Transaction Data Processing Method, Apparatus, Electronic Device, and Storage Medium

Abstract

The present invention discloses a transaction data processing method, apparatus, electronic device, and storage medium, relating to the technical field of data processing. Among them, the method includes: obtaining voice control information of a transaction object, where the voice control information is used to initiate a transaction instruction; processing the voice control information into key business data and voice segment data; processing the key business data using a voice data processing model to obtain a preprocessed transaction form; and performing risk control detection processing on the preprocessed transaction form based on the voice segment data to obtain a final transaction form. The present invention solves the technical problems in the prior art that the transaction data processing methods all adopt manual bookkeeping by business personnel or manual entry into system software, which cannot meet the market demand and greatly consumes the energy of business personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a transaction data processing method, apparatus, electronic device, and storage medium. Background Art

[0002] In the field of capital transactions in the financial market, at present, most practitioners in each institution manage transactions through manual bookkeeping or the web page of the operating system. The bookkeeping efficiency is low, and there are relatively high requirements for the qualifications of practitioners. Business personnel need to have a deep understanding of a series of proprietary terms.

[0003] At present, with the rapid development of the financial market, products have become increasingly complex. There are many key elements on the operation page of the existing system design software. When business personnel enter data, it is rather cumbersome and extremely prone to problems, which cannot meet the transaction sinking and popularization in the financial market field, and greatly consumes the energy and manpower of traders.

[0004] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of the present invention provide a transaction data processing method, apparatus, electronic device, and storage medium, so as to at least solve the technical problem that in the prior art, the transaction data processing method adopts manual bookkeeping by business personnel or manual entry into the system software, which cannot meet the market demand and greatly consumes the energy of business personnel.

[0006] According to one aspect of the embodiments of the present invention, a transaction data processing method is provided, including: obtaining voice control information of a transaction object, where the voice control information is used to initiate a transaction instruction; processing the voice control information into key business data and voice segment data; processing the key business data by using a voice data processing model to obtain a preprocessed transaction form; and performing risk control detection processing on the preprocessed transaction form based on the voice segment data to obtain a final transaction form.

[0007] Optionally, the processing the voice control information into key business data and voice segment data includes: performing conversion processing on the voice control information to obtain text information corresponding to the voice control information; performing extraction processing on the text information to obtain the key business data and the voice segment data, where the key business data includes at least one of the following: product type, transaction amount, transaction currency, number of transaction pens, trading date, maturity date, and the voice segment data includes at least one of the following: transaction object name, customer name, obtaining transaction object identity information, the institution to which the transaction object belongs, customer identity information, and the region to which the customer belongs.

[0008] Optionally, processing the above key business data using the voice data processing model to obtain a preprocessed transaction form includes: analyzing and processing the above key business data to obtain business type data; matching the voice data processing model based on the above business type data to determine transaction data; matching the transaction data processing model based on the above transaction data, where the above transaction data processing model is used to provide a preprocessed transaction form with a fixed template; and generating the above preprocessed transaction form using the above transaction data processing model.

[0009] Optionally, performing risk control detection processing on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form includes: analyzing and processing the above voice segment data to obtain non-transaction data; performing authentication processing on the above non-transaction data using a risk control data processing model to obtain transaction qualification information; and obtaining the final transaction form based on the above transaction qualification information.

[0010] Optionally, after performing risk control detection processing on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form, the method further includes: sending the above final transaction form to the transaction device corresponding to the above transaction object; and obtaining the processing result feedback by the above transaction object in the above transaction device, where the above processing result includes: confirmation, cancellation, modification.

[0011] Optionally, after obtaining the processing result feedback by the above transaction object in the above transaction device, the method further includes: adjusting the above voice data processing model based on the above processing result.

[0012] According to another aspect of the embodiments of the present invention, there is also provided a transaction data processing device, including: an acquisition module, configured to acquire voice control information of a transaction object, where the above voice control information is used to initiate a transaction instruction; a first processing module, configured to process the above voice control information into key business data and voice segment data; a second processing module, configured to process the above key business data using a voice data processing model to obtain a preprocessed transaction form; and a third processing module, configured to perform risk control detection processing on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form.

[0013] Optionally, the above second processing module further includes: a processing unit, configured to analyze and process the above key business data to obtain business type data; a first matching unit, configured to match the voice data processing model based on the above business type data to determine transaction data; a second matching unit, configured to match the transaction data processing model based on the above transaction data, where the above transaction data processing model is used to provide a preprocessed transaction form with a fixed template; and a generating unit, configured to generate the above preprocessed transaction form using the above transaction data processing model.

[0014] On the other hand, according to an embodiment of the present invention, there is also provided a computer-readable storage medium storing multiple instructions adapted to be loaded and executed by a processor to perform any of the above transaction data processing methods.

[0015] On the other hand, according to an embodiment of the present invention, there is also provided an electronic device including one or more processors and a memory for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement any of the above transaction data processing methods.

[0016] In an embodiment of the present invention, by obtaining voice control information of a transaction object, where the voice control information is used to initiate a transaction instruction, processing the voice control information into key business data and voice segment data, processing the key business data using a voice data processing model to obtain a preprocessed transaction form, and performing risk control detection processing on the preprocessed transaction form based on the voice segment data to obtain a final transaction form, the purpose of entering transaction information by voice is achieved, thereby realizing the technical effect of generating a transaction form according to voice information and completing risk control detection, and further solving the technical problem in the prior art that the transaction data processing methods all adopt manual bookkeeping by business personnel or manual entry into system software, which cannot meet the market demand and greatly consumes the energy of business personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and the illustrative embodiments and descriptions of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0018] Figure 1 is a flowchart of a transaction data processing method according to an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of an optional transaction form page structure according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of an adaptation technical process of an optional voice data processing model according to an embodiment of the present invention;

[0021] Figure 4 is a schematic diagram of an optional operation process of a financial market transaction bookkeeping system according to an embodiment of the present invention;

[0022] Figure 5 is a schematic diagram of the structure of a time series prediction device according to an embodiment of the present application;

[0023] Figure 6It is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. Detailed implementation manners

[0024] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties.

[0027] According to an embodiment of the present invention, an embodiment of a transaction data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0028] Figure 1 It is a flowchart of a transaction data processing method according to an embodiment of the present invention. As Figure 1 shown, the method includes the following steps:

[0029] Step S102, obtain the voice control information of the transaction object, where the voice control information is used to initiate a transaction instruction;

[0030] Step S104, process the voice control information into key service data and voice segment data;

[0031] Step S106: Process the above key business data using a voice data processing model to obtain a preprocessed transaction form.

[0032] Step S108: Perform risk control detection and processing on the preprocessed transaction form based on the above voice segment data to obtain a final transaction form.

[0033] In the embodiment of the present application, a financial market trading bookkeeping system (hereinafter referred to as the system) is used to obtain the voice control information of the trading object, and process the above voice control information into key business data and voice segment data; use a voice data processing model to process the above key business data to obtain a preprocessed transaction form; perform risk control detection and processing on the preprocessed transaction form based on the above voice segment data to obtain a final transaction form.

[0034] It should be noted that the above trading object may be a trader who helps customers conduct transactions; the above voice control information is a voice message sent by the trader to the trading device, and the above voice control information is used to initiate a trading instruction.

[0035] As an optional embodiment, the above financial market trading bookkeeping system mainly consists of a trading data processing model, a voice data processing model, and a risk control data processing model; among them, the trading data processing model is used to perform model abstraction on the data related to common financial market products, such as: spot foreign exchange, forward foreign exchange, foreign exchange swap, money market, etc. data using deep learning algorithms, and fill and match the basic trading elements based on the template definition of the trading product. The above voice data processing model is used to process and model the content of the trader's voice input, model the trader's common business types, such as: foreign exchange, investment, financing, derivatives, etc., as well as language characteristics (used to say a paragraph / short words), trading characteristics (single / batch transaction processing, large / small transaction amounts), etc., and construct standard financial market product trading bookkeeping business elements from the trader's corpus. The above risk control data processing model is used to perform risk control detection and processing on the business elements extracted by the voice data processing model and the voice segment data, and prompt the trader to confirm or cancel the transaction based on the risk control detection result.

[0036] Optionally, in the trading data processing model of the above system, a model template of the transaction form is provided, and the trader enters the common trading elements and general parameters of the common business varieties in the system, such as Figure 2 as shown in the schematic diagram of the transaction form page structure; the trader can match the trading model by key information such as the business category and template name in the voice input.

[0037] It should be noted that the above transaction data processing model can generate a transaction order template for business products based on actual business requirements. Taking the transaction bookkeeping in the money market as an example, by collecting transaction data for the past 10 - 15 years, a fixed transaction order template is generated. Moreover, traders can maintain or change the transaction order template in the money market in the system. The parameters for maintenance or change include conventional transaction elements such as currency type, transaction type (borrowing / lending), interest payment type, settlement method, interest calculation basis, rules for the interval between the trading date and the maturity date, rules for the interval between the trading date and the value date, and interest rate type. Transaction elements such as counterparty, transaction amount, and interest rate can be omitted in the above transaction order template.

[0038] Through the embodiments of the present application, the system can capture the voice commands issued by the trader user through the microphone; convert the voice commands issued by the trader or user into text, extract the key business data and voice segment data; and submit them to the voice data processing model and the risk control data processing model for processing respectively; and obtain the final transaction order according to the processing results, complete the transaction bookkeeping, achieving the purpose of entering transaction information through voice input, thus realizing the technical effect of generating a transaction order based on voice information and completing risk control detection, and further solving the technical problem that in the prior art, the transaction data processing methods all adopt manual bookkeeping by business personnel or manual entry into system software, which cannot meet the market demand and greatly consumes the energy of business personnel.

[0039] As an alternative embodiment, the processing of the above voice control information into key business data and voice segment data includes:

[0040] Step S202, perform conversion processing on the above voice control information to obtain text information corresponding to the above voice control information;

[0041] Step S204, perform extraction processing on the above text information to obtain the above key business data and the above voice segment data, where the above key business data includes at least one of the following: product type, transaction amount, transaction currency, number of transaction records, trading date, maturity date, and the above voice segment data includes at least one of the following: name of the trading object, customer name, obtain the identity information of the trading object, the institution to which the trading object belongs, the identity information of the customer, and the region to which the customer belongs.

[0042] In the embodiments of the present application, after the system obtains the above voice control information, it first performs conversion processing on the above voice control information to obtain text information corresponding to the above voice control information; and performs extraction processing on the above text information to obtain the above key business data and the above voice segment data.

[0043] It should be noted that the above key business data includes at least one of the following: product type, transaction amount, transaction currency, number of transactions, transaction date, maturity date. The above voice segment data includes at least one of the following: name of the transaction object, customer name, obtaining identity information of the transaction object, institution to which the transaction object belongs, customer identity information, and region to which the customer belongs.

[0044] As an alternative embodiment, as Figure 3 shown in the schematic diagram of the adaptation technical process of the voice data processing model; the voice control information of the trader can be obtained through devices such as microphones, the voice input by the trader is converted into text, and split according to keywords. For example: the trader's voice is "Help me do 10 foreign exchange spot transactions with customer XXX, 10,000 yuan each in XX currency, today's transaction, tomorrow's maturity", and the keyword of the transaction elements after splitting is: me, customer XXX, 10, foreign exchange spot transactions, each, 10,000, XX currency, today, transaction, tomorrow, maturity; and the voice segment is intercepted in combination with the split keywords.

[0045] As an alternative embodiment, the above key business data is processed by using the voice data processing model to obtain a preprocessed transaction form, including:

[0046] Step S302, analyze and process the above key business data to obtain business type data;

[0047] Step S304, match the voice data processing model based on the above business type data to determine transaction data;

[0048] Step S306, match the transaction data processing model based on the above transaction data, wherein the above transaction data processing model is used to provide a preprocessed transaction form with a fixed template;

[0049] Step S308, generate the above preprocessed transaction form by using the above transaction data processing model.

[0050] In the embodiment of the present application, after the system splits the above voice control information to obtain the key business data and the above voice segment data, it analyzes and processes the above key business data to obtain business type data; matches the voice data processing model based on the above business type data to determine transaction data; matches the transaction data processing model based on the above transaction data; and generates the above preprocessed transaction form by using the above transaction data processing model.

[0051] It should be noted that the above voice data processing model can be implemented in the following way. Add a "Voice Bookkeeping Matching Model" menu to the system, which supports traders to perform voice input, voice matching correction, and key voice segment matching on this page, so as to achieve personal adaptation to the basic voice model provided by the system. For example: the trader uses the voice input function to input voice in the system; uses the voice matching correction function to convert the voice data input by the trader into text, split it according to keywords, provide it to the trader for text correction, and add it to the dictionary; uses the key voice segment matching function to perform default conversion, and supports the trader to maintain the matching dictionary in the system. The matching dictionary is shown in Table 1:

[0052] Table 1

[0053] Voice keyword Data after system conversion Today Current system date Tomorrow Current system date + 1 XX Currency Currency abbreviation: XXX Expire Transaction expiration date Transaction Transaction start date Accrue interest Transaction accrual date Fixed Transaction type: Fixed rate Floating / reset Transaction type: Floating rate Foreign exchange spot (transaction) Business product: Foreign exchange spot Foreign exchange forward (transaction) Business product: Foreign exchange forward Foreign exchange swap (transaction) Business product: Foreign exchange swap Money market (transaction) Business product: Money market I Trader: Obtain trader ID *(Name) Trader: Corresponding trader ID *Customer Counterparty: Obtain counterparty ID

[0054] As an optional embodiment, after the system splits the above voice control information into key business data and the above voice segment data, it obtains the data maintained by the trader in the corresponding menu and corrects the preprocessed text data; obtains the data maintained by the trader in the corresponding menu and the matching parameters provided by the system by default, and converts the preprocessed text data into business parameters and technical parameters; obtains the business type data; matches the voice data processing model based on the above business type data to determine the transaction data; matches the transaction data processing model based on the above transaction data; uses the above transaction data processing model to generate the above preprocessed transaction order.

[0055] It should be noted that on the basis of the maintained transaction data processing model template, the preprocessed data is matched with the transaction model parameters; the common supervised machine learning algorithm (K-nearest neighbor algorithm) is used for supervised learning. The transaction bookkeeping system trains the model according to the voice input in the Mandarin version, and then generates a preprocessed transaction order by matching the business products of the fixed template, and conducts supervised training to generate a voice data processing model; then through the personal actual transaction operation process of the trader, the voice model is optimized. The above K-nearest neighbor algorithm is a classification algorithm and belongs to supervised learning in machine learning. Its idea is: if a sample belongs to a certain category in most of the K most similar (i.e., the nearest in the feature space) samples in the feature control, then this sample also belongs to this category; K is usually an integer not greater than 20. In the nearest neighbor algorithm, the selected neighbors are all objects that have been correctly classified.

[0056] It should also be noted that the characteristic parameters of the above voice model mainly include the following dimensions: user name, affiliated institution name, customer name, customer nature, customer risk level, customer credit limit, business category, product template, amount, currency, interest rate, number of transaction pens, trading date, maturity date, etc.

[0057] As an alternative embodiment, the risk control detection process for the preprocessed transaction order based on the voice segment data to obtain the final transaction order includes:

[0058] Step S402: Analyze and process the voice segment data to obtain non-transaction data;

[0059] Step S404: Use the risk control data processing model to authenticate the non-transaction data to obtain transaction qualification information;

[0060] Step S406: Based on the transaction qualification information, obtain the final transaction order.

[0061] In the embodiment of the present application, the voice segment data is analyzed and processed to obtain non-transaction data; the non-transaction data is authenticated using the risk control data processing model to obtain transaction qualification information; and the final transaction order is obtained based on the transaction qualification information.

[0062] It should be noted that the above risk control data processing model mainly includes two parts: business control and transaction control. Business control manages non-transaction element parameters such as traders, trading counterparts, affiliated institutions, and affiliated regions, and transaction control manages transaction elements such as transaction amounts, transaction volumes, and customer limits; the specific implementation part is implemented by an external interface, and this system calls the functions of this part after unified encapsulation.

[0063] As an alternative embodiment, after the risk control detection process for the preprocessed transaction order based on the voice segment data to obtain the final transaction order, the method further includes:

[0064] Step S502: Send the final transaction order to the transaction device corresponding to the transaction object;

[0065] Step S504: Obtain the processing result feedback by the transaction object in the transaction device, where the processing result includes: confirmation, cancellation, and modification.

[0066] As an alternative embodiment, after obtaining the processing result feedback by the transaction object in the transaction device, the method further includes:

[0067] Step S602: Adjust the voice data processing model based on the processing result.

[0068] In the embodiment of the present application, after generating the final transaction order, the final transaction order is sent to the transaction device corresponding to the transaction object; the transaction object can view the final transaction order on the transaction device for confirmation.

[0069] As an optional embodiment, the trader can complete the processing flow of the final transaction order through operations such as confirmation, cancellation, and modification, and optimize the voice data processing model based on the processing results. For example: if you choose to confirm the transaction, the voice model branch will be strengthened; if you choose to cancel the transaction, the voice model branch will be weakened; if you choose to modify, the transaction element matching parameters will be optimized.

[0070] In the embodiments of the present application, Figure 4 The schematic diagram of the operation process of the financial market transaction bookkeeping system shown in the figure, the system captures the voice instructions issued by the trader user through the microphone; converts the voice instructions issued by the trader into text, extracts the key business data and voice fragment data and submits them to the voice model and risk control model for processing respectively; and matches the extracted transaction element keywords with the voice data processing model to obtain the general configuration parameters in the model, thereby obtaining the business product type and transaction data conversion to be operated by the trader; the transaction data processing model matches the corresponding transaction model according to the converted data to generate a pre-processed transaction order; forms a pre-processed transaction order for financial market products; extracts parameter information such as non-transaction elements; the risk control data processing model pre-processes risk control parameter data such as transaction elements; combines the risk control model (business management and control) part to check the trader's transaction limit and customer credit limit, and whether the customer is on the blacklist; performs a risk control model (transaction control) check based on the transaction amount and other contents of the pre-processed transaction order, and submits the generated final transaction order to the trader for confirmation after the check is passed; the trader completes the processing flow of the final transaction order through operations such as confirmation, cancellation, and modification, and the system optimizes the voice data processing model according to the processing results.

[0071] Through the above steps, the human resources of financial market traders can be released. By using voice to record transactions, traders can quickly and massively record transactions and improve work efficiency. It can also increase social consensus on financial market products, lower the trading threshold for basic financial market products, uniformly maintain common business parameters, filter out irrelevant technical parameters, and promote the ease of human-computer interaction. It can also open up certain business products to ordinary users to buy and sell financial products, thereby improving the liquidity of the financial market.

[0072] Figure 5 is a schematic diagram of the structure of a time series prediction device according to an embodiment of the present application, such as Figure 5 As shown, the above-mentioned time series prediction device includes: an acquisition module 50, a first processing module 52, a second processing module 54 and a third processing module 56, wherein:

[0073] An acquisition module 50 is used to acquire voice control information of a transaction object, wherein the voice control information is used to initiate a transaction instruction;

[0074] The first processing module 52 is configured to process the above voice control information into key service data and voice segment data;

[0075] The second processing module 54 is configured to process the above key service data by using a voice data processing model to obtain a preprocessed transaction form;

[0076] The third processing module 56 is configured to perform risk control detection processing on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form.

[0077] Optionally, in the transaction data processing device provided in the embodiment of the present application, the second processing module further includes: a processing unit configured to analyze and process the above key service data to obtain service type data; a first matching unit configured to match a voice data processing model based on the above service type data to determine transaction data; a second matching unit configured to match a transaction data processing model based on the above transaction data, where the transaction data processing model is used to provide a preprocessed transaction form with a fixed template; and a generating unit configured to generate the above preprocessed transaction form by using the above transaction data processing model.

[0078] The transaction data processing device provided in the embodiment of the present application obtains the voice control information of a transaction object, where the above voice control information is used to initiate a transaction instruction; processes the above voice control information into key service data and voice segment data; processes the above key service data by using a voice data processing model to obtain a preprocessed transaction form; and performs risk control detection processing on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form, achieving the purpose of entering transaction information by voice, thereby realizing the technical effect of generating a transaction form according to voice information and completing risk control detection, and further solving the technical problem that in the prior art, the transaction data processing method all adopts manual bookkeeping by business personnel or manual entry into system software, which cannot meet the market demand and greatly consumes the energy of business personnel.

[0079] The above transaction data processing device includes a processor and a memory. The above acquisition module 50, the first processing module 52, the second processing module 54, the third processing module 56, etc. are all stored in the memory as program units, and the processor executes the above program units stored in the memory to implement corresponding functions.

[0080] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the training and prediction speeds of the convolutional neural network are accelerated by adjusting the kernel parameters.

[0081] The memory may include non - permanent memory in the form of computer - readable media, random access memory (RAM) and / or non - volatile memory such as read - only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0082] An embodiment of the present invention provides a computer - readable storage medium, on which a program is stored, and when the program is executed by a processor, the above - mentioned transaction data processing method is implemented.

[0083] An embodiment of the present invention provides a processor, which is used to run a program, and when the program runs, the above - mentioned transaction data processing method is executed.

[0084] As Figure 6 As shown, an embodiment of the present invention provides an electronic device. The electronic device 10 includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining voice control information of a transaction object, where the voice control information is used to initiate a transaction instruction; processing the voice control information into key business data and voice segment data; using a voice data processing model to process the key business data to obtain a pre - processed transaction form; performing risk control detection processing on the pre - processed transaction form based on the voice segment data to obtain a final transaction form.

[0085] Optionally, when the processor executes the program, the following steps are implemented: performing conversion processing on the voice control information to obtain text information corresponding to the voice control information; performing extraction processing on the text information to obtain the key business data and the voice segment data, where the key business data includes at least one of the following: product type, transaction amount, transaction currency, number of transaction pens, trading date, maturity date, and the voice segment data includes at least one of the following: transaction object name, customer name, obtaining transaction object identity information, the institution to which the transaction object belongs, customer identity information, and the region to which the customer belongs.

[0086] Optionally, when the processor executes the program, the following steps are implemented: performing analysis processing on the key business data to obtain business type data; matching a voice data processing model based on the business type data to determine transaction data; matching a transaction data processing model based on the transaction data, where the transaction data processing model is used to provide a pre - processed transaction form with a fixed template; generating the pre - processed transaction form using the transaction data processing model.

[0087] Optionally, when the processor executes the program, the following steps are implemented: performing analysis processing on the voice segment data to obtain non - transaction data; performing authentication processing on the non - transaction data using a risk control data processing model to obtain transaction qualification information; obtaining a final transaction form based on the transaction qualification information.

[0088] Optionally, when the processor executes the program, the following steps are implemented: sending the above final transaction form to the transaction device corresponding to the above transaction object; obtaining the processing result feedback by the above transaction object in the above transaction device, where the above processing result includes: confirmation, cancellation, modification.

[0089] Optionally, when the processor executes the program, the following steps are implemented: adjusting the above speech data processing model based on the above processing result.

[0090] The present application also provides a computer program product, which when executed on a data processing device, is adapted to execute a program initialized with the following method steps: obtaining voice control information of a transaction object, where the above voice control information is used to initiate a transaction instruction; processing the above voice control information into key service data and voice segment data; using a voice data processing model to process the above key service data to obtain a preprocessed transaction form; performing a risk control detection process on the above preprocessed transaction form based on the above voice segment data to obtain a final transaction form.

[0091] Optionally, when executed on a data processing device, it is adapted to execute a program initialized with the following method steps: performing a conversion process on the above voice control information to obtain text information corresponding to the above voice control information; performing an extraction process on the above text information to obtain the above key service data and the above voice segment data, where the above key service data includes at least one of the following: product type, transaction amount, transaction currency, number of transaction pens, transaction date, maturity date, and the above voice segment data includes at least one of the following: transaction object name, customer name, obtaining transaction object identity information, the institution to which the transaction object belongs, customer identity information, and the region to which the customer belongs.

[0092] Optionally, when executed on a data processing device, it is adapted to execute a program initialized with the following method steps: performing an analysis process on the above key service data to obtain service type data; matching a voice data processing model based on the above service type data to determine transaction data; matching a transaction data processing model based on the above transaction data, where the above transaction data processing model is used to provide a preprocessed transaction form with a fixed template; generating the above preprocessed transaction form using the above transaction data processing model.

[0093] Optionally, when executed on a data processing device, it is adapted to execute a program initialized with the following method steps: performing an analysis process on the above voice segment data to obtain non-transaction data; performing an authentication process on the above non-transaction data using a risk control data processing model to obtain transaction qualification information; obtaining a final transaction form based on the above transaction qualification information.

[0094] Optionally, when executed on a data processing device, it is adapted to execute a program initialized with the following method steps: sending the above-mentioned final transaction form to the transaction device corresponding to the above-mentioned transaction object; obtaining the processing result feedback by the above-mentioned transaction object in the above-mentioned transaction device, where the above-mentioned processing result includes: confirmation, cancellation, modification.

[0095] Optionally, when executed on a data processing device, it is adapted to execute a program initialized with the following method steps: adjusting the above-mentioned voice data processing model based on the above-mentioned processing result.

[0096] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0098] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1Steps for the functions specified in one or more boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0101] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0102] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0103] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0105] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for processing transaction data, characterized in that, including: Obtain the voice control information of the trading object, where the voice control information is used to initiate a trading instruction; Process the voice control information into key business data and voice segment data; Process the key business data using a voice data processing model to obtain a preprocessed trading order; Perform risk control detection processing on the preprocessed trading order based on the voice segment data to obtain a final trading order; The process of using a voice data processing model to process the key business data to obtain a preprocessed trading order includes: analyzing and processing the key business data to obtain business type data; matching a voice data processing model based on the business type data to determine transaction data; matching a transaction data processing model based on the transaction data, where the transaction data processing model is used to provide a preprocessed trading order with a fixed template; generating the preprocessed trading order using the transaction data processing model; The process of performing risk control detection processing on the preprocessed trading order based on the voice segment data to obtain a final trading order includes: analyzing and processing the voice segment data to obtain non-transaction data; authenticating the non-transaction data using a risk control data processing model to obtain transaction qualification information; obtaining the final trading order based on the transaction qualification information.

2. The method according to claim 1, wherein The process of processing the voice control information into key business data and voice segment data includes: Performing conversion processing on the voice control information to obtain text information corresponding to the voice control information; Performing extraction processing on the text information to obtain the key business data and the voice segment data, where the key business data includes at least one of the following: product type, transaction amount, transaction currency, number of transaction pens, trading date, maturity date, and the voice segment data includes at least one of the following: trading object name, customer name, obtaining trading object identity information, trading object affiliated institution, customer identity information, customer affiliated region.

3. The method according to claim 1, characterized in that, After performing risk control detection processing on the preprocessed trading order based on the voice segment data to obtain a final trading order, the method further includes: Sending the final trading order to the trading device corresponding to the trading object; Obtaining the processing result feedback by the trading object in the trading device, where the processing result includes: confirmation, cancellation, modification.

4. The method according to claim 3, characterized in that After obtaining the processing result feedback by the trading object in the trading device, the method further includes: Adjusting the voice data processing model based on the processing result.

5. A transaction data processing device, characterized in that, including: An obtaining module, configured to obtain the voice control information of the trading object, where the voice control information is used to initiate a trading instruction; A first processing module, configured to process the voice control information into key business data and voice segment data; A second processing module, configured to process the key business data using a voice data processing model to obtain a preprocessed trading order; A third processing module, configured to perform risk control detection processing on the preprocessed trading order based on the voice segment data to obtain a final trading order; The second processing module further includes: a processing unit configured to analyze and process the critical business data to obtain business type data; a first matching unit configured to match a voice data processing model based on the business type data to determine transaction data; a second matching unit configured to match a transaction data processing model based on the transaction data, wherein the transaction data processing model is used to provide a preprocessed transaction form with a fixed template; and a generating unit configured to generate the preprocessed transaction form by using the transaction data processing model. The apparatus is further configured to analyze and process the voice segment data to obtain non-transaction data; authenticate the non-transaction data by using a risk control data processing model to obtain transaction qualification information; and obtain a final transaction form based on the transaction qualification information.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the transaction data processing method according to any one of claims 1 to 4.

7. An electronic device, characterized in that, It includes one or more processors and a memory, and the memory is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the transaction data processing method according to any one of claims 1 to 4.

Images