Data processing method and device, equipment, medium and program product

Abstract

The invention provides a data processing method and device, equipment, a medium and a program product, can be applied to the technical field of artificial intelligence, and relates to application of a large model in a financial science and technology scene. The data processing method comprises the following steps: in response to received interaction data of a user, identifying an intention indicated by the interaction data by using a main agent to obtain a target intention; representing a business consultation class in response to the target intention, calling a business consultation agent for executing business consultation by using the main agent, and processing the interaction data by using the business consultation agent to obtain first reply data of the interaction data; representing a business handling class in response to the target intention, and generating a business handling process by utilizing business handling data obtained by interaction with the user based on the interaction data; wherein the main agent and the business consultation agent are constructed based on a pre-training large model.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, to the application of large models in fintech scenarios, and more specifically to a data processing method, apparatus, device, medium, and program product. Background Technology

[0002] In the relevant technology, when customers go to offline outlets to handle business, they need to submit paper materials at the manual window, and relevant staff will verify and enter the information to process the relevant business processes. The operation efficiency is low and the customer experience is poor. Summary of the Invention

[0003] In view of the above problems, this application provides data processing methods, apparatus, devices, media and program products.

[0004] According to a first aspect of this application, a data processing method is provided, comprising: in response to receiving user interaction data, using a main intelligent agent to identify the intent indicated by the interaction data to obtain a target intent; in response to the target intent representing a business consultation class, using the main intelligent agent to invoke a business consultation intelligent agent for performing business consultation, and using the business consultation intelligent agent to process the interaction data to obtain first response data of the interaction data; in response to the target intent representing a business processing class, using business processing data obtained by interacting with the user based on the interaction data to generate a business processing flow; wherein the main intelligent agent and the business consultation intelligent agent are constructed based on a pre-trained large model.

[0005] According to an embodiment of this application, the above-mentioned processing of the interaction data by the business consultation intelligent agent to obtain the first response data of the interaction data includes: the business consultation intelligent agent accessing a preset database in response to the interaction data belonging to a preset business consultation scope to obtain knowledge data matching the interaction data; and generating the first response data of the interaction data based on the knowledge data and the interaction data using a pre-trained large model configured by the business consultation intelligent agent.

[0006] According to an embodiment of this application, the above-mentioned generation of the first response data of the interaction data based on the knowledge data and the interaction data using the pre-trained large model configured by the business consultation agent includes: generating a first prompt word using the business consultation agent based on the knowledge data and the interaction data; and processing the first prompt word using the pre-trained large model configured by the business consultation agent to obtain the first response data of the interaction data.

[0007] According to an embodiment of this application, the above-mentioned method of accessing a preset database using the business consulting agent to obtain knowledge data matching the interaction data includes: obtaining an interaction vector based on the interaction data using a retrieval module configured in the business consulting agent; accessing the preset database using the retrieval module configured in the business consulting agent; and determining knowledge data matching the interaction vector from the preset database based on the interaction vector.

[0008] According to an embodiment of this application, the method further includes: generating a second prompt word based on the interaction data using the business consultation agent; and processing the second prompt word using a pre-trained large model configured by the business consultation agent to determine whether the interaction data belongs to or does not belong to the preset business consultation scope.

[0009] According to an embodiment of this application, the above-mentioned method of generating a business processing flow using business processing data obtained by interacting with the user based on the above-mentioned interaction data includes: using the main intelligent agent to call a business processing intelligent agent for performing business processing, wherein the business processing intelligent agent is constructed based on the above-mentioned pre-trained large model; using the business processing intelligent agent to interact with the user based on the above-mentioned interaction data to obtain the above-mentioned business processing data; and using the business processing intelligent agent to generate the above-mentioned business processing flow based on the above-mentioned business processing data.

[0010] According to an embodiment of this application, the above-mentioned business processing intelligent agent generates the above-mentioned business processing flow based on the above-mentioned business processing data, including: using the above-mentioned business processing intelligent agent to determine a business processing template that matches the above-mentioned business processing data; using the above-mentioned business processing intelligent agent to generate a third prompt word based on the above-mentioned business processing template and the above-mentioned business processing data; and using a pre-trained large model configured by the above-mentioned business processing intelligent agent to process the above-mentioned third prompt word to obtain the above-mentioned business processing flow.

[0011] According to an embodiment of this application, the aforementioned business processing data includes business processing sub-data corresponding to each of multiple business processing elements; wherein, the process of obtaining the business processing data by interacting with the user based on the aforementioned interaction data using the aforementioned business processing intelligent agent includes: determining at least one business processing element based on the aforementioned interaction data using the aforementioned business processing intelligent agent; repeatedly performing the following operations until obtaining the business processing sub-data of each of the multiple business processing elements; determining a target business processing element from the aforementioned at least one business processing element; generating a fourth prompt word using the aforementioned business processing intelligent agent based on the interaction data associated with the aforementioned target business processing element and the aforementioned target business processing element; processing the aforementioned fourth prompt word using a pre-trained large model configured by the aforementioned business processing intelligent agent to generate query data for interacting with the aforementioned user; and obtaining the business processing sub-data corresponding to the aforementioned target business processing element based on the aforementioned second response data generated by the user based on the aforementioned query data using the aforementioned business processing intelligent agent.

[0012] According to embodiments of this application, the above-mentioned method of using a primary intelligent agent to identify the intent indicated by the interaction data and obtain the target intent includes: using the primary intelligent agent to generate a fifth prompt word based on the interaction data; and using a pre-trained large model configured by the primary intelligent agent to process the fifth prompt word to obtain a target intent representing the business consultation category or the business processing category. According to embodiments of this application, the sensitive word detection results of at least one of the interaction data, the first reply data, the business processing data, or the business processing flow indicate that the detection has passed; the sensitive word detection result of the interaction data is obtained by performing sensitive word detection on the interaction data using a risk detection module configured by the primary intelligent agent; the sensitive word detection result of the first reply data is obtained by performing sensitive word detection on the first reply data using a risk detection module configured by the primary intelligent agent; the sensitive word detection result of the business processing data is obtained by performing sensitive word detection on the business processing data using a risk detection module configured by the primary intelligent agent; and the sensitive word detection result of the business processing flow is obtained by performing sensitive word detection on the business processing flow using a risk detection module configured by the primary intelligent agent.

[0013] According to an embodiment of this application, the method further includes: using the sensitive word detection results of the main intelligent agent in response to the interaction data, the first reply data, the business processing data, or the business processing procedure to characterize the detection failure; using the intervention module configured in the main intelligent agent to obtain the risk type of the interaction data, the first reply data, the business processing data, or the business processing procedure based on the interaction data, the first reply data, the business processing data, or the business processing procedure; and using the intervention module configured in the main intelligent agent to generate a risk intervention result based on the risk type.

[0014] A second aspect of this application provides a data processing apparatus, comprising: an intent recognition module, configured to, in response to receiving user interaction data, use a main intelligent agent to recognize the intent indicated by the interaction data to obtain a target intent; a consultation module, configured to, in response to the target intent representing a business consultation class, use the main intelligent agent to call a business consultation intelligent agent for performing business consultation, and use the business consultation intelligent agent to process the interaction data to obtain first response data of the interaction data; and a business processing module, configured to, in response to the target intent representing a business processing class, use business processing data obtained from interacting with the user based on the interaction data to generate a business processing flow; wherein the main intelligent agent and the business consultation intelligent agent are constructed based on a pre-trained large model.

[0015] A third aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0016] A fourth aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0017] The fifth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0018] According to the embodiments of this application, the main intelligent agent identifies the intent indicated by the user's interaction data, thus determining the target intent from the user's interaction data. This reduces the complexity of subsequent processing. Furthermore, when the target intent represents a business consultation, the main intelligent agent invokes a business consultation intelligent agent; when the target intent represents a business processing, the main intelligent agent interacts with the user based on business processing data to generate a business processing flow. The main intelligent agent, following a preset binary search strategy, invokes the corresponding intelligent agent or flow for processing, avoiding resource waste caused by a single intelligent agent processing across domains. Moreover, by automatically generating a business processing flow based on the business processing data obtained from user interaction with the interaction data, business processing efficiency is improved while eliminating cumbersome processing steps, enhancing user experience and reducing the workload of relevant staff. Attached Figure Description

[0019] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0020] Figure 1 This illustration schematically depicts an application scenario of the data processing method and apparatus according to embodiments of this application.

[0021] Figure 2 A flowchart illustrating a data processing method according to an embodiment of this application is shown schematically.

[0022] Figure 3 A detailed flowchart illustrating a data processing method according to an embodiment of this application is shown schematically.

[0023] Figure 4 This schematic diagram illustrates a structural block diagram of a data processing apparatus according to an embodiment of the present application;

[0024] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a data processing method according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0026] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0027] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0028] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0029] In the technical solution of this application, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0030] In scenarios involving automated decision-making using personal information, the methods, devices, and systems provided in this application all offer users corresponding entry points for choosing to agree to or reject the automated decision-making results. If the user chooses to reject, the process proceeds to the expert decision-making stage. Here, "automated decision-making" refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests, or economic, health, and credit status through computer programs, and then making a decision. Here, "expert decision-making" refers to the activity of making decisions by personnel who specialize in a particular field, possess specialized experience, knowledge, and skills, and have reached a certain level of professional expertise.

[0031] With the rapid development of large-scale artificial intelligence models, the convenience, flexibility, and immediacy of user services across various industries, scenarios, and systems have been significantly improved. However, in these technologies, when customers visit physical branches to conduct business, they still require one-on-one service from staff, resulting in low operational efficiency and a poor customer experience.

[0032] In view of this, embodiments of this application provide a data processing method, the method comprising: in response to receiving user interaction data, using a main intelligent agent to identify the intent indicated by the interaction data to obtain a target intent; in response to the target intent representing a business consultation class, using the main intelligent agent to call a business consultation intelligent agent for performing business consultation, and using the business consultation intelligent agent to process the interaction data to obtain first response data of the interaction data; in response to the target intent representing a business processing class, using business processing data obtained from interacting with the user based on the interaction data to generate a business processing flow; wherein, the main intelligent agent and the business consultation intelligent agent are constructed based on a pre-trained large model.

[0033] Figure 1 The illustration shows an application scenario of the data processing method and apparatus according to embodiments of this application.

[0034] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0035] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0036] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0037] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0038] It should be noted that the data processing method provided in the embodiments of this application can generally be executed by server 105. Correspondingly, the data processing device provided in the embodiments of this application can generally be located in server 105. The data processing method provided in the embodiments of this application can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the data processing device provided in the embodiments of this application can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0039] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0040] The following will be based on Figure 1 The described scene, through Figures 2-3 The data processing method according to the embodiments of this application will be described in detail.

[0041] Figure 2 A flowchart illustrating a data processing method according to an embodiment of this application is shown.

[0042] like Figure 2 As shown, the data processing method of this embodiment includes operations S210 to S230.

[0043] In operation S210, in response to receiving user interaction data, the main agent identifies the intent indicated by the interaction data and obtains the target intent.

[0044] According to the embodiments of this application, when a user arrives at an offline branch to conduct business, the first terminal device 101, the second terminal device 102, and the third terminal device 103 (hereinafter referred to as terminals for ease of description) can actively interact with the user to obtain the user's interaction data.

[0045] According to the embodiments of this application, multiple options can be displayed to the user through the terminal, and the user's target intent can be determined based on the user's selection of the options.

[0046] According to the embodiments of this application, the user's interaction data may include voice data or text data. When the interaction data is voice data, it can be converted into text data by ASR (Automatic Speech Recognition) technology for further processing.

[0047] In operation S220, in response to the target intent characterization business consultation class, the main agent calls the business consultation agent used to perform the business consultation, and the business consultation agent processes the interaction data to obtain the first response data of the interaction data.

[0048] For example, if a user's interaction data is "How many bank cards do I have?", the main intelligent agent will identify the target intent as a business inquiry and call the business inquiry intelligent agent. The business inquiry intelligent agent will generate the first response data based on the aforementioned user interaction data, such as "You have X bank cards under your name" or "We recommend the 'My Account' function for you, you can click to apply".

[0049] In operation S230, in response to the target intent characterization of the business processing class, a business processing flow is generated using business processing data obtained from interaction with the user based on interactive data.

[0050] Among them, the main intelligent agent and the business consulting intelligent agent are constructed based on a pre-trained large model.

[0051] According to embodiments of this application, the aforementioned pre-trained large model can be, for example, a large language model.

[0052] According to the embodiments of this application, users can be guided to conduct business by preset guidance data. For example, when a user wants to deposit XXX yuan, the terminal can first confirm the account-related data with the customer and guide the user to enter the password. After the user confirms, the deposit amount can be further determined to guide the user to complete the deposit.

[0053] According to the embodiments of this application, the main intelligent agent identifies the intent indicated by the user's interaction data, thus determining the target intent from the user's interaction data. This reduces the complexity of subsequent processing. Furthermore, when the target intent represents a business consultation, the main intelligent agent invokes a business consultation intelligent agent; when the target intent represents a business processing, the main intelligent agent interacts with the user based on business processing data to generate a business processing flow. The main intelligent agent, following a preset binary search strategy, invokes the corresponding intelligent agent or flow for processing, avoiding resource waste caused by a single intelligent agent processing across domains. Moreover, by automatically generating a business processing flow based on the business processing data obtained from user interaction with the interaction data, business processing efficiency is improved while eliminating cumbersome processing steps, enhancing user experience and reducing the workload of relevant staff.

[0054] According to the embodiments of this application, the above-mentioned use of a business consultation intelligent agent to process interactive data and obtain the first response data of the interactive data includes: using the business consultation intelligent agent to respond to the interactive data belonging to a preset business consultation scope, accessing a preset database to obtain knowledge data matching the interactive data; and using a pre-trained large model configured by the business consultation intelligent agent to generate the first response data of the interactive data based on the knowledge data and the interactive data.

[0055] According to the embodiments of this application, the aforementioned preset database stores knowledge data related to consulting services. For example, when a user asks the terminal "What is my credit card billing date?", the business consulting agent will immediately access the preset database, retrieve the knowledge data associated with the user's card number, and input the knowledge data and interaction data together into the pre-trained large model to obtain the first response data as "Your credit card billing date is the Xth of each month".

[0056] According to the embodiments of this application, by querying a preset database, knowledge data matching the interaction data can be obtained, which can ensure that the pre-trained large model is based on professional business knowledge, avoid the pre-trained large model from being misled, and ensure the accuracy and reliability of the first response data. Furthermore, the next step will only be carried out if the interaction data falls within the preset business consultation scope, thus ensuring the professionalism of the generated first response data.

[0057] According to an embodiment of this application, the above-mentioned generation of first response data of interactive data based on knowledge data and interaction data using a pre-trained large model configured by the business consultation agent includes: generating a first prompt word using the business consultation agent based on knowledge data and interaction data; and processing the first prompt word using the pre-trained large model configured by the business consultation agent to obtain the first response data of interactive data.

[0058] According to the embodiments of this application, the first prompt word can indicate knowledge data and interaction data. The first prompt word can include content in the knowledge data related to the interaction data. For the example of querying a credit card, the first prompt word can be, for example, "The user's account number is XXXXX, the billing date is the Xth of each month, and the final payment date is X days after the billing date. The user asks what the credit card billing date is, and the prompt word is answered accurately and politely in one sentence, while reminding the user of the final payment date."

[0059] According to the embodiments of this application, by utilizing a business consulting intelligent agent to generate a first prompt word based on knowledge data and interaction data, relatively complex knowledge data and interaction data can be encapsulated into a short first prompt word, maintaining contextual consistency while reducing the inference cost of pre-trained large models.

[0060] According to an embodiment of this application, accessing a preset database using a business consulting agent to obtain knowledge data matching the interaction data includes: using a retrieval module configured in the business consulting agent to obtain an interaction vector based on the interaction data; and using the retrieval module configured in the business consulting agent to access the preset database and, based on the interaction vector, determining knowledge data matching the interaction vector from the preset database.

[0061] According to the embodiments of this application, the above-mentioned interaction vector can be obtained by the retrieval module by extracting features from the interaction data. The preset database stores vectorized knowledge data, and the retrieval module can return the knowledge data that is closest to the interaction vector based on the nearest neighbor search in the preset database.

[0062] According to the embodiments of this application, the above method further includes: using a business consultation agent to generate a second prompt word based on the interaction data; using a pre-trained large model configured by the business consultation agent to process the second prompt word to obtain whether the interaction data belongs to or does not belong to the preset business consultation scope.

[0063] According to an embodiment of this application, the aforementioned second prompt may include user interaction data and a preset judgment template. The preset judgment template is "Please determine whether this question falls under the category of 'business consultation' (yes / no), and only output 'yes' or 'no'." For example, if the user's interaction data is "Can I bring a balloon to ride the subway?", then the generated second prompt may be "User question: Can I bring a balloon to ride the subway? Please determine whether this question falls under the category of 'business consultation' (yes / no), and only output 'yes' or 'no'." The pre-trained large model will then output "no," meaning that the interaction data does not fall under the preset business consultation scope.

[0064] According to the embodiments of this application, by converting user interaction data into discrete labels indicating whether it falls within the scope of business consultation, interaction data that does not fall within the scope of business consultation can be intercepted, thereby reducing hardware resource waste and network overhead. At the same time, the scope of business consultation can be determined by a pre-trained large model, which can cover a variety of different questions, reducing the number of people maintaining keywords and regular expressions and alleviating the workload of relevant staff.

[0065] According to an embodiment of this application, the above-mentioned generation of a business processing flow using business processing data obtained through interaction with the user based on interactive data includes: using a main intelligent agent to call a business processing intelligent agent for executing business processing, wherein the business processing intelligent agent is constructed based on a pre-trained large model; using the business processing intelligent agent to interact with the user based on interactive data to obtain business processing data; and using the business processing intelligent agent to generate a business processing flow based on the business processing data.

[0066] According to the embodiments of this application, the target intent is accurately routed to the business processing intelligent agent based on the pre-trained large model by the main intelligent agent. The business processing intelligent agent interacts with the user based on the interaction data to obtain business processing data and then generates the business processing process. This realizes the fully automated generation from intent recognition to business processing process, reduces the access frequency of relevant personnel, and shortens the business processing time.

[0067] For example, if a user's interaction data is "I want to deposit XXXX yuan into card A", the business processing intelligent agent will first prompt the user to enter the password for card A. After the customer enters the password and successfully verifies it, the business processing intelligent agent will further confirm the card number with the user. After the user confirms the card number, the business processing intelligent agent and the user will interact to confirm the deposit amount, and then generate a business processing flow to make the deposit for the user.

[0068] According to the embodiments of this application, the above-mentioned generation of a business processing flow based on business processing data using a business processing intelligent agent includes: using the business processing intelligent agent to determine a business processing template that matches the business processing data; using the business processing intelligent agent to generate a third prompt word based on the business processing template and the business processing data; and using a pre-trained large model configured by the business processing intelligent agent to process the third prompt word to obtain the business processing flow.

[0069] For example, for bank card application processing data, the corresponding application template could be: "1. Verify user identity information; 2. Determine user contact information; 3. Determine bank card parameters; 4. Set up the account corresponding to the bank card; 5. User confirms agreement and authorization; 6. User signs." The corresponding generated third prompt could be: "You are responsible for guiding the user through the entire bank card opening process. The user needs to bring their ID (with a remaining validity period of ≥30 days) and record the user's contact information and password. ID verification and facial recognition (similarity ≥85% is considered successful) are also required to obtain the user's electronic signature. The bank card applied for by this user is a debit card. The final card issuance process can only be completed after the user reads and checks the agreement and signs their electronic signature." Furthermore, the application agent generates the application process based on the third prompt.

[0070] According to the embodiments of this application, the above-mentioned business processing intelligent agent matches business processing data with a preset business processing template, and then generates a third prompt word based on the matched business processing template. This enables the pre-trained large model to generate the corresponding business processing process only based on the third prompt word, that is, it can only generate the corresponding business processing process within the constraint space, thereby avoiding the pre-trained large model generating different business processing processes when processing the same business processing data, and improving the reliability of the system.

[0071] According to an embodiment of this application, the aforementioned business processing data includes business processing sub-data corresponding to each of multiple business processing elements; wherein, obtaining business processing data by using a business processing intelligent agent to interact with the user based on interactive data includes: using the business processing intelligent agent to determine at least one business processing element based on the interactive data; repeating the following operations until obtaining business processing sub-data for each of the multiple business processing elements: determining a target business processing element from the at least one business processing element; using the business processing intelligent agent to generate a fourth prompt word based on the interactive data associated with the target business processing element and the target business processing element; using a pre-trained large model configured by the business processing intelligent agent to process the fourth prompt word and generate query data for interaction with the user; and using the business processing intelligent agent to respond to receiving second reply data generated by the user based on the query data, and obtaining the business processing sub-data corresponding to the target business processing element based on the second reply data.

[0072] For example, continuing with the bank card application example above, the process of applying for a bank card needs to determine the type of card the user wants to apply for, the user's ID information, and the user's contact information. When the user's interaction data is "I want to apply for a bank card," the business processing elements determined at this time at least include "card type, user's ID information, and user's contact information." For the card type, the generated fourth prompt word could be, for example, "Please confirm whether the user wants to apply for a debit card or a credit card, asking in a polite tone." This would then generate query data such as "Do you want to apply for a credit card or a debit card?" If the user replies "debit card," the business processing sub-data would be "card type is debit card." The aforementioned operation is repeated until the business processing sub-data for each of the multiple business processing elements is obtained, that is, the user's card type, user's ID information, and user's contact information are obtained.

[0073] According to the embodiments of this application, by determining at least one business processing element, and then splitting each business processing element into queries, business processing sub-data corresponding to each business processing element is obtained, ensuring that the business processing sub-data corresponding to each business processing element is collected. At the same time, the query data generated by the pre-trained large model under the constraint of the fourth prompt word has contextual consistency, and the query strategy can be adjusted according to the user's previous answers to reduce redundant questions.

[0074] According to the embodiments of this application, the above-mentioned method of using the main intelligent agent to identify the intent indicated by the interaction data and obtain the target intent includes: using the main intelligent agent to generate a fifth prompt word based on the interaction data; and using a pre-trained large model configured by the main intelligent agent to process the fifth prompt word to obtain a target intent representing a business consultation or business processing type.

[0075] According to the embodiments of this application, the main intelligent agent encapsulates the interactive data into a fifth prompt word and hands it over to a pre-trained large model for processing. In turn, the interactive data is mapped to the target intent of business consultation or business processing, providing a more reliable decision basis for subsequent invocation of the business consultation intelligent agent or processing of business processing data through protected data.

[0076] According to the embodiments of this application, the sensitive word detection result of at least one of the above-mentioned interactive data, first reply data, business processing data, or business processing flow indicates that the detection has passed; the sensitive word detection result of the interactive data is obtained by performing sensitive word detection on the interactive data using the risk detection module configured by the main intelligent agent; the sensitive word detection result of the first reply data is obtained by performing sensitive word detection on the first reply data using the risk detection module configured by the main intelligent agent; the sensitive word detection result of the business processing data is obtained by performing sensitive word detection on the business processing data using the risk detection module configured by the main intelligent agent; the sensitive word detection result of the business processing flow is obtained by performing sensitive word detection on the business processing flow using the risk detection module configured by the main intelligent agent.

[0077] According to the embodiments of this application, in order to ensure the security of services provided by various intelligent agents, this application introduces a risk detection module. This module employs a dual mechanism of real-time automatic screening and manual sampling. It filters sensitive content in real time through a preset sensitive word database and semantic analysis to ensure the security of users' business transactions. Simultaneously, relevant personnel will also conduct random checks on the content output by the business consultation intelligent agent to ensure the security of users' business transactions. If relevant personnel or the real-time automatic screening detects that the content output by the business consultation intelligent agent contains sensitive words, it will be reported to the intervention module configured in the main intelligent agent to further determine the processing method.

[0078] Furthermore, with the user's consent, this application will record the user's interaction data to facilitate subsequent adjustments to the various intelligent agents. It is important to note that user consent or authorization can be obtained before acquiring user interaction data. For example, a request to acquire and save the user's interaction data can be sent before acquiring it. This operation will be performed only if the user consents or authorizes the acquisition of their interaction data.

[0079] According to the embodiments of this application, the above-mentioned use of the main intelligent agent to represent the failure of detection by sensitive words in response to the interaction data, the first reply data, the business processing data, or the business processing process is used to obtain the risk type of each of the interaction data, the first reply data, the business processing data, or the business processing process based on the interaction data, the first reply data, the business processing data, or the business processing process; and the intervention module configured by the main intelligent agent generates a risk intervention result based on the risk type.

[0080] According to embodiments of this application, when sensitive word detection fails in interactive data, the risk intervention result may, for example, be informing the user of the reason for interrupting the main intelligent agent's service and simultaneously generating relevant solutions to inform the relevant user. Alternatively, it may suggest that the user handle the corresponding business manually and simultaneously notify relevant staff.

[0081] According to the embodiments of this application, the above-mentioned risk types may include, for example, sensitive word risk, default risk, and abnormal risk, and different risk types may correspond to different risk intervention results.

[0082] For example, when the main AI detects that the interaction data contains the high-risk phrase "I don't want to repay the money anymore", it can pop up a prompt: "Your statement involves potential default risk, and self-service has been suspended." At the same time, it can generate a solution: "If you need to know about repayment extension or installment plans, please go to any branch to consult the relevant staff."

[0083] According to the embodiments of this application, based on the risk types of business processing data or business processing procedures, the intervention module generates corresponding risk intervention results to ensure the compliance of the system and to promptly block risks in the business processing procedures.

[0084] Figure 3 A detailed flowchart illustrating a data processing method according to an embodiment of this application is shown schematically.

[0085] like Figure 3 As shown, after a user clicks on the terminal, the system first performs a sensitive word check on the interaction data. If a sensitive word is included, the intervention module processes and terminates the process. If no sensitive word is included, the main agent identifies the intent. For business consultations, the business consultation agent matches knowledge data to generate the first response data, performs another sensitive word check, and then displays it to the user. For business processing, the business processing agent collects business processing sub-data element by element through multiple rounds of interaction. At the same time, each round of interaction and the collected business processing sub-data are subjected to sensitive word checks again. After all checks are passed, the business is completed according to the generated business processing flow.

[0086] Based on the above data processing method, this application also provides a data processing apparatus. The following will be combined with... Figure 4 The device is described in detail.

[0087] Figure 4 A schematic block diagram of a data processing apparatus according to an embodiment of this application is shown.

[0088] like Figure 4 As shown, the data processing device 400 in this embodiment includes an intent recognition module 410, an inquiry module 420, and a business processing module 430.

[0089] The intent recognition module 410 is used to respond to received user interaction data, and to use the main intelligent agent to recognize the intent indicated by the interaction data to obtain the target intent. In one embodiment, the intent recognition module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0090] The consultation module 420 is used to respond to the aforementioned target intent characterization business consultation class, utilize the aforementioned main intelligent agent to call the business consultation intelligent agent used to perform business consultation, and utilize the aforementioned business consultation intelligent agent to process the aforementioned interaction data to obtain the first response data of the aforementioned interaction data. In one embodiment, the consultation module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0091] The business processing module 430 is used to respond to the aforementioned target intent representation of the business processing class, and generate a business processing flow using the business processing data obtained from the interaction with the user based on the aforementioned interaction data. The aforementioned main intelligent agent and the aforementioned business consultation intelligent agent are constructed based on a pre-trained large model. In one embodiment, the business processing module 430 can be used to execute the operation S230 described above, which will not be repeated here.

[0092] According to an embodiment of this application, the consultation module 420 includes: an access submodule, used to utilize the business consultation agent to access a preset database in response to the interaction data falling within a preset business consultation scope, and obtain knowledge data matching the interaction data; and a generation submodule, used to utilize a pre-trained large model configured by the business consultation agent to generate first response data for the interaction data based on the knowledge data and the interaction data.

[0093] According to an embodiment of this application, the aforementioned access submodule includes: a first prompt word generation unit, configured to generate a first prompt word using the aforementioned business consultation intelligent agent based on the aforementioned knowledge data and the aforementioned interaction data; and a first processing unit, configured to process the aforementioned first prompt word using a pre-trained large model configured by the aforementioned business consultation intelligent agent to obtain first response data of the aforementioned interaction data.

[0094] According to an embodiment of this application, the above-mentioned generation submodule includes: an interaction vector generation unit, used to obtain an interaction vector based on the interaction data using a retrieval module configured in the above-mentioned business consulting agent; and an access unit, used to access the above-mentioned preset database using a retrieval module configured in the above-mentioned business consulting agent, and determine knowledge data matching the interaction vector from the above-mentioned preset database based on the interaction vector.

[0095] According to an embodiment of this application, the above-mentioned apparatus further includes: a second generation module, used to generate a second prompt word based on the interaction data using the business consultation intelligent agent; and a judgment module, used to process the second prompt word using a pre-trained large model configured by the business consultation intelligent agent to determine whether the interaction data belongs to the preset business consultation scope or does not belong to the preset business consultation scope.

[0096] According to an embodiment of this application, the aforementioned business processing module 430 includes: a business processing invocation submodule, used to invoke a business processing intelligent agent for performing business processing using the aforementioned main intelligent agent, wherein the aforementioned business processing intelligent agent is constructed based on the aforementioned pre-trained large model; a business processing data acquisition submodule, used to interact with the aforementioned user based on the aforementioned interaction data using the aforementioned business processing intelligent agent to obtain the aforementioned business processing data; and a business processing flow generation submodule, used to generate the aforementioned business processing flow based on the aforementioned business processing data using the aforementioned business processing intelligent agent.

[0097] According to an embodiment of this application, the above-mentioned business processing flow generation submodule includes: a template determination unit, used to determine a business processing template that matches the above-mentioned business processing data using the above-mentioned business processing intelligent agent; a third prompt word generation unit, used to generate a third prompt word using the above-mentioned business processing intelligent agent based on the above-mentioned business processing template and the above-mentioned business processing data; and a third processing unit, used to process the above-mentioned third prompt word using a pre-trained large model configured by the above-mentioned business processing intelligent agent to obtain the above-mentioned business processing flow.

[0098] According to an embodiment of this application, the aforementioned business processing data includes business processing sub-data corresponding to each of multiple business processing elements; the aforementioned business processing data acquisition sub-module includes: an element determination unit, used to determine at least one business processing element based on the aforementioned interaction data using the aforementioned business processing intelligent agent; repeating the following operations until the business processing sub-data of each of the aforementioned multiple business processing elements is obtained; a target element determination unit, used to determine a target business processing element from the aforementioned at least one business processing element; a fourth prompt word generation unit, used to generate a fourth prompt word based on the aforementioned interaction data associated with the aforementioned target business processing element and the aforementioned target business processing element using the aforementioned business processing intelligent agent; a fourth processing unit, used to process the aforementioned fourth prompt word using a pre-trained large model configured by the aforementioned business processing intelligent agent to generate inquiry data for interaction with the aforementioned user; and a business processing sub-data generation unit, used to obtain the business processing sub-data corresponding to the aforementioned target business processing element based on the aforementioned second response data generated by the user based on the aforementioned inquiry data in response to the aforementioned business processing intelligent agent.

[0099] According to an embodiment of this application, the intent recognition module 410 includes: a fifth prompt word generation submodule, used to generate a fifth prompt word using the main agent based on the interaction data; and a fifth processing submodule, used to process the fifth prompt word using a pre-trained large model configured by the main agent to obtain a target intent representing the business consultation class or the business processing class.

[0100] According to embodiments of this application, the sensitive word detection results of at least one of the above-mentioned interactive data, the above-mentioned first response data, the above-mentioned business processing data, or the above-mentioned business processing procedure indicate that the detection has passed; the sensitive word detection result of the above-mentioned interactive data is obtained by performing sensitive word detection on the above-mentioned interactive data using the risk detection module configured by the above-mentioned main intelligent agent; the sensitive word detection result of the above-mentioned first response data is obtained by performing sensitive word detection on the above-mentioned first response data using the risk detection module configured by the above-mentioned main intelligent agent; the sensitive word detection result of the above-mentioned business processing data is obtained by performing sensitive word detection on the above-mentioned business processing data using the risk detection module configured by the above-mentioned main intelligent agent; the sensitive word detection result of the above-mentioned business processing procedure is obtained by performing sensitive word detection on the above-mentioned business processing procedure using the risk detection module configured by the above-mentioned main intelligent agent.

[0101] According to an embodiment of this application, the above-mentioned apparatus further includes: a risk type determination module, configured to use the sensitive word detection results of the main intelligent agent in response to the interaction data, the first reply data, the business processing data, or the business processing procedure to characterize the detection failure, and use the intervention module configured in the main intelligent agent to obtain the risk type of the interaction data, the first reply data, the business processing data, or the business processing procedure based on the interaction data, the first reply data, the business processing data, or the business processing procedure; and an intervention result generation module, configured to use the intervention module configured in the main intelligent agent to generate a risk intervention result based on the risk type.

[0102] According to embodiments of this application, any multiple modules among the intent recognition module 410, consultation module 420, and business processing module 430 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of this application, at least one of the intent recognition module 410, consultation module 420, and business processing module 430 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the intent recognition module 410, consultation module 420, and business processing module 430 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0103] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a data processing method according to an embodiment of this application.

[0104] like Figure 5 As shown, an electronic device 500 according to an embodiment of this application includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0105] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0106] According to embodiments of this application, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0107] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0108] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0109] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to enable the computer system to implement the data processing methods provided in the embodiments of this application.

[0110] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0111] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0112] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this application embodiment. According to embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0113] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0115] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A data processing method, characterized in that, The method includes: In response to receiving user interaction data, the main intelligent agent identifies the intent indicated by the interaction data to obtain the target intent; In response to the target intent characterization business consultation class, the main agent calls the business consultation agent used to perform the business consultation, and the business consultation agent processes the interaction data to obtain the first response data of the interaction data; In response to the target intent representing the business processing class, a business processing flow is generated using the business processing data obtained from the interaction with the user based on the interaction data; The main intelligent agent and the business consultation intelligent agent are constructed based on a pre-trained large model.

2. The method according to claim 1, characterized in that, The step of processing the interaction data using the business consultation intelligent agent to obtain the first response data of the interaction data includes: The business consultation agent responds to the interaction data by accessing a preset database to obtain knowledge data that matches the interaction data, since the interaction data falls within a preset business consultation scope. The pre-trained large model configured using the business consultation agent generates the first response data of the interaction data based on the knowledge data and the interaction data.

3. The method according to claim 2, characterized in that, The pre-trained large model configured using the business consultation agent generates first response data for the interaction data based on the knowledge data and the interaction data, including: The business consultation intelligent agent generates a first prompt word based on the knowledge data and the interaction data; The first prompt word is processed using a pre-trained large model configured by the business consultation agent to obtain the first response data of the interaction data.

4. The method according to claim 2, characterized in that, The step of using the business consultation intelligent agent to access a preset database and obtain knowledge data matching the interaction data includes: The retrieval module configured by the business consultation intelligent agent obtains the interaction vector based on the interaction data; The retrieval module configured by the business consultation agent accesses the preset database, and based on the interaction vector, determines the knowledge data that matches the interaction vector from the preset database.

5. The method according to claim 2, characterized in that, The method further includes: The business consultation intelligent agent generates a second prompt word based on the interaction data; The second prompt word is processed using a pre-trained large model configured by the business consultation agent to determine whether the interaction data belongs to or does not belong to the preset business consultation scope.

6. The method according to any one of claims 1 to 5, characterized in that, The step of generating a business processing flow using business processing data obtained through interaction with the user based on the interaction data includes: The main intelligent agent invokes a business processing intelligent agent to perform business processing, the business processing intelligent agent being constructed based on the pre-trained large model; The business processing intelligent agent interacts with the user based on the interaction data to obtain the business processing data; The business processing intelligent agent generates the business processing flow based on the business processing data.

7. The method according to claim 6, characterized in that, The step of generating the business processing flow based on the business processing data using the business processing intelligent agent includes: The business processing intelligent agent is used to determine a business processing template that matches the business processing data. The intelligent agent for handling business transactions generates a third prompt word based on the business transaction template and the business transaction data. The third prompt word is processed using a pre-trained large model configured for the business processing agent to obtain the business processing flow.

8. The method according to claim 6, characterized in that, The business processing data includes business processing sub-data corresponding to each of the multiple business processing elements; The step of using the business processing intelligent agent to interact with the user based on the interaction data to obtain the business processing data includes: Based on the interaction data, the business processing intelligent agent determines at least one business processing element. Repeat the following operations until the business processing sub-data for each of the multiple business processing elements is obtained: Determine the target business processing element from the at least one business processing element; The business processing intelligent agent generates a fourth prompt word based on the interaction data associated with the target business processing element and the target business processing element; The pre-trained large model configured by the business handling agent is used to process the fourth prompt word and generate query data for interaction with the user. The business processing intelligent agent responds to receiving second response data generated by the user based on the inquiry data, and obtains business processing sub-data corresponding to the target business processing element based on the second response data.

9. The method according to any one of claims 1 to 5, characterized in that, The step of using the main intelligent agent to identify the intent indicated by the interaction data to obtain the target intent includes: The main intelligent agent generates a fifth prompt word based on the interaction data; The fifth prompt word is processed using a pre-trained large model configured by the main intelligent agent to obtain the target intent representing the business consultation class or the business processing class.

10. The method according to any one of claims 1 to 5, characterized in that, The sensitive word detection results of at least one of the interactive data, the first response data, the business processing data, or the business processing procedure indicate that the detection has passed. The sensitive word detection result of the interaction data is obtained by performing sensitive word detection on the interaction data using the risk detection module configured by the main intelligent agent. The sensitive word detection result of the first response data is obtained by performing sensitive word detection on the first response data using the risk detection module configured by the main intelligent agent. The sensitive word detection result of the business processing data is obtained by performing sensitive word detection on the business processing data using the risk detection module configured by the main intelligent agent. The sensitive word detection result of the business processing procedure is obtained by performing sensitive word detection on the business processing procedure using the risk detection module configured in the main intelligent agent.

11. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The main intelligent agent responds to the sensitive word detection results of the interaction data, the first response data, the business processing data, or the business processing procedure to characterize the failure of the detection. The intervention module configured in the main intelligent agent obtains the risk type of the interaction data, the first response data, the business processing data, or the business processing procedure based on the interaction data, the first response data, the business processing data, or the business processing procedure. The intervention module configured by the main intelligent agent generates risk intervention results based on the risk type.

12. A data processing apparatus, characterized in that, The device includes: The intent recognition module is used to respond to received user interaction data, and to use the main intelligent agent to recognize the intent indicated by the interaction data to obtain the target intent; The consultation module is used to respond to the target intent characterization business consultation class, use the main intelligent agent to call the business consultation intelligent agent used to perform business consultation, and use the business consultation intelligent agent to process the interaction data to obtain the first response data of the interaction data; The business processing module is used to respond to the target intent characterization business processing class and generate a business processing flow using business processing data obtained by interacting with the user based on the interaction data. The main intelligent agent and the business consultation intelligent agent are constructed based on a pre-trained large model.

13. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 11.

Images