Conversation robot interaction method and device for pledge-type repurchase transaction, electronic equipment and storage medium

Abstract

The invention discloses a conversation robot interaction method and device for pledge-type repurchase transaction, electronic equipment and a storage medium, and the method comprises the steps: responding to an inquiry process of pledge-type repurchase transaction, and according to a first interaction interface in a conversation management and natural language processing module and a second interaction interface in an internal transaction system, obtaining an inquiry result of the pledge-type repurchase transaction; session content for a conversation robot is generated, the first interaction interface is used as an information transmission interface, and the second interaction interface is used as a transaction element checking interface; and sending the session content through a financial transaction instant messaging platform. According to the invention, traders are helped to automatically process pledge-type rebuying related processes, the efficiency is improved, and the burden is relieved.

Description

Technical Field

[0001] This application relates to the technical fields of artificial intelligence and dialogue robot technology, and in particular, to a dialogue robot interaction method, device, electronic device, and storage medium for pledged repurchase transactions. Background Art

[0002] In a pledged repurchase transaction, while the fund-raising party (the repurchaser) pledges bonds to the fund-supplying party (the reverse repurchaser) to raise funds, the two parties agree that on a certain future date, the repurchaser will return the principal and the interest calculated at the agreed repurchase rate to the reverse repurchaser, and the reverse repurchaser will return the originally pledged bonds to the repurchaser.

[0003] In the related art, using dialogue quotes is a common quoting method for pledged repurchases. Traders quote and inquire with each other through instant messaging tools to discuss specific details such as the price, quantity, and term of the transaction.

[0004] However, all dialogue quotes in pledged repurchase transactions require manual conversations. In this way, traders inquire, quote, and match with the counterparty through instant messaging software, and finally reach a transaction intention. In work, a large number of cumbersome conversations are inefficient, and at the same time, it is easier to make manual communication errors, making the burden on relevant traders heavier. Summary of the Invention

[0005] Embodiments of this application provide a dialogue robot interaction method, device, electronic device, and storage medium for pledged repurchase transactions to provide an automated interaction method to help traders automatically process pledged repurchase-related processes and improve efficiency and reduce the burden.

[0006] Embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, embodiments of this application provide a dialogue robot interaction method for pledged repurchase transactions, where the method includes:

[0008] In response to an inquiry process for a pledged repurchase transaction, generate conversation content for the dialogue robot according to a first interaction interface in the session management and natural language processing module and a second interaction interface in the internal trading system, where the first interaction interface is used as an information transmission interface, and the second interaction interface is used as a trading element check interface;

[0009] Send the conversation content through the financial trading instant messaging platform.

[0010] In some embodiments, the generating conversation content for the dialogue robot according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system in response to an inquiry process for a pledged repurchase transaction includes:

[0011] In response to the active inquiry process of the pledged repo transaction, the Robot service in the internal trading system is started;

[0012] Invoking the first interactive interface according to the Robot service, generating a first POST request and sending it to the session management and natural language processing module, wherein the first POST request carries at least an active inquiry identifier and an active inquiry parameter;

[0013] The first interactive interface is called to receive the active inquiry words returned by the first POST request, and an active inquiry message is generated and pushed to the financial transaction instant messaging platform.

[0014] In some embodiments, in response to the inquiry process of the pledged repo transaction, generating conversation content for the dialogue robot according to the first interaction interface in the conversation management and natural language processing module and the second interaction interface in the internal transaction system includes:

[0015] In response to the process of receiving an inquiry for a pledged repo transaction, sending a notification message to the Robot service in the internal trading system;

[0016] Starting the Risk service in the internal trading system according to the Robot service, generating a second POST request and sending it to the session management and natural language processing module, wherein the second POST request carries at least a static check result and a request text;

[0017] Receive the inquiry receiving words returned by the second POST request, generate an inquiry receiving message and push it to the financial transaction instant messaging platform.

[0018] In some embodiments, the method further comprises:

[0019] Perform corresponding static checks according to the Robot service;

[0020] If the static check passes, the internal transaction system initiates the second POST request by calling the first interactive interface, and the second POST request is used to request the session management and natural language processing module to generate a response script for receiving an inquiry.

[0021] In some embodiments, the method further comprises:

[0022] The session management and natural language processing module invokes the second interaction interface to perform transaction element checks, and returns the check results to the session management and natural language processing module according to the second interaction interface, so that the session management and natural language processing module generates corresponding reply scripts based on the check results of the second interaction interface, and at the same time performs the interface return of the first interaction interface;

[0023] The internal trading system obtains the return result through the first interaction interface, pushes the reply script for receiving the inquiry to the financial trading instant messaging platform, and updates the session status at the same time.

[0024] In some embodiments, the first interaction interface is stored in the session management and natural language processing module and provided for the internal trading system to call;

[0025] The first interaction interface includes basic parameters, static check parameters, inquiry parameters, and other parameters.

[0026] In some embodiments, the second interaction interface is stored in the internal trading system and provided for the session management and natural language processing module to call;

[0027] The transaction elements of the second interaction interface include session ID, quotation direction, repurchase term, transaction amount, type of pledged securities, type of repurchase interest rate, whether to conduct credit check, issuer name and quota list, and whether to actively inquire.

[0028] In a second aspect, an embodiment of the present application further provides a dialogue robot interaction device for a pledged repurchase transaction, where the device includes:

[0029] A response module, configured to respond to the inquiry process of the pledged repurchase transaction, generate session content for the dialogue robot according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system, where the first interaction interface is used as an information transmission interface, and the second interaction interface is used as a transaction element check interface;

[0030] A sending module, configured to send the session content through the financial trading instant messaging platform.

[0031] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the above method.

[0032] Fourthly, an embodiment of the present application further provides a computer-readable storage medium storing one or more programs, which, when executed by an electronic device including multiple application programs, cause the electronic device to execute the above method.

[0033] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: In response to the inquiry process of the pledged repurchase transaction, session content for the chatbot is generated according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system. Based on the fact that the first interaction interface is used as an information transmission interface and the second interaction interface is used as a trading element inspection interface, the interaction between the internal trading system and the session management and natural language processing module is realized, and the session content is sent through the financial trading instant messaging platform to realize chatbot interaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0035] Figure 1 It is a schematic flowchart of the chatbot interaction method for the pledged repurchase transaction in the embodiment of the present application;

[0036] Figure 2 It is a schematic structural diagram of the pledged repurchase transaction robot corresponding to the chatbot interaction method for the pledged repurchase transaction in the embodiment of the present application;

[0037] Figure 3 It is a schematic timing diagram of the active inquiry process in the chatbot interaction method for the pledged repurchase transaction in the embodiment of the present application;

[0038] Figure 4 It is a schematic timing diagram of the received inquiry process in the chatbot interaction method for the pledged repurchase transaction in the embodiment of the present application;

[0039] Figure 5 It is a schematic structural diagram of the chatbot interaction device for the pledged repurchase transaction in the embodiment of the present application;

[0040] Figure 6 It is a schematic structural diagram of an electronic device in the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the objectives, technical solutions, and advantages of this application more clear, the following will clearly and completely describe the technical solutions of this application in combination with specific embodiments of this application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0042] The following will, in combination with the drawings, elaborate on the technical solutions provided by each embodiment of this application.

[0043] Dialogue robots can be classified into rule-based dialogue robots and large model-based dialogue robots based on different underlying algorithms. Rule-based dialogue robots conduct conversations according to predefined rules and provide fixed responses based on keywords or menu options; large model-based dialogue robots can handle a wider range of topics without being limited to specific fields or tasks. They can have a wider range of conversations with users, from casual chats to discussions in professional fields. Current dialogue robots, depending on their objectives, include customer service dialogue robots for communicating with customers for pre-sales and after-sales, popular science dialogue robots for interacting with students, travel dialogue robots for users to book hotels and flights, etc.

[0044] Dialogue trading robots related to financial transactions need to meet the requirements of professionalism, accuracy, and real-time performance. In terms of professionalism, the dialogue robot for pledged repurchase transactions needs to possess rich financial market and trading knowledge. Especially in the field of pledged repurchase, the dialogue needs to ensure that the robot has the ability to handle complex financial products, pledged securities, and trading processes. In terms of accuracy, the dialogue robot uses highly precise algorithms in repurchase transaction calculations, pricing, risk assessment, etc., to ensure that data processing and analysis do not deviate from the financial model to avoid misleading decisions. In terms of real-time performance, the dialogue robot needs to respond quickly, conduct real-time checks and verifications on relevant trading elements of the counterparty to ensure that the transaction meets the expected assumptions and meets the requirements of risk control and legal compliance.

[0045] Aiming at the problem in the related technology that there is a lack of a dedicated dialogue robot for pledged repurchase transactions in the financial field, the embodiments of this application provide an interaction method for a dialogue robot for pledged repurchase transactions. The internal trading system of a financial institution can be combined with a rule-based dialogue robot or a large model-based dialogue robot to realize functions such as transaction inquiry and quotation, trading element inspection, collateral management, trading risk control, and transaction confirmation.

[0046] The embodiments of this application provide an interaction method for a dialogue robot for pledged repurchase transactions, as Figure 1As shown in the figure, a schematic flowchart of the method for the dialogue robot interaction in the pledged repo transaction in the embodiment of the present application is provided. The method at least includes the following steps S110 to S120:

[0047] Step S110, in response to the inquiry process of the pledged repo transaction, generate the session content for the dialogue robot according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system. The first interaction interface is used as an information transmission interface, and the second interaction interface is used as a trading element check interface.

[0048] As a dialogue robot for pledged repo transactions, it is mainly used to respond to the relevant inquiry processes of pledged repo transactions, give corresponding session content to reply to the inquiry processes, and conduct subsequent trading inquiries and quotes, trading element checks, collateral management, trading risk control, transaction confirmations, etc. according to the inquiry processes. Trading inquiries and quotes, as an important link, can be taken on by the dialogue robot for the dialogue task. And in the subsequent processes, confirm trading risks, check trading elements, and manage the collateral associated with the pledged repo transaction. It can be understood that the dialogue robot based on the pledged repo transaction can realize the automatic dialogue transaction of the pledged repo transaction, help traders automatically process steps such as inquiries, quotes, and confirmations related to pledged repo, and reduce the manual burden on traders.

[0049] A first interaction interface is set in the session management and natural language processing module, and a second interaction interface is set in the internal trading system. Through the first interaction interface and the second interaction interface, the session content for the dialogue robot can be generated. Specifically, the first interaction interface realizes basic calls and transmissions as an information transmission interface, and the second interaction interface realizes trading-related element checks as a trading element check interface to ensure the security of the transaction.

[0050] Step S120, send the session content through the financial trading instant messaging platform.

[0051] The financial trading instant messaging platform is a well-known and common API interface in the art. Through the financial trading instant messaging platform, the generated session content can be sent to the other party (the repo party or the reverse repo party) of the pledged repo transaction.

[0052] Through the above method, through the first interaction interface and the second interaction interface, combined with technologies such as NLP natural language processing, automatic dialogue transactions of pledged repo transactions can be realized in the financial trading system, helping traders automatically process steps such as inquiries, quotes, and confirmations related to pledged repo.

[0053] In addition, by integrating conversational robots into the interbank market, financial service platforms or internal trading systems, full-process risk control and transaction processing can be achieved to improve the efficiency of traders' transactions, reduce manual intervention, and ensure accuracy and compliance.

[0054] like Figure 2 As shown, in order to realize the collaboration between the internal trading system of a financial institution and a rule-based dialogue robot or a large model-based dialogue robot to complete the intelligent dialogue transaction of the pledged repurchase transaction, and to help traders automatically handle the inquiry, quotation, confirmation and other steps related to the pledged repurchase, two types of interaction interfaces are proposed in the embodiments of the present application, and related interaction methods are given.

[0055] It can be understood that the conversational robot can choose to adopt a rule-based conversational robot or a large model-based conversational robot, or both a rule-based conversational robot and a large model-based conversational robot according to the actual scenario.

[0056] like Figure 2 As shown, it is the smallest unit that constitutes the pledged repo transaction dialogue robot: iDeal, the internal transaction system of the financial institution (referred to as the internal transaction system), and the session management and natural language processing module. Among them, iDeal is an instant messaging platform launched by the China Foreign Exchange Trading Center (CFETS) for the inter-bank domestic and foreign currency markets. iDeal is mainly used to send and receive conversations between its own traders and counterparty institutional traders, send and confirm transaction intentions, etc. The internal transaction system is mainly used for process control of the transaction robot and inspection of transaction elements, etc. The session management and natural language processing module is mainly used to extract the intention and entity of the conversation through natural language recognition, and at the same time perform session management and generate reply words according to the return results of the element inspection interface. The above three modules cooperate with each other to jointly realize the pledged repo transaction. In the embodiment of the present application, the dialogue text transmission, transaction parameter inspection and related process control are realized through the configuration of the interactive interface.

[0057] In one embodiment of the present application, in response to the inquiry process of the pledged repurchase transaction, according to the first interactive interface in the session management and natural language processing module and the second interactive interface in the internal transaction system, a conversation content for the dialogue robot is generated, including: in response to the active inquiry process of the pledged repurchase transaction, starting the Robot service in the internal transaction system; calling the first interactive interface according to the Robot service, generating a first POST request and sending it to the session management and natural language processing module, the first POST request carrying at least an active inquiry identifier and an active inquiry parameter; calling the first interactive interface to receive the active inquiry script returned by the first POST request, generating an active inquiry message and pushing it to the financial transaction instant messaging platform.

[0058] like Figure 3 As shown in the figure, in the active inquiry scenario of pledged repo transactions, the following steps are mainly included:

[0059] Step 1: The Robot service actively starts the price inquiry thread.

[0060] Step 2: Post request to generate reply words. The Post request includes but is not limited to active inquiry mark, active inquiry parameters, etc.

[0061] Step 3, generate active inquiry script: Hello, today's transaction plan has been announced as follows:

[0062] [Transaction Type] Pledged Repo

[0063]

Transaction direction

[0064] [Optional transaction period] 1 day - 7 days

[0065] Step 4: Post request return. Post request return includes but is not limited to (1) reply text (Hello, our trading plan for today has been announced), (2) session control, and (3) transaction elements.

[0066] Step 5: Actively push the inquiry message to the institution plug-in and update the session status.

[0067] Active price inquiry includes but is not limited to: (1) searching for the trader with whom the counterparty institution has recently chatted in the set group according to the active price inquiry trading plan; (2) flow control; and (3) passing static detection.

[0068] In the above process, the Robot service is completed in the internal trading system, the Post request is sent by the internal trading system to the session management and natural language processing module, and the Post request return is sent by the session management and natural language processing module to the internal trading system. The institution plug-in uses iDeal.

[0069] It can be understood that the Robot service is a general automation service, that is, through the Robot service, a machine can simulate human operation and complete related automation services.

[0070] Please continue to refer to Figure 3 In the process of the pledged repo transaction dialogue robot actively inquiring other institutions, the interaction process is as follows:

[0071] First, the active inquiry thread of the relevant services of the internal trading system of the financial institution is started, and the counterparties are found in the group according to the trading plan set by the trader to make inquiries.

[0072] Then, the trading system calls the first interactive interface, initiates a POST request, and requests the session management and natural language processing module to generate a reply script. The session management and natural language processing module generates an active inquiry script, the call request ends, and the relevant request result is returned. Figure 3 As shown in ②-④.

[0073] Finally, after the trading system calls the first type of interactive interface and gets the return result, it pushes the active inquiry message to iDeal and updates the session status, etc. Figure 3 As shown in ⑤-⑥.

[0074] In one embodiment of the present application, in response to the inquiry process of the pledged repurchase transaction, according to the first interactive interface in the session management and natural language processing module and the second interactive interface in the internal trading system, a conversation content for the dialogue robot is generated, including: in response to the receiving inquiry process of the pledged repurchase transaction, a notification message is sent to the Robot service in the internal trading system; according to the Robot service, the Risk service in the internal trading system is started, a second POST request is generated and sent to the session management and natural language processing module, and the second POST request carries at least a static check result and a request text; receiving the receiving inquiry script returned by the second POST request, generating a receiving inquiry message and pushing it to the financial transaction instant messaging platform.

[0075] like Figure 4 As shown in the figure, in the scenario of receiving price inquiry in pledged repo transaction, the following steps are mainly included:

[0076] Step 1: The organization plugin sends a message to the Robot service.

[0077] Step 2: The Robot service performs a static check and starts the Risk service at the same time. The check includes but is not limited to iDeal friend check, friend robot start and stop check, trading plan start and stop check, trading time period check, blacklist and whitelist check, and anti-money laundering / anti-fraud check.

[0078] Step 3, Post request, request to generate reply script. Post request includes but is not limited to static check results and request text such as: Good morning, I want to borrow 50 million yuan overnight.

[0079] Step 4: Extract elements. For example, transaction amount: 50 million yuan, repurchase period: 1 day, etc.

[0080] Step 5: Check the factors. The content of the factor check includes but is not limited to the quotation direction check, transaction amount check, and repurchase period check.

[0081] Step 6: Return the feature detection result.

[0082] Step 7, generate conversation scripts. For example, "What type of pledged securities do you pledge? Currently, our bank supports pledging interest rate bonds. You can directly reply with the type of pledged securities, such as 'interest rate bonds'."

[0083] Step 9, Post request return. For example, (1) Reply text: "What type of pledged securities do you pledge..."; (2) Conversation control; (3) Element control.

[0084] Such as Figure 4 As shown, during the process of the pledged repurchase transaction chatbot receiving inquiries from other institutions, the interaction process is as follows:

[0085] First, the trader of other institutions sends a message to the back-end of the internal trading system through iDeal, and the pledged repurchase chatbot service of the internal trading system conducts relevant static checks.

[0086] Secondly, after the static check passes, the trading system calls the first interaction interface to initiate a POST request to request the session management and natural language processing module to generate a reply script, as Figure 4 shown in ③.

[0087] Then, the session management and natural language processing module calls the second interaction interface, i.e., the trading element check interface, to check the extracted trading elements such as the quotation direction, trading amount, repurchase term, etc. Subsequently, the second interaction interface returns the result to the session management and natural language processing module. As Figure 4 shown in ④-⑥.

[0088] Then, the session management and natural language processing module generates a corresponding reply script according to the check result of the second interaction interface (trading element check interface), and at the same time makes an interface return of the first interaction interface, as Figure 4 shown in ⑨.

[0089] Finally, after the trading system obtains the return result from the first interaction interface, it pushes the reply script to iDeal and updates the session status, etc., as Figure 4 shown in ⑩.

[0090] In an embodiment of the present application, the method further includes: performing corresponding static checks according to the Robot service; if the static checks pass, the internal trading system initiates the second POST request by calling the first interaction interface, and the second POST request is used to request the session management and natural language processing module to generate a reply script for receiving inquiries.

[0091] Such as Figure 4As shown, the internal transaction system performs a corresponding static check according to the Robot service, and if the static check passes, a reply script for receiving the inquiry is generated in the session management and natural language processing module. The internal transaction system initiates the second POST request by calling the first interactive interface.

[0092] In one embodiment of the present application, the method also includes: calling the second interactive interface through the session management and natural language processing module to check the transaction elements, and returning the check result to the session management and natural language processing module according to the second interactive interface, so that the session management and natural language processing module generates a corresponding reply script according to the check result of the second interactive interface, and simultaneously returns the interface of the first interactive interface; the internal transaction system obtains the return result through the first interactive interface, pushes the reply script of the received inquiry to the financial transaction instant messaging platform and updates the session status at the same time.

[0093] The session management and natural language processing module calls the second interactive interface to check the transaction elements and returns the check result to the session management and natural language processing module according to the second interactive interface, so that the session management and natural language processing module generates a corresponding reply script according to the check result of the second interactive interface. The interface return of the first interactive interface is also performed through the reply script. In this way, the internal transaction system obtains the return result through the first interactive interface, and then pushes the reply script of the received inquiry to the financial transaction instant messaging platform and updates the session status at the same time.

[0094] In one embodiment of the present application, the first interactive interface is stored in the session management and natural language processing module and provided to the internal transaction system for calling; the first interactive interface includes basic parameters, static check parameters, inquiry parameters and other parameters.

[0095] The interactive interface, as the basic information transmission interface, is based on the HTTP protocol and uses the POST method. The request parameters of this interface mainly include basic parameters, static check parameters, inquiry parameters and other parameters, and the parameters of each part have different application scopes.

[0096] The first interface is configured in the session management and natural language processing module, and is mainly provided to the internal transaction system of the financial institution for calling. It can be understood that the internal transaction system is the caller, and the session management and natural language processing module is the called party.

[0097] The basic parameters mainly include the session ID, whether to transfer to manual operation (when the trader actively intervenes to transfer to manual operation), the timeout flag, and the chat message. They are mainly used to store the basic parameters for the conversation, as shown in Table 1.

[0098] Table 1

[0099]

[0100] The session ID (sessionId) refers to the session ID generated by the internal trading system and is the unique identifier for a round of sessions subsequently.

[0101] Whether to transfer to a human operator (when a trader actively intervenes to transfer to a human operator). For example, when it is true, it is a transfer to a human operator, and when it is false, it is not. When it is true, the dialogue management closes the session message.

[0102] Timeout flag. For example, when it is true, the dialogue management closes the session message and returns a timeout prompt message, and the internal trading system will notify the customer of this message.

[0103] The static check parameters mainly include whether the robot starts and stops, whether the trading plan is enabled, whether it is an ideal friend, whether it is the trading time period, whether the black and white list verification passes, and whether the anti-money laundering / anti-fraud verification passes, as shown in Table 2. Through the above static checks such as whether the robot starts and stops, whether the trading plan is enabled, whether it is an ideal friend, whether it is the trading time period, whether the black and white list verification passes, and whether the anti-money laundering / anti-fraud verification passes, it serves as the basis for the compliance check before investing in the financial market.

[0104] Table 2

[0105]

[0106] The inquiry parameters mainly include whether to actively inquire, the actively inquired trading variety (pledge-style repurchase), the trading direction of the inquiring party, the lower limit of the actively inquired trading term, the upper limit of the actively inquired trading term, the actively inquired trading amount, the actively inquired clearing speed, the actively inquired type of pledged securities, etc., as shown in Table 3.

[0107] Table 3

[0108]

[0109] The other parameters mainly include the inquiry timeout time. The user can set the inquiry timeout time in the trading system and send this timeout time to the robot session management in the form of interface parameters, so as to prevent no response or expired response during long-term inquiries and reduce the usage rate of machine resources. As shown in Table 4.

[0110] Table 4

[0111]

[0112] In one embodiment of the present application, the second interaction interface is stored in the internal trading system and provided to the session management and natural language processing module for invocation; the trading elements of the second interaction interface include session ID, quotation direction, repurchase term, trading amount, type of pledged securities, type of repurchase interest rate, whether to conduct credit check, issuer name and quota list, and whether to actively inquire. The second interaction interface mainly facilitates the data invocation for post-investment management in the later stage.

[0113] The second interaction interface is a trading element check interface, which is based on the HTTP protocol and uses the POST method. This interface is mainly provided to the session management and natural language processing module for invocation, and the session management and natural language processing module of the dialogue robot generates a session according to the trading element check results obtained by the invocation. The second interface is configured in the internal trading system of financial institutions and is mainly provided to the session management and natural language processing module for invocation. The session management and natural language processing module is the calling party, and the trading system is the called party.

[0114] The request parameter fields of the trading element check interface are shown in Table 5.

[0115] Table 5

[0116]

[0117]

[0118] The embodiment of the present application further provides a dialogue robot interaction device 500 for pledged repurchase transactions, as Figure 5 shown, which provides a schematic structural diagram of the dialogue robot interaction device for pledged repurchase transactions in the embodiment of the present application. The dialogue robot interaction device 500 for pledged repurchase transactions at least includes: a response module 510 and a sending module 520, where:

[0119] In one embodiment of the present application, the response module 210 is specifically configured to: in response to the inquiry process of the pledged repurchase transaction, generate session content for the dialogue robot according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system. The first interaction interface is used as an information transmission interface, and the second interaction interface is used as a trading element check interface.

[0120] As a dialogue robot for pledged repurchase transactions, it is mainly used to respond to relevant inquiry processes of pledged repurchase transactions, give corresponding conversation content to reply to the inquiry process, and conduct subsequent transaction inquiries and quotations, transaction element inspections, collateral management, transaction risk control, transaction confirmations, etc. according to the inquiry process. Transaction inquiries and quotations, as an important link, can be undertaken by the dialogue robot. And in the subsequent process, confirm transaction risks, check transaction elements, and manage the collateral associated with pledged repurchase transactions. It can be understood that the dialogue robot based on pledged repurchase transactions can realize automatic dialogue transactions for pledged repurchase transactions, help traders automatically process steps such as inquiries, quotations, and confirmations related to pledged repurchase, and reduce the manual burden on traders.

[0121] A first interaction interface is set in the session management and natural language processing module, and a second interaction interface is set in the internal trading system. Through the first interaction interface and the second interaction interface, conversation content for the dialogue robot can be generated. Specifically, the first interaction interface serves as an information transmission interface to achieve basic calls and transmissions, and the second interaction interface serves as a transaction element inspection interface to implement transaction-related element inspections to ensure transaction security.

[0122] In an embodiment of the present application, the sending module 520 is specifically configured to: send the conversation content through a financial trading instant messaging platform.

[0123] The financial trading instant messaging platform is a well-known and common API interface in the art. Through the financial trading instant messaging platform, the generated conversation content can be sent to the other party (the repurchase party or the reverse repurchase party) of the pledged repurchase transaction.

[0124] In an embodiment of the present application, the response module 510 is further configured to:

[0125] In response to the active inquiry process of the pledged repurchase transaction, start the Robot service in the internal trading system;

[0126] According to the Robot service, call the first interaction interface, generate a first POST request and send it to the session management and natural language processing module. The first POST request carries at least an active inquiry identifier and active inquiry parameters;

[0127] Call the first interaction interface to receive the active inquiry conversation generated in response to the first POST request, and generate an active inquiry message to be pushed to the financial trading instant messaging platform.

[0128] In an embodiment of the present application, the response module 510 is further configured to:

[0129] In response to the process of receiving an inquiry for a pledged repurchase transaction, a notification message is sent to the Robot service in the internal trading system;

[0130] According to the Robot service, the Risk service in the internal trading system is started, a second POST request is generated and sent to the session management and natural language processing module, and the second POST request carries at least static inspection results and a request text;

[0131] The received inquiry speech generated by the second POST request is received, and a received inquiry message is generated and pushed to the financial trading instant messaging platform.

[0132] In an embodiment of the present application, the response module 510 is further configured to:

[0133] Perform corresponding static inspections according to the Robot service;

[0134] If the static inspection passes, the internal trading system initiates the second POST request by calling the first interaction interface, and the second POST request is used to request the session management and natural language processing module to generate a reply speech for receiving an inquiry.

[0135] In an embodiment of the present application, the response module 510 is further configured to:

[0136] The session management and natural language processing module is called through the second interaction interface to perform transaction element inspections, and the inspection results are returned to the session management and natural language processing module according to the second interaction interface, so that the session management and natural language processing module generates corresponding reply speeches according to the inspection results of the second interaction interface, and at the same time, the interface return of the first interaction interface is performed;

[0137] The internal trading system obtains a return result through the first interaction interface, pushes the reply speech for receiving an inquiry to the financial trading instant messaging platform, and updates the session status at the same time.

[0138] In an embodiment of the present application, the first interaction interface is stored in the session management and natural language processing module and provided for the internal trading system to call;

[0139] The first interaction interface includes basic parameters, static inspection parameters, inquiry parameters, and other parameters.

[0140] In an embodiment of the present application, the second interaction interface is stored in the internal trading system and provided for the session management and natural language processing module to call;

[0141] The transaction elements of the second interaction interface include session ID, quote direction, repurchase term, transaction amount, type of pledged securities, type of repurchase interest rate, whether to conduct credit check, issuer name and quota list, and whether to actively inquire.

[0142] It can be understood that the above-mentioned dialogue robot interaction device for pledged repurchase transactions can implement each step of the dialogue robot interaction method for pledged repurchase transactions provided in the foregoing embodiments. The relevant explanations regarding the transaction reconciliation method are applicable to the dialogue robot interaction device for pledged repurchase transactions and will not be elaborated here.

[0143] Figure 6 It is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 6 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0144] The processor, network interface, and memory can be interconnected through an internal bus. The internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 6 only a bidirectional arrow is used in [the figure] to represent it, but it does not mean that there is only one bus or one type of bus.

[0145] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0146] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a dialogue robot interaction device for pledged repurchase transactions at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0147] In response to the inquiry process of the pledged repurchase transaction, session content for the chatbot is generated according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system. The first interaction interface is used as an information transmission interface, and the second interaction interface is used as a trading element check interface;

[0148] Send the session content through the financial trading instant messaging platform.

[0149] The above as in this application Figure 1 The method executed by the chatbot interaction device for the pledged repurchase transaction disclosed in the embodiments shown in this application can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or the instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of this application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0150] The electronic device can also execute Figure 1 the method executed by the chatbot interaction device for the pledged repurchase transaction in, and implement the functions of the chatbot interaction device for the pledged repurchase transaction in the embodiments shown in Figure 1 This application will not elaborate on this here.

[0151] An embodiment of the present application also provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions that, when executed by an electronic device including a plurality of application programs, enable the electronic device to execute Figure 1 the method executed by the dialogue robot interaction device in the illustrated embodiment of the pledged repurchase transaction, and specifically used to execute:

[0152] In response to the inquiry process of the pledged repurchase transaction, generate session content for the dialogue robot according to the first interaction interface in the session management and natural language processing module and the second interaction interface in the internal trading system, where the first interaction interface is used as an information transmission interface, and the second interaction interface is used as a trading element check interface;

[0153] Send the session content through the financial transaction instant messaging platform.

[0154] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention 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.

[0155] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. 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 a device for realizing the specified function in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0156] 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 product including an instruction device, and the instruction device realizes the specified function in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0157] 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 steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 steps for the functions specified in one block or multiple blocks.

[0158] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0159] 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.

[0160] Computer-readable media includes permanent and non-permanent, removable and non-removable media and 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 cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0161] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, commodity or device comprising the element.

[0162] 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.

[0163] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications 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 dialogue robot interaction method for pledge repo transactions, wherein: The method comprises: In response to the inquiry process of the pledged repo transaction, a conversation content for the dialogue robot is generated according to a first interaction interface in the conversation management and natural language processing module and a second interaction interface in the internal transaction system, wherein the first interaction interface is used as an information transmission interface and the second interaction interface is used as a transaction element inspection interface; The conversation content is sent via a financial transaction instant messaging platform.

2. The method of claim 1, wherein: The step of generating conversation content for the conversation robot in response to the inquiry process of the pledged repo transaction according to the first interaction interface in the conversation management and natural language processing module and the second interaction interface in the internal transaction system includes: In response to the active inquiry process of the pledged repo transaction, the Robot service in the internal trading system is started; Invoking the first interactive interface according to the Robot service, generating a first POST request and sending it to the session management and natural language processing module, wherein the first POST request carries at least an active inquiry identifier and an active inquiry parameter; The first interactive interface is called to receive the active inquiry words returned by the first POST request, and an active inquiry message is generated and pushed to the financial transaction instant messaging platform.

3. The method of claim 2, wherein: The step of generating conversation content for the conversation robot in response to the inquiry process of the pledged repo transaction according to the first interaction interface in the conversation management and natural language processing module and the second interaction interface in the internal transaction system includes: In response to the process of receiving an inquiry for a pledged repo transaction, sending a notification message to the Robot service in the internal trading system; Starting the Risk service in the internal trading system according to the Robot service, generating a second POST request and sending it to the session management and natural language processing module, wherein the second POST request carries at least a static check result and a request text; Receive the inquiry receiving words returned by the second POST request, generate an inquiry receiving message and push it to the financial transaction instant messaging platform.

4. The method according to claim 3, further comprising: Perform corresponding static checks according to the Robot service; If the static check passes, the internal transaction system initiates the second POST request by calling the first interactive interface, and the second POST request is used to request the session management and natural language processing module to generate a response script for receiving an inquiry.

5. The method according to claim 4, further comprising: The second interactive interface is called by the session management and natural language processing module to check transaction elements, and the check result is returned to the session management and natural language processing module according to the second interactive interface, so that the session management and natural language processing module generates corresponding reply words according to the check result of the second interactive interface, and simultaneously returns the interface of the first interactive interface; The internal transaction system obtains the return result through the first interactive interface, pushes the reply words of the received inquiry to the financial transaction instant messaging platform and updates the session status at the same time.

6. The method of claim 1, wherein: The first interactive interface is stored in the session management and natural language processing module and provided to the internal transaction system for calling; The first interactive interface includes basic parameters, static check parameters, price inquiry parameters and other parameters.

7. The method of claim 1, wherein: The second interactive interface is stored in the internal transaction system and provided to the session management and natural language processing module for calling; The transaction elements of the second interactive interface include session ID, quotation direction, repurchase period, transaction amount, pledge bond type, repurchase rate type, whether to conduct credit check, issuer name and quotation list, and whether to actively inquire.

8. A dialogue robot interactive device for pledge repurchase transactions, wherein: The device comprises: A response module, used to respond to the inquiry process of the pledged repo transaction, generate a conversation content for the dialogue robot according to the first interaction interface in the conversation management and natural language processing module and the second interaction interface in the internal transaction system, wherein the first interaction interface is used as an information transmission interface and the second interaction interface is used as a transaction element inspection interface; The sending module is used to send the conversation content through the financial transaction instant messaging platform.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 7.

Images