historical interaction data comprise bank outbound call data, incoming voice call data, text communication and image data of communication software and the like. Through real-time interaction collection: relevant data is collected in real-time interactions with the customer. Collecting by a third party data source: data is collected from third party data sources such as social media, news websites, and the like.
S302, preprocessing an original customer service data set to obtain a model training data set and a model testing data set.
In this embodiment, the process of preprocessing the original customer service data set to obtain the model training data set and the model test data set may be implemented through steps S3021 to S3023:
s3021: the original customer service data set is subjected to word segmentation to obtain a word segmentation data set, specifically, a nub (Jieba) word segmentation tool can be used for word segmentation of the original customer service data set, the nub word segmentation tool is a Python Chinese word segmentation component, three word segmentation modes of an accurate mode, a full mode and a search engine mode are supported, simultaneously, complex word segmentation and a custom dictionary are supported, and more accurate word segmentation results can be obtained through the Jieba word segmentation. In this embodiment, other word segmentation tools may be used to segment the original customer service data set, which is not limited herein.
S3022: and converting the word segmentation data set into vector representation containing context semantic information through a GPT-4 pre-training language model to obtain a model data set. GPT-4 is a disclosed ultra-large-scale language preprocessing model, and a word segmentation data set after word segmentation processing is converted into vector representation containing context semantic information through the GPT-4 pre-training language model. The vector representation, i.e. the information contained in the model dataset, generated after pre-training the language model by GPT-4 is more accurate.
S3023: and classifying the model data set according to a preset duty ratio to obtain a model training data set and a model testing data set. Specifically, the preset duty ratio is set according to the actual situation, and the present embodiment is not particularly limited. The model data set can be divided into a model training data set and a model test data set, the model training is carried out by using the model training data set, and then the parameter adjustment is carried out by using the model test data set, so that the accuracy of a model result is improved.
S303, pre-training the language characterization model by using the model training data set to obtain a pre-training model.
In this embodiment, the training data set is used to perform pre-training of the language characterization model, that is, learn the rule of the training set, perform loop iteration training on the language characterization model, and output the trained pre-training model.
Specifically, the language characterization model may select a BERT model, which is an abbreviation of Bidirectional Encoder Representations from Transformer, which is mainly used for semantic understanding and natural language generation tasks, has excellent language understanding capability, can be trained with a large amount of nonstandard data, and supports various natural language processing tasks.
S304, fine tuning is carried out on the pre-training model by adopting a model test data set, and a pre-trained customer service model is obtained.
In this embodiment, the model test data set includes a plurality of test data and labels corresponding to the test data, and correspondingly, the process of fine tuning the pre-training model by using the model test data set to obtain the pre-trained customer service model includes the following steps:
s3041: and inputting each test data into the pre-training model to obtain a test result. Specifically, after the model is pre-trained, the test data in the model test data set is input into the pre-training model, and the pre-training model outputs a test result.
S3042: and adjusting parameters of the pre-training model according to the test result and the comparison result of the labels corresponding to the test data. Specifically, the comparison result of the test result and the label corresponding to the test data may be regarded as a calculated loss value of the pre-training model, and the parameter of the pre-training model is adjusted according to the loss value, so that the loss value may be minimized.
S3043: when the error of the comparison result of the label corresponding to the test result and the test data reaches a set value, the adjusted pre-training model is used as a pre-trained customer service model. Step S3042 adjusts the parameters of the pre-training model, and then the calculated loss value of the pre-training model is reduced, and when the loss value is reduced to the error of the comparison result of the test result and the label corresponding to the test data reaches the set value, the pre-training model can be considered to have reduced the loss value to the greatest extent, and the adjusted pre-training model can be used as the pre-trained customer service model. Specifically, the setting value is set according to the specific situation, and the present embodiment is not particularly limited.
In summary, the customer service processing method of the embodiment processes the obtained original customer service data set, trains and fine-tunes the language characterization model according to the processed model training data set and model testing data set to obtain a pre-trained customer service model, so as to realize the establishment of the customer service model, and the model can be used for more accurately replying the problem raised by the user, thereby improving the efficiency and quality of the customer service.
Fig. 4 is a schematic structural diagram of a customer service processing device according to an embodiment of the present application. As shown in fig. 4, the customer service processing apparatus 40 includes: a receiving module 401, an extracting module 402, a parsing module 403, an obtaining module 404 and a sending module 405.
The receiving module 401 is configured to receive issue data sent by a user, where the issue data is generated in response to an input operation of the user.
An extracting module 402, configured to extract keywords in the question data.
The parsing module 403 is configured to parse the intent of each keyword to obtain intent information of the question data.
The obtaining module 404 is configured to input intention information of the question data as target question data into a pre-trained customer service model, so that the pre-trained customer service model obtains reply content corresponding to the target question information according to the target question information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model.
And the sending module 405 is configured to send the reply content to the user terminal.
In some embodiments, the parsing module 403 is specifically configured to perform semantic labeling on each keyword; and aggregating the marked semantics to obtain the intention information of the problem data.
In some embodiments, the customer service processing apparatus further comprises: a training module 406, configured to obtain an original customer service data set; preprocessing an original customer service data set to obtain a model training data set and a model testing data set; pre-training the language characterization model by using a model training data set to obtain a pre-training model; and fine tuning the pre-training model by adopting a model test data set to obtain a pre-trained customer service model.
In some embodiments, the training module 406 is further configured to obtain historical interaction data of the financial system, where the historical interaction data includes call data, text data of the communication software, and image data; acquiring real-time interaction data of a financial system and a user; acquiring third party data of a third party data source; and summarizing the historical interaction data, the real-time interaction data and the third party data to obtain an original customer service data set.
In some embodiments, the training module 406 is further configured to perform word segmentation on the original customer service data set to obtain a word segmentation data set; converting the word segmentation data set into vector representation containing context semantic information through a GPT-4 pre-training language model to obtain a model data set; and classifying the model data set according to a preset duty ratio to obtain a model training data set and a model testing data set.
In some embodiments, the model test data set includes a plurality of labels corresponding to the test data, and accordingly, the training module 406 is further configured to input each test data into the pre-training model to obtain a test result; according to the test result and the comparison result of the label corresponding to the test data, adjusting the parameters of the pre-training model; when the error of the comparison result of the label corresponding to the test result and the test data reaches a set value, the adjusted pre-training model is used as a pre-trained customer service model.
The customer service processing device provided by the embodiment of the application can be used for executing the technical scheme of the customer service processing method in the embodiment, and the implementation principle and the technical effect are similar, and are not repeated here.
It should be noted that, it should be understood that the division of the modules of the above apparatus is merely a division of a logic function, and may be fully or partially integrated into a physical entity or may be physically separated. And these modules may all be implemented in software in the form of calls by the processing element; or can be realized in hardware; the method can also be realized in a form of calling software by a processing element, and the method can be realized in a form of hardware by a part of modules. For example, the extraction module 402 may be a processing element that is set up separately, may be implemented in a chip of the above apparatus, or may be stored in a memory of the above apparatus in the form of program codes, and may be called by a processing element of the above apparatus to execute the functions of the above extraction module 402. The implementation of the other modules is similar. In addition, all or part of the modules can be integrated together or can be independently implemented. The processing element here may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 5, the electronic device 50 may include: a transceiver 501, a processor 502, and a memory 503.
Processor 502 executes computer-executable instructions stored in memory, causing processor 502 to perform the aspects of the embodiments described above. The processor 502 may be a general purpose processor including a central processing unit CPU, a network processor (network processor, NP), etc.; but may also be a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.
The memory 503 is coupled to the processor 502 via a system bus and communicates with each other, the memory 503 being adapted to store computer program instructions.
The transceiver 501 may be used to obtain a task to be run and configuration information of the task to be run.
The system bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The system bus may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The transceiver is used to enable communication between the database access device and other computers (e.g., clients, read-write libraries, and read-only libraries). The memory may include random access memory (random access memory, RAM) and may also include non-volatile memory (non-volatile memory).
The electronic device provided by the embodiment of the application can be the terminal device of the embodiment.
The embodiment of the application also provides a chip for running the instruction, which is used for executing the technical scheme of the customer service processing method in the embodiment.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores computer instructions, and when the computer instructions run on a computer, the computer is caused to execute the technical scheme of the customer service processing method in the embodiment.
The embodiment of the application also provides a computer program product, which comprises a computer program stored in a computer readable storage medium, wherein at least one processor can read the computer program from the computer readable storage medium, and the technical scheme of the customer service processing method in the embodiment can be realized when the at least one processor executes the computer program.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.
In addition, each functional module in the embodiments of the present application may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit. The units formed by the modules can be realized in a form of hardware or a form of hardware and software functional units.
The integrated modules, which are implemented in the form of software functional modules, may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or processor to perform some of the steps of the methods of the various embodiments of the application.
It should be understood that the above processor may be a central processing unit (Central Processing Unit, abbreviated as CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, abbreviated as DSP), application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile memory NVM, such as at least one magnetic disk memory, and may also be a U-disk, a removable hard disk, a read-only memory, a magnetic disk or optical disk, etc.
The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
The storage medium may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). Of course, the processor and the storage medium may reside as discrete components in an electronic control unit or master control device.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application.
Claims (10)
1. A customer service processing method, comprising:
receiving problem data sent by a user side, wherein the problem data is generated in response to input operation of a user;
extracting keywords in the problem data;
carrying out intention analysis on each keyword to obtain intention information of the problem data;
the intention information of the question data is used as target question data to be input into a pre-trained customer service model, so that the pre-trained customer service model obtains reply content corresponding to the target question information according to the target question information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model;
and sending the reply content to the user side.
2. The method of claim 1, wherein the performing intent analysis on each keyword to obtain intent information of the question data includes:
semantic labeling is carried out on each keyword;
and aggregating the marked semantics to obtain the intention information of the problem data.
3. The method of claim 1, wherein the training process of the pre-trained customer service model comprises:
acquiring an original customer service data set;
preprocessing the original customer service data set to obtain a model training data set and a model testing data set;
pre-training the language characterization model by adopting the model training data set to obtain a pre-training model;
and fine tuning the pre-training model by adopting the model test data set to obtain the pre-trained customer service model.
4. A method according to claim 3, wherein said obtaining an original customer service data set comprises:
acquiring historical interaction data of a financial system, wherein the historical interaction data comprises call data, text data of communication software and image data;
acquiring real-time interaction data of a financial system and a user;
acquiring third party data of a third party data source;
and summarizing the historical interaction data, the real-time interaction data and the third party data to obtain an original customer service data set.
5. A method according to claim 3, wherein said preprocessing said original customer service data set to obtain a model training data set and a model test data set comprises:
performing word segmentation on the original customer service data set to obtain a word segmentation data set;
converting the word segmentation data set into vector representation containing context semantic information through a GPT-4 pre-training language model to obtain a model data set;
and classifying the model data set according to a preset duty ratio to obtain a model training data set and a model testing data set.
6. The method of any one of claims 3 to 5, wherein the model test dataset comprises a plurality of test data and labels corresponding to the test data;
correspondingly, the fine tuning of the pre-training model by using the model test data set to obtain the pre-trained customer service model comprises the following steps:
inputting each test data into the pre-training model to obtain a test result;
according to the comparison result of the test result and the label corresponding to the test data, adjusting parameters of a pre-training model;
and when the error of the comparison result of the test result and the label corresponding to the test data reaches a set value, taking the adjusted pre-training model as the pre-trained customer service model.
7. A customer service processing apparatus, comprising:
the receiving module is used for receiving problem data sent by a user side, wherein the problem data is generated in response to input operation of a user;
the extraction module is used for extracting keywords in the problem data;
the analysis module is used for carrying out intention analysis on each keyword to obtain intention information of the problem data;
the acquisition module is used for inputting intention information of the problem data as target problem data into a pre-trained customer service model so that the pre-trained customer service model acquires reply content corresponding to the target problem information according to the target problem information; the pre-trained customer service model is a deep learning model obtained by pre-training a language characterization model;
and the sending module is used for sending the reply content to the user side.
8. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-6.
9. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310605880.4A CN116628163A (en) | 2023-05-25 | 2023-05-25 | Customer service processing method, customer service processing device, customer service processing equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310605880.4A CN116628163A (en) | 2023-05-25 | 2023-05-25 | Customer service processing method, customer service processing device, customer service processing equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116628163A true CN116628163A (en) | 2023-08-22 |
Family
ID=87636242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310605880.4A Pending CN116628163A (en) | 2023-05-25 | 2023-05-25 | Customer service processing method, customer service processing device, customer service processing equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116628163A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391515A (en) * | 2023-10-24 | 2024-01-12 | 科讯嘉联信息技术有限公司 | Service quality management method and system based on general large language model |
| CN117875908A (en) * | 2024-03-08 | 2024-04-12 | 蒲惠智造科技股份有限公司 | Work order processing method and system based on enterprise management software SAAS |
-
2023
- 2023-05-25 CN CN202310605880.4A patent/CN116628163A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117391515A (en) * | 2023-10-24 | 2024-01-12 | 科讯嘉联信息技术有限公司 | Service quality management method and system based on general large language model |
| CN117875908A (en) * | 2024-03-08 | 2024-04-12 | 蒲惠智造科技股份有限公司 | Work order processing method and system based on enterprise management software SAAS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663409B2 (en) | Systems and methods for training machine learning models using active learning | |
| US20210232761A1 (en) | Methods and systems for improving machine learning performance | |
| US11216510B2 (en) | Processing an incomplete message with a neural network to generate suggested messages | |
| US20190180196A1 (en) | Systems and methods for generating and updating machine hybrid deep learning models | |
| CN109514586B (en) | Method and system for realizing intelligent customer service robot | |
| WO2019113122A1 (en) | Systems and methods for improved machine learning for conversations | |
| CN116628163A (en) | Customer service processing method, customer service processing device, customer service processing equipment and storage medium | |
| US10965812B1 (en) | Analysis and classification of unstructured computer text for generation of a recommended conversation topic flow | |
| US11531987B2 (en) | User profiling based on transaction data associated with a user | |
| CN112559865B (en) | Information processing system, computer-readable storage medium, and electronic device | |
| CN112417158A (en) | Training method, classification method, device and equipment of text data classification model | |
| US11238050B2 (en) | Method and apparatus for determining response for user input data, and medium | |
| CN113360699A (en) | Model training method and device, image question answering method and device | |
| CN111325156A (en) | Face recognition method, device, equipment and storage medium | |
| CN110890088A (en) | Voice information feedback method and device, computer equipment and storage medium | |
| CN114218945A (en) | Entity identification method, device, server and storage medium | |
| CN110738056B (en) | Method and device for generating information | |
| CN116860921A (en) | Dialog pre-labeling method, system, computer device and storage medium | |
| CN114417045A (en) | Insurance case spot inspection method, system, equipment and storage medium based on neural network | |
| US20210312223A1 (en) | Automated determination of textual overlap between classes for machine learning | |
| CN113033912A (en) | Problem solving person recommendation method and device | |
| CN110232328A (en) | A kind of reference report analytic method, device and computer readable storage medium | |
| CN116911313B (en) | Semantic drift text recognition method and device | |
| CN116933800B (en) | Template-based generation type intention recognition method and device | |
| CN112906370B (en) | Intention recognition model training method, intention recognition method and related device |
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 |