Intelligent operation method, device and equipment for bank self-service counter and medium
By using the target question-and-answer model in bank self-service equipment, the problem of difficulty in operating on bank self-service equipment is solved, and the provision of fast and accurate operational guidance is achieved, which reduces business processing time and improves customer experience.
Patent Information
- Application Number
- CN202411491060.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-02-07
AI Technical Summary
When customers use bank self-service equipment, due to the complex banking business, they need multiple verifications and guidance, which increases the business time of bank employees and customers, affecting the customer experience.
By obtaining bank transaction process data and equipment operation processes in the knowledge base, adding data indexes, and using pre-trained models for training, we obtain the target question and answer model. Receive user voice questions, use voice recognition technology to convert them into text questions, and enter the target question and answer model to obtain operational guidance.
It achieves rapid and accurate operational guidance for customers, reduces business time for bank employees and customers, and improves customer experience.
Smart Images
Figure CN119396974A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a bank self-service counter intelligent operation method, device, equipment and medium. Background Art
[0002] In order to facilitate customers to handle business, each bank branch will have independent equipment for customers to operate, so as to facilitate customers to handle business and save users' time. However, when customers use the self-service equipment of bank branches, because banking business is usually more complicated, it requires multiple verifications and supervision to protect customer safety. Customers are unfamiliar with it and often need bank staff to guide them. However, due to the supervision of protecting customer information security and fund security, bank staff cannot always guide customers, which increases the time for bank staff and customers to handle business. Therefore, there is an urgent need for an automated and intelligent auxiliary customer to operate self-service equipment, reduce the time for bank staff and customers to handle business, so as to improve customer experience. Summary of the invention
[0003] The present invention provides an artificial intelligence bank self-service counter intelligent operation method, device, computer equipment and medium to solve the technical problems of inaccurate matching of semantic matching models, serious lack of matching ability, and subsequent poor question-answering effects.
[0004] In a first aspect, an artificial intelligence-based intelligent operation method for a bank self-service counter is provided, comprising: Obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; Using the bank transaction process data, the device operation process and the data index, the pre-trained model is trained to obtain a target question-answering model; Receive user operation voice questions, and convert the user operation voice questions into text questions using speech recognition technology; The text question is input into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice.
[0005] In a second aspect, a bank self-service counter intelligent operation device is provided, comprising: An indexing module is used to obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; A model training module, used to train a pre-trained model using the bank transaction process data, the device operation process and the data index to obtain a target question-answering model; A question receiving module, used for receiving a user's voice question and converting the user's voice question into a text question using speech recognition technology; The answer output module is used to input the text question into the target question-answering model so that the target question-answering model outputs the operation instructions corresponding to the user's operation voice question through voice.
[0006] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned bank self-service counter intelligent operation method when executing the computer program.
[0007] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned bank self-service counter intelligent operation method are implemented.
[0008] In the scheme implemented by the above-mentioned bank self-service counter intelligent operation method, device, computer equipment and storage medium, by acquiring the bank transaction process data and the equipment operation process in the knowledge base, a data index is added to the bank transaction process data and the equipment operation process; the pre-trained model is trained using the bank transaction process data, the equipment operation process and the data index to obtain a target question and answer model; user operation voice questions are received, and the user operation voice questions are converted into text questions using speech recognition technology; the text questions are input into the target question and answer model so that the target question and answer model outputs the operation instructions corresponding to the user operation voice questions through voice. In the present invention, in order to solve the problem of customers using self-service devices to handle business in a bank, firstly, data indexes are added to the bank transaction process data and the device operation process by acquiring data bank transaction process data and the device operation process in the knowledge base to obtain the data index, and the pre-trained model is trained by the bank transaction process data, the device operation process and the data index to obtain a target question-answering model, and the target question-answering model is used to find customer voice operation problems and output operation instructions through voice, so that customer questions can be answered quickly, which effectively solves the problem that bank employees cannot be there to guide customers at all times, and also effectively reduces the problem of customer business handling time, thereby improving customer experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0010] Figure 1 This is a schematic diagram of an application environment of a bank self-service counter intelligent operation method according to an embodiment of the present invention; Figure 2 It is a flow chart of a bank self-service counter intelligent operation method according to an embodiment of the present invention; Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S10; Figure 4 yes Figure 1 A schematic flow chart of a specific implementation of step S30; Figure 5 yes Figure 4 A schematic flow chart of a specific implementation of step S40; Figure 6 It is a structural schematic diagram of an intelligent operation device for a bank self-service counter in one embodiment of the present invention; Figure 7 is a schematic diagram of a structure of a computer device in one embodiment of the present invention; Figure 8 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION
[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0012] The bank self-service counter intelligent operation method based on artificial intelligence provided by the embodiment of the present invention can be applied in Figure 1In the application environment, the client communicates with the server through the network. The server can obtain the bank transaction process data and the device operation process in the knowledge base, add data indexes to the bank transaction process data and the device operation process; use the bank transaction process data, the device operation process and the data index to train the pre-trained model to obtain the target question-answering model; receive the user operation voice question, and use the voice recognition technology to convert the user operation voice question into a text question; input the text question into the target question-answering model, so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice. In the present invention, for the problem that customers use self-service equipment to handle business in the bank, first, by obtaining the data bank transaction process data and the device operation process in the knowledge base, add data indexes to the bank transaction process data and the device operation process to obtain the data index, and train the pre-trained model through the bank transaction process data, the device operation process and the data index to obtain the target question-answering model, use the target question-answering model to find the customer's voice operation problem and output the operation guidance through voice, so that the customer's question can be quickly answered, effectively solving the problem that bank staff cannot be at the customer's side to guide at any time, and at the same time effectively reducing the problem of the customer's business handling time, and improving the customer experience. The client can be, but is not limited to, various personal computers, laptops, smart phones, and tablet devices. The server can be implemented with an independent server or a server cluster consisting of multiple servers.
[0013] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0014] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0015] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.
[0016] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0017] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0018] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0019] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.
[0020] In one embodiment, see Figure 2 As shown, Figure 2 A flow chart of an intelligent operation method of a bank self-service counter based on artificial intelligence provided by an embodiment of the present invention includes the following steps: S10: Obtain the bank transaction process data and the device operation process in the knowledge base, and add data indexes to the bank transaction process data and the device operation process.
[0021] The bank self-service counter intelligent operation method provided by the present invention can be applied to the use of self-service counters in various application scenarios. The self-service counter obtains the bank transaction process data and the equipment operation process data in the knowledge base, and uses the bank transaction process data and the equipment operation process to add data indexes to the bank transaction process data and the equipment operation process to obtain the data index, wherein the bank transaction process data includes: obtaining the user's personal identity information, verifying the identity information, obtaining the user's business transaction type, providing the user with business handling credentials and other processes to ensure the safety, accuracy and efficiency of the user's transactions. The equipment operation process refers to the operations that the autonomous device needs to perform for each step of different bank transaction processes.
[0022] S20: Using the bank transaction process data, the device operation process and the data index, training the pre-trained model to obtain a target question-answering model; Specifically, to obtain the bank transaction process data and device operation process in the knowledge base, for example, for user transfer, it is necessary to obtain the transaction data required by the bank for the bank transfer operation and the specific process of self-service device operation. In addition to transfer, the business handled by the bank also includes account inquiry, account management, transfer and remittance, credit, investment and financial management, etc. The transaction data and device operation process required for different business types are different. Therefore, it is necessary to classify the bank transaction process data according to different business types to obtain the transaction data corresponding to different transaction types of the bank, and classify the device operation process according to different business types to obtain the device operation process corresponding to different transaction types of the bank, and then train the pre-trained model according to the classified transaction data and the classified device operation process to obtain the target question-answering model.
[0023] It is worth noting that the target question-answering model uses the chat-gpt3.5 model released by OpenAI as the basic model, and uses the bank transaction process data and device operation process in the knowledge base to train the pre-trained model to obtain the target question-answering model.
[0024] S30: receiving a user's voice question, and converting the user's voice question into a text question using speech recognition technology; Specifically, when a user uses a self-service counter to handle business and encounters unclear questions, he or she can click on the voice assistant on the self-service counter. The voice assistant will obtain the user's voice questions and convert them into text questions through voice recognition technology so that the text questions can be input into the target question-answering model.
[0025] S40: Input the text question into the target question-answering model, so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice.
[0026] Specifically, after the self-service counter converts the voice question into a text question, the converted text question will be input into the target question-answering model, which will perform feature extraction on the input question and output the operation instructions corresponding to the user's voice question using voice.
[0027] In this embodiment, data indexes are added to the bank transaction process data and the device operation process by acquiring data bank transaction process data and device operation process in the knowledge base to obtain data indexes, and the pre-trained model is trained through the bank transaction process data, the device operation process and the data index to obtain a target question-answering model. The target question-answering model is used to find customer voice operation problems and output operation instructions through voice, so that customer questions can be answered quickly, effectively solving the problem that bank employees cannot be there to guide customers at all times, and also effectively reducing the time it takes for customers to handle business, thereby improving customer experience.
[0028] In one embodiment, if Figure 3 As shown, in step S10, that is, adding data indexes to the bank transaction process data and the device operation process, the following steps are included: S11: Classify the bank transaction process data to obtain transaction process data corresponding to different bank transaction types.
[0029] S12: Classify the device operation process to obtain device operation processes corresponding to different bank transaction types.
[0030] S13: Add the same classification index to the classified transaction process data and device operation processes of the same type.
[0031] Specifically, in steps S11-S13, in order to use the data in the knowledge base to better train the pre-trained model, it is necessary to first classify the bank transaction process and the equipment operation process to obtain the equipment operation process corresponding to different transaction types, and add the same classification index to the transaction process data and equipment operation process of the same type after classification, so as to conduct more standardized training on the target question and answer model in the future and improve the accuracy of the target question and answer model.
[0032] In this embodiment, the bank transaction process data is classified to obtain bank transaction process data corresponding to different bank transaction types, and the device operation process is classified to obtain device operation processes corresponding to different bank transaction types. The same classification index is added to the transaction process data and device operation processes of the same type after classification. By adding data indexes to the bank transaction process data and the device operation process, it is convenient to train the target question and answer model bank transaction process data and the device operation process.
[0033] In one embodiment, if Figure 4 As shown, in step S30, that is, using speech recognition technology to convert the user's voice question into a text question, the following steps are also included: S31: Convert the user operation voice question into voice data.
[0034] S32: Determine whether the input is completed based on the duration of the silent state after the voice data becomes silent.
[0035] S33: After determining that the user operation voice question input has been completed, convert the user voice question into the text question.
[0036] Specifically, in order to obtain text questions, it is necessary to first convert the user's voice questions into voice data, and then convert the voice data into text questions through the Whisper model, that is, use the Whisper model to convert the user's voice questions into text questions, and at the same time determine whether the user has completed the input of the voice questions. Therefore, it is necessary to monitor the voice data. If the voice data is monitored to have no changes within a certain period of time, it is determined that the user's voice questions have been completely input into the self-service counter. At this time, the Whisper model will input the text questions converted from the user's voice questions into the target question-answering model.
[0037] Before the Whisper model converts the user's voice questions, it needs to convert the user's voice questions into voice data, divide the captured long audio data into 30-second segments, extract features from each collected audio segment, convert it into a log-Mel spectrogram through Fourier transform (FFT) and Mel filter group, and then pass it into the Whisper model. When the Whisper model recognizes that someone is speaking, it will start working, use the language recognition model to transcribe, and convert the voice questions into text questions. When it is determined that the user's voice data state becomes silent, the voice data will be converted into a text question.
[0038] In this embodiment, the user operation voice question is converted into voice data, and whether the input is completed is determined based on the duration of the silent state after the voice data becomes silent. After determining that the input of the user operation voice question is completed, the user voice question is converted into the text question, so that the user operation voice question can be input into the target question-answering model, and the operation instructions corresponding to the user operation voice question can be answered according to the text features, thereby reducing the risk of information leakage by customers through manual guidance.
[0039] In one embodiment, if Figure 5 As shown, in step S40, the text question is input into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice, which specifically includes the following steps: S41: using speech recognition technology to obtain the text question, and inputting the text question into the target question answering model so that the target question answering model extracts the text question features, and determines the text question type according to the text question features; S42: The target question-answering model obtains the operation instructions corresponding to the text question based on the determined text question type, and outputs the operation instructions using voice.
[0040] Specifically, after the text question is input into the target question-answering model, the target question-answering model needs to extract the features of the text question and determine the type of the text question based on the features of the text question. Then, the target question-answering model obtains the operation instructions corresponding to the text question based on the determined type of the text question and outputs the operation instructions using voice. For example, the text question is: How to manage an account? After receiving the text question, the target question-answering model will extract that the feature of the text question is "account management". Then, based on the extracted text question feature of "account management", the operation instructions for "account management" will be output by voice.
[0041] Optionally, in one embodiment, to obtain the operation instructions corresponding to the text question, it is necessary to sort the operation instructions obtained by the target question-answering model according to the text question features according to the matching degree, and output the operation instructions ranked first in matching degree.
[0042] Specifically, when obtaining the operation instructions corresponding to the text question, multiple operation instructions may be found based on the text feature target question and answer model. At this time, it is necessary to generate a matching degree for the multiple operation instructions corresponding to the obtained text question based on the extracted text features, and output the operation instructions ranked first in matching degree through voice.
[0043] In this embodiment, the text question is obtained by using speech recognition technology, and the text question is input into the target question and answer model so that the target question and answer model determines the type of the text question and extracts text question features according to the type of the text question. The target question and answer model obtains the operation instructions corresponding to the text question based on the extracted text question features, and outputs the operation instructions using speech. To obtain the operation instructions corresponding to the text question, the operation instructions obtained by the target question and answer model based on the text question features need to be sorted according to the degree of match, and the operation instructions ranked first in the degree of match are output. This embodiment outputs the operation instructions by speech using the question and answer model, thereby reducing the labor cost of manually guiding customer operations and the risk of violations in operating on behalf of customers.
[0044] In one embodiment, in step S40, the target question-answering model outputs the operation guidance corresponding to the user's operation voice question through voice, which specifically includes the following steps: S43: Obtain the user's age and region based on the user's identity information and the received voice of the user, and determine the target language; S44: Outputting the operation instructions corresponding to the text question using speech synthesis technology and the pre-determined target language.
[0045] Specifically, under normal circumstances, each business handled by a bank requires an ID card, and each self-service counter is located within a bank branch, which has a certain location. Therefore, the location of the self-service counter and the user's ID card are used to obtain the user's region, age and other information, and the target language output to the user is comprehensively determined. The operation instructions corresponding to the text question are output using speech synthesis technology and the pre-determined target language.
[0046] In this embodiment, the user's age and region are obtained based on the user's identity information and the received user's voice, and the target language is determined. The operation guidance corresponding to the text question is output using speech synthesis technology and the pre-determined target language. This embodiment obtains the user's personal identity and the user's region, and intelligently selects the language when outputting the operation guidance, thereby improving customer affinity and customer experience.
[0047] In one embodiment, after step S40, the bank self-service counter intelligent operation method, after obtaining the target question-answering model, further includes the following steps: S401: Continuously collect problems that occur during user use and solutions to the problems; S402: Classify the collected problems and solutions to the problems; S403: Upload the classified questions and corresponding solutions to the knowledge base so as to continuously train the target question-answering model.
[0048] Specifically, the target question-answering model continuously collects problems generated during user use and solutions to the problems, classifies the collected problems and solutions to the problems, and uploads the classified problems and corresponding solutions to the knowledge base, so as to continuously train the target question-answering model.
[0049] In this embodiment, by continuously collecting problems generated during user use and solutions to the problems, the collected problems and solutions to the problems are classified, and the classified problems and corresponding solutions are uploaded to the knowledge base, so as to continuously train the target question and answer model and improve the target question and answer model's answers to user voice operation questions.
[0050] In the scheme implemented by the above-mentioned bank self-service counter intelligent operation method, device, computer equipment and storage medium, by acquiring the bank transaction process data and the equipment operation process in the knowledge base, a data index is added to the bank transaction process data and the equipment operation process; the pre-trained model is trained using the bank transaction process data, the equipment operation process and the data index to obtain a target question and answer model; user operation voice questions are received, and the user operation voice questions are converted into text questions using speech recognition technology; the text questions are input into the target question and answer model so that the target question and answer model outputs the operation instructions corresponding to the user operation voice questions through voice. In the present invention, in order to solve the problem of customers using self-service devices to handle business in a bank, firstly, data indexes are added to the bank transaction process data and the device operation process by acquiring data bank transaction process data and the device operation process in the knowledge base to obtain the data index, and the pre-trained model is trained by the bank transaction process data, the device operation process and the data index to obtain a target question-answering model, and the target question-answering model is used to find customer voice operation problems and output operation instructions through voice, so that customer questions can be answered quickly, which effectively solves the problem that bank employees cannot be there to guide customers at all times, and also effectively reduces the problem of customer business handling time, thereby improving customer experience.
[0051] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0052] In one embodiment, a bank self-service counter intelligent operation device is provided, and the bank self-service counter intelligent operation device corresponds to the bank self-service counter intelligent operation method based on artificial intelligence in the above embodiment. Figure 6 As shown, the bank self-service counter intelligent operation device includes: an index building module 101, a model training module 102, a question receiving module 103 and an answer output module 104. The detailed description of each functional module is as follows: An indexing module is used to obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; A model training module, used to train a pre-trained model using the bank transaction process data, the device operation process and the data index to obtain a target question-answering model; A question receiving module, used for receiving a user's voice question and converting the user's voice question into a text question using speech recognition technology; The answer output module is used to input the text question into the target question-answering model so that the target question-answering model outputs the operation instructions corresponding to the user's operation voice question through voice.
[0053] In one embodiment, the index building module 101 is specifically used for: Classifying the bank transaction process data to obtain transaction process data corresponding to different bank transaction types; Classifying the device operation process to obtain device operation processes corresponding to different types of bank transactions; Add the same classification index to the bank transaction process data and equipment operation processes of the same type after classification.
[0054] In one embodiment, the question receiving module 103 is further configured to: Converting the user's voice operation question into voice data; Converting the voice data into a text question in real time through a voice model, and determining whether the user operation voice question has been input based on the duration of the silent state after the voice data becomes silent; After determining that the user operation voice question input has been completed, the user voice question is converted into the text question.
[0055] In one embodiment, the answer output module 104 is specifically configured to: Acquire the text question using speech recognition technology, and input the text question into the target question-answering model so that the target question-answering model extracts features of the text question and determines the type of the text question based on the text question; The target question-answering model obtains the operation instructions corresponding to the text question based on the extracted text question features, and outputs the operation instructions using voice.
[0056] In one embodiment, the answer output module 104 is specifically configured to: The operation instructions obtained by the target question-answering model according to the text question features are sorted according to the matching degree, and the operation instructions with the highest matching degree are output.
[0057] In one embodiment, the answer output module 104 is specifically configured to: According to the user's identity information and the received voice of the user, the user's age and region are obtained, and the target language is determined; The operation instructions corresponding to the text question are outputted in the pre-determined target language using speech synthesis technology.
[0058] The present invention provides an intelligent operation device for a bank self-service counter, which adds data indexes to the bank transaction process data and the device operation process by acquiring bank transaction process data and device operation process in a knowledge base; trains a pre-trained model using the bank transaction process data, the device operation process and the data index to obtain a target question-answering model; receives user operation voice questions, and converts the user operation voice questions into text questions using voice recognition technology; inputs the text questions into the target question-answering model, so that the target question-answering model outputs operation instructions corresponding to the user operation voice questions through voice. In the present invention, in view of the problem that customers use self-service equipment to handle business in a bank, firstly, data indexes are added to the bank transaction process data and the device operation process by acquiring data bank transaction process data and device operation process in a knowledge base to obtain data indexes, and trains the pre-trained model using the bank transaction process data, the device operation process and the data index to obtain a target question-answering model, uses the target question-answering model to find customer voice operation problems and outputs operation instructions through voice, so that customer problems can be quickly answered, effectively solving the problem that bank staff cannot be by the customer's side to guide at any time, and also effectively reducing the problem of customer handling business time, improving customer experience.
[0059] For the specific definition of the bank self-service counter intelligent operation device, please refer to the definition of the intelligent question-answering method above, which will not be repeated here. Each module in the above-mentioned bank self-service counter intelligent operation device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
[0060] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of a service-side method of intelligent operation of a bank self-service counter based on artificial intelligence.
[0061] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a bank self-service counter intelligent operation method based on artificial intelligence In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; Using the bank transaction process data, the device operation process and the data index, the pre-trained model is trained to obtain a target question-answering model; Receive user operation voice questions, and convert the user operation voice questions into text questions using speech recognition technology; The text question is input into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice.
[0062] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; Using the bank transaction process data, the device operation process and the data index, the pre-trained model is trained to obtain a target question-answering model; Receive user operation voice questions, and convert the user operation voice questions into text questions using speech recognition technology; The text question is input into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice.
[0063] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.
[0064] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0065] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0066] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A bank self-service counter intelligent operation method, characterized in that: include: Obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; Using the bank transaction process data, the device operation process and the data index, the pre-trained model is trained to obtain a target question-answering model; Receive user operation voice questions, and convert the user operation voice questions into text questions using speech recognition technology; The text question is input into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice.
2. The bank self-service counter intelligent operation method according to claim 1, characterized in that: Add data indexes to bank transaction process data and device operation processes, including: Classifying the bank transaction process data to obtain transaction process data corresponding to different bank transaction types; Classifying the device operation process to obtain device operation processes corresponding to different types of bank transactions; Add the same classification index to the bank transaction process data and equipment operation processes of the same type after classification.
3. The bank self-service counter intelligent operation method according to claim 1, characterized in that: Receiving a user's voice question, and converting the user's voice question into a text question using speech recognition technology, including: Converting the user's voice operation question into voice data; determining whether the input is completed based on the duration of the silent state after the voice data becomes silent; After determining that the user operation voice question input has been completed, the user voice question is converted into the text question.
4. The bank self-service counter intelligent operation method according to claim 1, characterized in that: Inputting the text question into the target question-answering model so that the target question-answering model outputs the operation guidance corresponding to the user operation voice question through voice, including: Acquire the text question using speech recognition technology, and input the text question into the target question-answering model so that the target question-answering model extracts features of the text question and determines the type of the text question based on the text question; The target question-answering model obtains the operation instructions corresponding to the text question based on the determined text question type, and outputs the operation instructions using voice.
5. The bank self-service counter intelligent operation method according to claim 4, characterized in that: Obtaining the operation instructions corresponding to the text question, including: The operation instructions obtained by the target question-answering model according to the text question features are sorted according to the matching degree, and the operation instructions with the highest matching degree are output.
6. The bank self-service counter intelligent operation method according to claim 1, characterized in that: The target question-answering model outputs the operation instructions corresponding to the user's operation voice question through voice, including: According to the user's identity information and the received voice of the user, the user's age and region are obtained, and the target language is determined; The operation instructions corresponding to the text question are outputted in the pre-determined target language using speech synthesis technology.
7. The bank self-service counter intelligent operation method according to claim 1, characterized in that: Get the target question answering model, then include: Continuously collect problems and solutions that users encounter during use; Categorize the collected problems and solutions to the problems; The classified questions and corresponding solutions are uploaded to the knowledge base to continuously train the target question-answering model.
8. An intelligent operation device for a bank self-service counter, characterized in that: include: An indexing module is used to obtain the bank transaction process data and the equipment operation process in the knowledge base, and add data indexes to the bank transaction process data and the equipment operation process; A model training module, used to train a pre-trained model using the bank transaction process data, the device operation process and the data index to obtain a target question-answering model; A question receiving module, used for receiving a user's voice question and converting the user's voice question into a text question using speech recognition technology; The answer output module is used to input the text question into the target question-answering model so that the target question-answering model outputs the operation instructions corresponding to the user's operation voice question through voice.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the bank self-service counter intelligent operation method as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the bank self-service counter intelligent operation method as described in any one of claims 1 to 7 are implemented.