Service processing method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the field of artificial intelligence and the field of financial science and technology, and relates to a service processing method and device based on artificial intelligence, computer equipment and a storage medium. Sending an identity authentication request to the third-party service based on a transport layer security protocol and receiving a returned identity authentication result; if the identity authentication result is that the authentication is passed, extracting user information and encrypted data from the service request, and generating a key acquisition request based on the user information; sending the key acquisition request to the third-party service and receiving a returned target key; decrypting the encrypted data based on the target key to obtain initial data, and executing a read-write operation corresponding to the initial data in a vector database in a confidential computing environment to obtain target vector data; reasoning the target vector data based on the large model to obtain service data; and returning the service data to the user. The data security is effectively ensured by combining the confidential computing environment with the use of the vector database.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and financial technology, and in particular to artificial intelligence-based service processing methods, devices, computer equipment and storage media. Background Art

[0002] With the rapid development of artificial intelligence technology, big models have made breakthrough progress in the field of image and video generation, greatly promoting the practical application of generative AI. By optimizing the step-by-step diffusion process of the traditional diffusion model, big models significantly reduce the time complexity, making it possible to generate high-quality video content in real time. However, this technological advancement also brings new challenges: the generative model is increasingly dependent on high-quality user prompt word data, making the user prompt word data itself a valuable digital asset.

[0003] At present, the privacy protection issues for this type of emerging digital assets are becoming increasingly prominent. Since user prompt word data directly determines the quality and characteristics of the generated content, its confidentiality is crucial to users. However, existing large-scale model application solutions are mostly limited by computing performance and it is difficult to directly integrate efficient privacy protection mechanisms. As a result, the privacy protection of user prompt word data mostly relies on non-technical protocols or agreements, which makes it difficult to fundamentally guarantee the data security of user prompt word data. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a service processing method, device, computer equipment and storage medium based on artificial intelligence, so as to solve the technical problem that existing large-model application solutions are mostly limited by computing performance and it is difficult to directly integrate efficient privacy protection mechanisms, resulting in the privacy protection of user prompt word data mostly relying on non-technical protocols or agreements, and it is difficult to fundamentally guarantee the data security of user prompt word data.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a service processing method based on artificial intelligence, which adopts the following technical solution:

[0006] Receiving a service request input by a user; wherein the service request carries the user information and encrypted data of the user;

[0007] Send an identity authentication request to a preset third-party service based on the transport layer security protocol, and receive the identity authentication result returned by the third-party service;

[0008] If the identity authentication result is authentication passed, extracting the user information and the encrypted data from the service request, and generating a corresponding key acquisition request based on the user information;

[0009] Sending the key acquisition request to the third-party service, and receiving a target key corresponding to the user information returned by the third-party service;

[0010] Decrypting the encrypted data based on the target key to obtain initial data, and performing read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data;

[0011] Performing reasoning processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data;

[0012] The service data is returned to the user.

[0013] Furthermore, the step of sending an identity authentication request to a preset third-party service based on the transport layer security protocol specifically includes:

[0014] Acquire operating environment information, and construct a corresponding operating environment information report based on the operating environment information;

[0015] Constructing the identity authentication request based on the operating environment information report;

[0016] Determine a target transport layer security protocol from a plurality of preset transport layer security protocols;

[0017] The identity authentication request is sent to the third-party service via the target transport layer security protocol.

[0018] Furthermore, the step of obtaining the operating environment information and constructing a corresponding operating environment information report based on the operating environment information specifically includes:

[0019] Obtaining a preset information type; wherein the number of the information types includes multiple;

[0020] Acquire the operating environment information corresponding to each of the information types;

[0021] Building a corresponding structured report based on all the operating environment information;

[0022] Get the preset private key;

[0023] Digitally signing the structured report based on the private key to obtain a corresponding target report;

[0024] The target report is used as the operating environment information report.

[0025] Furthermore, the step of digitally signing the structured report based on the private key to obtain the corresponding target report specifically includes:

[0026] Get the target hash function;

[0027] Processing the structured report based on the target hash function to obtain corresponding summary data;

[0028] Signing the summary data based on the private key to obtain a corresponding signature value;

[0029] The target report is generated based on the structured report and the signature value.

[0030] Furthermore, the step of determining the target transport layer security protocol from the preset multiple transport layer security protocols specifically includes:

[0031] Screening out a first transport layer security protocol having a security vulnerability from the multiple transport layer security protocols;

[0032] Filtering the first transport layer security protocol from the multiple transport layer security protocols to obtain a corresponding second transport layer security protocol;

[0033] Obtaining usage effect evaluation values ​​of each of the second transport layer security protocols, and screening out third transport layer security protocols whose usage effect evaluation values ​​are greater than a preset evaluation threshold from all the second transport layer security protocols;

[0034] Obtaining release time information of each of the third transport layer security protocols;

[0035] Calculate the time difference between the release time information of each of the third transport layer security protocols and the current time respectively;

[0036] A fourth transport layer security protocol with the smallest time difference is selected from all the third transport layer security protocols, and the fourth transport layer security protocol is used as the target transport layer security protocol.

[0037] Furthermore, the step of performing reasoning processing on the target vector data based on the large model in the preset computing environment to obtain corresponding service data specifically includes:

[0038] Invoking the large model in the confidential computing environment;

[0039] Performing inference processing on the target vector data based on the large model to obtain an inference result corresponding to the target vector data;

[0040] The inference result is used as the service data.

[0041] Furthermore, the step of returning the service data to the user specifically includes:

[0042] Using the target key to encrypt the service data to obtain corresponding target service data;

[0043] Obtaining communication information of the user;

[0044] Based on the communication information, target service data is returned to the user.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a service processing device based on artificial intelligence, which adopts the following technical solution:

[0046] A receiving module, used to receive a service request input by a user; wherein the service request carries the user information and encrypted data of the user;

[0047] A first sending module, used to send an identity authentication request to a preset third-party service based on a transport layer security protocol, and receive an identity authentication result returned by the third-party service;

[0048] An extraction module, configured to extract the user information and the encrypted data from the service request if the identity authentication result is authentication passed, and generate a corresponding key acquisition request based on the user information;

[0049] A second sending module, used to send the key acquisition request to the third-party service, and receive a target key corresponding to the user information returned by the third-party service;

[0050] A processing module, configured to decrypt the encrypted data based on the target key to obtain initial data, and to perform read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data;

[0051] An inference module, used for performing inference processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data;

[0052] The returning module is used to return the service data to the user.

[0053] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0054] Receiving a service request input by a user; wherein the service request carries the user information and encrypted data of the user;

[0055] Send an identity authentication request to a preset third-party service based on the transport layer security protocol, and receive the identity authentication result returned by the third-party service;

[0056] If the identity authentication result is authentication passed, extracting the user information and the encrypted data from the service request, and generating a corresponding key acquisition request based on the user information;

[0057] Sending the key acquisition request to the third-party service, and receiving a target key corresponding to the user information returned by the third-party service;

[0058] Decrypting the encrypted data based on the target key to obtain initial data, and performing read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data;

[0059] Performing reasoning processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data;

[0060] The service data is returned to the user.

[0061] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0062] Receiving a service request input by a user; wherein the service request carries the user information and encrypted data of the user;

[0063] Send an identity authentication request to a preset third-party service based on the transport layer security protocol, and receive the identity authentication result returned by the third-party service;

[0064] If the identity authentication result is authentication passed, extracting the user information and the encrypted data from the service request, and generating a corresponding key acquisition request based on the user information;

[0065] Sending the key acquisition request to the third-party service, and receiving a target key corresponding to the user information returned by the third-party service;

[0066] Decrypting the encrypted data based on the target key to obtain initial data, and performing read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data;

[0067] Performing reasoning processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data;

[0068] The service data is returned to the user.

[0069] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0070] The present application first receives a service request input by a user; wherein the service request carries the user information and encrypted data of the user; then, based on the transport layer security protocol, an identity authentication request is sent to a preset third-party service, and an identity authentication result returned by the third-party service is received; if the identity authentication result is authentication passed, the user information and the encrypted data are extracted from the service request, and a corresponding key acquisition request is generated based on the user information; then, the key acquisition request is sent to the third-party service, and a target key corresponding to the user information returned by the third-party service is received; subsequently, the encrypted data is decrypted based on the target key to obtain initial data, and read and write operations corresponding to the initial data are performed in a vector database in a preset confidential computing environment to obtain corresponding target vector data; further, the target vector data is inferred based on a large model in the preset computing environment to obtain corresponding service data; finally, the service data is returned to the user. This application introduces confidential computing technology to confidentialize the key middleware in the large model service, namely the vector database. By storing the user prompt word data in the large model application in the vector database in the confidential computing environment, the confidential computing environment provides additional security protection, which can protect the sensitive data in the vector database from being accessed by unauthorized personnel. By using encryption technology and access control mechanism, the user prompt word data can be effectively prevented from being leaked and illegally accessed, thereby achieving all-round privacy protection for the user prompt word data without affecting the computing performance of the large model, ensuring the privacy and confidentiality of the user prompt word data. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0072] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0073] Figure 2 A flowchart of an embodiment of an artificial intelligence-based service processing method according to the present application;

[0074] Figure 3 is a structural diagram of an embodiment of an artificial intelligence-based service processing device according to the present application;

[0075] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0076] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0077] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0078] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0079] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0080] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0081] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0082] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0083] It should be noted that the artificial intelligence-based service processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based service processing device is generally set in the server / terminal device.

[0084] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0085] Continue to refer Figure 2 , showing a flowchart of an embodiment of an artificial intelligence-based service processing method according to the present application. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted. The artificial intelligence-based service processing method provided in the embodiment of the present application can be applied to any scenario where service processing related to a large model is required, and the artificial intelligence-based service processing method can be applied to products in these scenarios, for example, service processing related to a large model in the field of finance and insurance. The artificial intelligence-based service processing method comprises the following steps:

[0086] Step S201, receiving a service request input by a user; wherein the service request carries the user information and encrypted data of the user.

[0087] In this embodiment, the service processing method based on artificial intelligence is executed on the electronic device (for example Figure 1The server / terminal device shown in the figure) can obtain the service request through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi F i connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wi DeBand) connection, and other wireless connection methods currently known or to be developed in the future. The embodiment of the present application may specifically be a server that provides a large model service, and may also be a service provider. The above-mentioned user information includes the user's name information. A trusted third party (such as a certificate authority or an independent encryption service provider) issues and records a unique key for data encryption for each user, and distributes the key to the user through a secure channel (such as a transport layer security protocol). These keys are only used to encrypt data sent by the user to the server to ensure the security of the data during transmission. Among them, the above-mentioned encrypted data is the data obtained after the user prompt word data is encrypted using the corresponding key locally on the user. User prompt word data (User Prompt Data) is a very important concept in the fields of artificial intelligence (AI) and machine learning (ML), especially in natural language processing (NLP), dialogue systems, recommendation systems and interactive AI applications. These data are usually used to guide the AI ​​model to understand the user's intentions, needs or expectations, so as to provide more personalized and accurate responses. The user prompt word data can be in the form of text input, such as search queries, chat messages, email content, etc. These text data can be used by the AI ​​model to understand the user's intentions, such as querying information, expressing opinions or requesting help. Exemplarily, the user prompt word data can be applied to the dialogue system of an insurance company. The dialogue system uses the text or voice input by the user to identify the user's intentions and generate corresponding responses, thereby improving the user satisfaction of the insurance consulting business. The user prompt word data can also be applied to the recommendation system of an insurance company. The recommendation system analyzes the user's search query and browsing behavior, and can recommend related content or products to improve the user experience and satisfaction, thereby improving the marketing success rate of insurance products. And the user prompt word data can also be applied to the intelligent customer service system of an insurance company. The intelligent customer service system uses the user prompt word data to identify the user's problems and needs and provide automated answers and help. This helps to reduce the labor costs of insurance companies and improve customer service efficiency.

[0088] Step S202: sending an identity authentication request to a preset third-party service based on the transport layer security protocol, and receiving an identity authentication result returned by the third-party service.

[0089] In this embodiment, the third-party service is specifically a trusted third party that has established a transport layer security protocol connection with the server. By establishing a transport layer security protocol connection, the confidentiality and integrity of the data between the server and the third-party service during the communication process can be ensured, and man-in-the-middle attacks can be prevented. Among them, the server sends an identity authentication request to a preset third-party service through the transport layer security protocol, and the identity authentication request contains the operating environment information that the server wants to prove that it is running in a confidential computing environment. After receiving the identity authentication request, the third-party service will check the operating environment information carried in the identity authentication request to ensure that the server is indeed running in a secure confidential computing environment, and after determining that the server has passed the identity authentication, it will return the authentication result of the authentication to the server. In addition, the specific implementation process of sending an identity authentication request to a preset third-party service based on the transport layer security protocol will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0090] Step S203: If the identity authentication result is authentication passed, the user information and the encrypted data are extracted from the service request, and a corresponding key acquisition request is generated based on the user information.

[0091] In this embodiment, the service request can be parsed to extract the user information and the encrypted data from the service request. After the server passes the identity authentication, a request for obtaining the user's key can be sent to a third party. The key acquisition request is a request that carries the user's user information.

[0092] Step S204: sending the key acquisition request to the third-party service, and receiving the target key corresponding to the user information returned by the third-party service.

[0093] In this embodiment, after receiving the key acquisition request, the third-party service confirms whether the server has the authority to access the user's key. For example, it may involve checking the identity of the server, the service agreement, and the user authorization information. If it is verified that the server has the authority to access the user's key, the third-party service will securely send the user's matching key, that is, the above-mentioned target key, to the server through the transport layer security protocol connection. Among them, the user can cancel the key authorization on his own, so that even if the server saves the key data, it cannot be used, thereby improving the security of the key data.

[0094] Step S205, decrypt the encrypted data based on the target key to obtain initial data, and perform read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data.

[0095] In this embodiment, the server deploys the service interface and its vector database for recording user data in a confidential computing environment. The vector database application in the confidential computing environment needs to establish a transport layer security protocol connection with a trusted third party through a remote authentication transport layer security protocol based on a bidirectional transport layer security protocol across confidential computing platforms, prove to the trusted third-party service that it is running in a confidential computing environment, and prove that the running content does not contain any program that leaks user privacy through a hash signature of the running content. Specifically, hardware-level security features such as Intel SGX (SoftwareGuard Extensions) or AMD SEV (Secure Encrypted Virtualization) can be used to ensure the confidentiality and integrity of code and data during execution. In addition, the vector database deployed in the confidential computing environment is used to store the vector embedding results generated after the user input data is processed by the model, which can reduce repeated calculations and directly process sensitive data in a secure environment. Specifically, after receiving the target key, the server uses the target key to decrypt the encrypted data sent by the user and obtain the initial data. Then, the read and write operations corresponding to the initial data are performed in the vector database in the confidential computing environment to obtain the above-mentioned target vector data. By converting the initial data into vectors, the vector database can use the distance or similarity between vectors to quickly locate data, thereby greatly improving the accuracy and efficiency of data search. In addition, the vector database saves the vector data corresponding to the user prompt word data entered by the user. Compared with directly saving the user prompt word data entered by the user, saving vector data can avoid repeated embedding operations and directly input large model interactions, effectively improving the efficiency of large model services. In addition, the vector database itself can be deployed in a confidential computing environment, and a third-party service independent of the user and the server can provide security authentication services, effectively ensuring the privacy and confidentiality of the user prompt word data and protecting user privacy.

[0096] Step S206, performing inference processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data.

[0097] In this embodiment, the above-mentioned specific implementation process of inferring the target vector data based on the large model in the preset computing environment to obtain the corresponding service data will be further described in detail in the subsequent specific embodiments of this application and will not be elaborated here.

[0098] Step S207: returning the service data to the user.

[0099] In this embodiment, the specific implementation process of returning the service data to the user will be described in further detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0100] This application introduces confidential computing technology to confidentialize the key middleware in the large model service, namely the vector database. By storing the user prompt word data in the large model application in the vector database in the confidential computing environment, the confidential computing environment provides additional security protection, which can protect the sensitive data in the vector database from being accessed by unauthorized personnel. By using encryption technology and access control mechanism, the user prompt word data can be effectively prevented from being leaked and illegally accessed, thereby achieving all-round privacy protection for the user prompt word data without affecting the computing performance of the large model, ensuring the privacy and confidentiality of the user prompt word data.

[0101] In some optional implementations, the step of sending an identity authentication request to a preset third-party service based on the transport layer security protocol in step S202 includes the following steps:

[0102] Acquire operating environment information, and construct a corresponding operating environment information report based on the operating environment information.

[0103] In this embodiment, the above operating environment information may specifically be information about the operating environment of the confidential computing environment collected by the server in its confidential computing environment. The specific implementation process of obtaining the operating environment information and constructing a corresponding operating environment information report based on the operating environment information will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0104] The identity authentication request is constructed based on the operating environment information report.

[0105] In this embodiment, the identity authentication request is obtained by constructing a request carrying the operating environment information report, wherein the operating environment information report may also be encoded or encapsulated to meet the transmission requirements of the target transport layer security protocol.

[0106] A target transport layer security protocol is determined from a plurality of preset transport layer security protocols.

[0107] In this embodiment, the specific implementation process of determining the target transport layer security protocol from the preset multiple transport layer security protocols will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0108] The identity authentication request is sent to the third-party service via the target transport layer security protocol.

[0109] In this embodiment, after the construction of the identity authentication request is completed, the target transport layer security protocol can be used to securely send the identity authentication request to the third-party service.

[0110] This application obtains the operating environment information and constructs the corresponding operating environment information report based on the operating environment information; then constructs the identity authentication request based on the operating environment information report to achieve fast and intelligent completion of the construction of the identity authentication request, thereby improving the construction efficiency of the identity authentication request. Afterwards, the target transport layer security protocol is determined from a plurality of preset transport layer security protocols; subsequently, the identity authentication request is sent to the third-party service through the target transport layer security protocol to achieve fast, intelligent and secure sending of the identity authentication request to the third-party service, thereby improving the transmission security and transmission standardization of the identity authentication request.

[0111] In some optional implementations of this embodiment, the obtaining of the operating environment information and constructing a corresponding operating environment information report based on the operating environment information includes the following steps:

[0112] Obtain preset information types; wherein the number of the information types includes multiple.

[0113] In this embodiment, the above information type is a type that is pre-set and related to the information of the operating environment of the confidential computing environment in the server. The information type may at least include the hardware platform information type (such as CPU model, support status of the confidential computing environment), software version type (such as operating system version, confidential computing environment version), and code hash type currently executed by the confidential computing environment (such as the hash value of the code in the confidential computing environment).

[0114] Obtain the operating environment information corresponding to each of the information types.

[0115] In this embodiment, the above-mentioned operating environment information may include at least hardware platform information, software version information, and code hash information currently executed by the confidential computing environment.

[0116] A corresponding structured report is constructed based on all the operating environment information.

[0117] In this embodiment, all the acquired operating environment information may be organized into a structured report, namely, the structured report.

[0118] Get the preset private key.

[0119] In this embodiment, the server can obtain the private key for signing from the secure storage of the confidential computing environment. This private key is unique and is only available within the confidential computing environment to ensure that the signature cannot be forged. There is no specific limitation on the data content of the private key, which can be set according to the actual signature requirements.

[0120] Digitally signing the structured report based on the private key to obtain a corresponding target report;

[0121] In this embodiment, the specific implementation process of digitally signing the structured report based on the private key to obtain the corresponding target report will be further described in detail in subsequent specific embodiments of the present application and will not be elaborated on here.

[0122] The target report is used as the operating environment information report.

[0123] The present application obtains the operating environment information corresponding to each of the information types, and constructs a corresponding structured report based on all the operating environment information; then digitally signs the structured report based on the acquired private key to obtain a corresponding target report, and uses the target report as the operating environment information report, so as to quickly and intelligently complete the construction of the operating environment information report corresponding to the operating environment information, thereby improving the construction efficiency and construction intelligence of the operating environment information report.

[0124] In some optional implementations, the digitally signing the structured report based on the private key to obtain the corresponding target report includes the following steps:

[0125] Get the target hash function.

[0126] In this embodiment, there is no specific limitation on the selection of the above-mentioned target hash function, which can be set according to actual business usage requirements. For example, any one of the hash functions such as MD5, SHA-1, SHA-256, etc. can be selected.

[0127] The structured report is processed based on the target hash function to obtain corresponding summary data.

[0128] In this embodiment, after the target hash function is determined, the structured report is processed into a fixed-length summary by using the target hash function to obtain the summary data.

[0129] The summary data is signed based on the private key to obtain a corresponding signature value.

[0130] In this embodiment, after the summary data is obtained, the summary data is encrypted by using the private key, that is, digitally signed, to obtain the signature value.

[0131] The target report is generated based on the structured report and the signature value.

[0132] In this embodiment, the structured report and the signature value may be integrated to obtain corresponding integrated data, and the integrated data may be used as the target report.

[0133] The present application obtains the target hash function, and processes the structured report based on the target hash function to obtain corresponding summary data; then signs the summary data based on the private key to obtain a corresponding signature value; subsequently generates the target report based on the structured report and the signature value, and processes the structured report based on the target hash function and the use of the private key to achieve fast and intelligent generation of the corresponding target report, effectively improving the generation efficiency and generation intelligence of the target report.

[0134] In some optional implementations, determining the target transport layer security protocol from a plurality of preset transport layer security protocols comprises the following steps:

[0135] A first transport layer security protocol having a security vulnerability is screened out from the multiple transport layer security protocols.

[0136] In this embodiment, the above-mentioned multiple transport layer security protocols at least include RATS-TLS (Remote Attestation TLS), TLS1.3, TLS1.2, TLS1.1, SSL 2.0, SSL 3.0, RC4 and other protocols. The above-mentioned first transport layer security protocol refers to a protocol with known security vulnerabilities, such as SSL 2.0, SSL 3.0, RC4 protocols.

[0137] The first transport layer security protocol is filtered from the multiple transport layer security protocols to obtain a corresponding second transport layer security protocol.

[0138] In this embodiment, the filtering process refers to the process of deleting the first transport layer security protocol from the multiple transport layer security protocols. The present application can effectively reduce the risk of service data being attacked by filtering the first transport layer security protocol from the multiple transport layer security protocols to avoid using a transport layer security protocol with security vulnerabilities for data transmission.

[0139] Obtain usage effect evaluation values ​​of each of the second transport layer security protocols, and select third transport layer security protocols whose usage effect evaluation values ​​are greater than a preset evaluation threshold from all the second transport layer security protocols.

[0140] In this embodiment, the user data of the transport layer security protocol can be consulted from the network, and the use effect evaluation value of each second transport layer security protocol can be queried from the user data. The user data may at least include the use effect evaluation value of the transport layer security protocol published by the user. In addition, the value of the evaluation threshold is not specifically limited and can be set according to actual use requirements.

[0141] Obtain release time information of each of the third transport layer security protocols.

[0142] In this embodiment, the release time information refers to the release time of each of the third transport layer security protocols. The format of the release time information can be specifically in the format of year-month-day.

[0143] The time difference between the release time information of each of the third transport layer security protocols and the current time is calculated respectively.

[0144] In this embodiment, the current time is also in the format of year-month-day. For each of the third transport layer security protocols, the time difference between the release time information of each of the third transport layer security protocols and the current time is calculated respectively.

[0145] A fourth transport layer security protocol with the smallest time difference is selected from all the third transport layer security protocols, and the fourth transport layer security protocol is used as the target transport layer security protocol.

[0146] In this embodiment, all the calculated time differences can be numerically compared and compared in ascending order, thereby selecting the specified time difference with the smallest value, and then selecting the fourth transport layer security protocol corresponding to the above specified time difference from all the third transport layer security protocols, and using the fourth transport layer security protocol as the target transport layer security protocol. Among them, the transport layer security protocol with a newer release time usually contains more security features and fixes known vulnerabilities in the old version, so using the transport layer security protocol with a newer release time for data transmission can improve the security of data transmission.

[0147] The present application first filters the first transport layer security protocol with security vulnerabilities from the multiple transport layer security protocols to obtain the second transport layer security protocol; then obtains the use effect evaluation value of each of the second transport layer security protocols, and selects the third transport layer security protocol whose use effect evaluation value is greater than the preset evaluation threshold from all the second transport layer security protocols; then obtains the release time information of each of the third transport layer security protocols, and respectively calculates the time difference between the release time information of each of the third transport layer security protocols and the current time; subsequently selects the fourth transport layer security protocol with the smallest time difference from all the third transport layer security protocols, and uses the fourth transport layer security protocol as the target transport layer security protocol. The present application first filters the first transport layer security protocol from the multiple transport layer security protocols to obtain the second transport layer security protocol, which can avoid using the transport layer security protocol with security vulnerabilities for data transmission, thereby effectively reducing the risk of service data being attacked. Subsequently, the second transport layer security protocol is screened based on the use effect evaluation value and release time information of the transport layer security protocol to obtain the final target transport layer security protocol. Since the target transport layer security protocol is the transport layer security protocol with the best comprehensive processing capability corresponding to the use effect evaluation value and the release time information, the accuracy of determining the target transport layer security protocol is effectively improved. The target transport layer security protocol is subsequently used to send the identity authentication request to the third-party service, which can effectively improve the transmission security of the identity authentication request.

[0148] In some optional implementations of this embodiment, step S206 includes the following steps:

[0149] The large model is invoked in the confidential computing environment.

[0150] In this embodiment, there is no specific limitation on the selection of the above-mentioned large model, and it can be selected according to the actual service requirements. For example, any one of the Transformer model, GPT (Generated Pretrained Transformer) model, and BERT (Bidirectional Encoder Representations from Transformers) model can be selected as the large model. The Transformer model is a deep learning model based on the self-attention mechanism, which is widely used in the field of natural language processing (NLP). It effectively solves the problems of traditional sequence models in dealing with long-distance dependencies through technologies such as multi-head attention mechanism and position encoding. The GPT model is a series of pre-trained language models developed by OpenAI, which has powerful text generation capabilities. With the iteration of versions, the number of parameters and performance of the model are continuously improved. The BERT model is a bidirectional encoding representation model based on Transformer, which learns language representation through pre-training and has achieved excellent performance in multiple NLP tasks. In addition, by using a large model to perform inference processing on the target vector data in a confidential computing environment, the security of the generated service data in the entire service processing flow can be effectively ensured.

[0151] The target vector data is inferred based on the large model to obtain an inference result corresponding to the target vector data.

[0152] In this embodiment, the target vector data is input as a model into the above-mentioned large model, so that the target vector data is inferred by the large model and an inference result corresponding to the target vector data is output.

[0153] The inference result is used as the service data.

[0154] In this embodiment, in addition to using a large model in a confidential computing environment to perform reasoning on the target vector data, a large model can also be used in a general computing environment on the server to perform reasoning on the target vector data. The general computing environment is a computing environment for different confidential computing environments. By using a large model in a general computing environment to perform reasoning on the target vector data, the operating pressure of the confidential computing environment can be effectively reduced, thereby ensuring the operating stability of the confidential computing environment.

[0155] The present application calls the large model in the confidential computing environment; then performs reasoning processing on the target vector data based on the large model to obtain a reasoning result corresponding to the target vector data, and uses the reasoning result as the service data. The present application uses the large model in the confidential computing environment to perform reasoning processing on the target vector data, which can effectively ensure the security of the generated service data in the entire service processing flow.

[0156] In some optional implementations of this embodiment, step S207 includes the following steps:

[0157] The service data is encrypted using the target key to obtain corresponding target service data.

[0158] In this embodiment, after obtaining the service data output by the large model, the service data can be further encrypted using the target key corresponding to the user information returned by the third-party service to obtain the corresponding target service data.

[0159] Acquire the communication information of the user.

[0160] In this embodiment, the communication information may include the user's mobile phone number or email address.

[0161] Based on the communication information, target service data is returned to the user.

[0162] In this embodiment, the communication information is used to send the target service data to the communication terminal corresponding to the user.

[0163] This application encrypts the service data using the target key to obtain the corresponding target service data; then obtains the communication information of the user; and subsequently returns the target service data to the user based on the communication information. After obtaining the service data output by the large model, this application will further use the received target key to encrypt the service data to obtain the target service data, and then return the target service data to the user based on the obtained user's communication information. By encrypting the service data using the target key corresponding to the user and then returning it to the user, the transmission security of the service data can be effectively ensured, and the transmission intelligence of the service data is improved.

[0164] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0165] It should be emphasized that in order to further ensure the privacy and security of the above service data, the above service data can also be stored in a blockchain node.

[0166] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0167] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0168] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0169] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0170] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0171] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a service processing device based on artificial intelligence. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0172] like Figure 3 As shown, the service processing device 300 based on artificial intelligence described in this embodiment includes: a receiving module 301, a first sending module 302, an extraction module 303, a second sending module 304, a processing module 305, an inference module 306 and a return module 307. Among them:

[0173] The receiving module 301 is used to receive a service request input by a user; wherein the service request carries the user information and encrypted data of the user;

[0174] The first sending module 302 is used to send an identity authentication request to a preset third-party service based on the transport layer security protocol, and receive an identity authentication result returned by the third-party service;

[0175] The extraction module 303 is used to extract the user information and the encrypted data from the service request if the identity authentication result is authentication passed, and generate a corresponding key acquisition request based on the user information;

[0176] The second sending module 304 is used to send the key acquisition request to the third-party service, and receive the target key corresponding to the user information returned by the third-party service;

[0177] A processing module 305 is used to decrypt the encrypted data based on the target key to obtain initial data, and perform read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data;

[0178] An inference module 306 is used to perform inference processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data;

[0179] The returning module 307 is used to return the service data to the user.

[0180] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0181] In some optional implementations of this embodiment, the first sending module 302 includes:

[0182] A first construction submodule is used to obtain operating environment information and construct a corresponding operating environment information report based on the operating environment information;

[0183] A second construction submodule, configured to construct the identity authentication request based on the operating environment information report;

[0184] A first determination submodule is used to determine a target transport layer security protocol from a plurality of preset transport layer security protocols;

[0185] The sending submodule is used to send the identity authentication request to the third-party service through the target transport layer security protocol.

[0186] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0187] In some optional implementations of this embodiment, the first construction submodule includes:

[0188] A first acquisition unit is used to acquire a preset information type; wherein the number of the information types includes multiple;

[0189] A second acquisition unit, used to acquire the operating environment information corresponding to each of the information types;

[0190] A construction unit, used to construct a corresponding structured report based on all the operating environment information;

[0191] A third obtaining unit, used to obtain a preset private key;

[0192] A signing unit, configured to digitally sign the structured report based on the private key to obtain a corresponding target report;

[0193] The first determining unit is configured to use the target report as the operating environment information report.

[0194] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0195] In some optional implementations of this embodiment, the signature unit includes:

[0196] An acquisition subunit is used to acquire a target hash function;

[0197] A processing subunit, configured to process the structured report based on the target hash function to obtain corresponding summary data;

[0198] A signature subunit, used to sign the summary data based on the private key to obtain a corresponding signature value;

[0199] A generating subunit is used to generate the target report based on the structured report and the signature value.

[0200] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0201] In some optional implementations of this embodiment, the first determining submodule includes:

[0202] A first screening unit, configured to screen out a first transport layer security protocol having a security vulnerability from the plurality of transport layer security protocols;

[0203] A filtering unit, configured to filter the first transport layer security protocol from the plurality of transport layer security protocols to obtain a corresponding second transport layer security protocol;

[0204] A second screening unit is used to obtain the use effect evaluation value of each of the second transport layer security protocols, and screen out the third transport layer security protocol whose use effect evaluation value is greater than a preset evaluation threshold from all the second transport layer security protocols;

[0205] A fourth acquisition unit, used to acquire the release time information of each of the third transport layer security protocols;

[0206] A calculation unit, used to respectively calculate the time difference between the release time information of each of the third transport layer security protocols and the current time;

[0207] The second determining unit is used to select a fourth transport layer security protocol with the smallest time difference from all the third transport layer security protocols, and use the fourth transport layer security protocol as the target transport layer security protocol.

[0208] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0209] In some optional implementations of this embodiment, the reasoning module 306 includes:

[0210] A calling submodule, used for calling the large model in the confidential computing environment;

[0211] An inference submodule, used for performing inference processing on the target vector data based on the large model to obtain an inference result corresponding to the target vector data;

[0212] The second determining submodule is used to use the inference result as the service data.

[0213] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0214] In some optional implementations of this embodiment, the returning module 307 includes:

[0215] An encryption submodule, used to encrypt the service data using the target key to obtain corresponding target service data;

[0216] An acquisition submodule, used to acquire the communication information of the user;

[0217] The return submodule is used to return the target service data to the user based on the communication information.

[0218] In this embodiment, the operations performed by the above modules or units correspond one-to-one to the steps of the artificial intelligence-based service processing method in the aforementioned implementation mode, and will not be repeated here.

[0219] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0220] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0221] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0222] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of a service processing method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0223] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based service processing method.

[0224] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0225] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the artificial intelligence-based service processing method as described above.

[0226] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0227] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A service processing method based on artificial intelligence, characterized in that: The steps include: Receiving a service request input by a user; wherein the service request carries the user information and encrypted data of the user; Send an identity authentication request to a preset third-party service based on the transport layer security protocol, and receive the identity authentication result returned by the third-party service; If the identity authentication result is authentication passed, extracting the user information and the encrypted data from the service request, and generating a corresponding key acquisition request based on the user information; Sending the key acquisition request to the third-party service, and receiving a target key corresponding to the user information returned by the third-party service; Decrypting the encrypted data based on the target key to obtain initial data, and performing read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data; Performing reasoning processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data; The service data is returned to the user.

2. The service processing method based on artificial intelligence according to claim 1, characterized in that: The step of sending an identity authentication request to a preset third-party service based on the transport layer security protocol specifically includes: Acquire operating environment information, and construct a corresponding operating environment information report based on the operating environment information; Constructing the identity authentication request based on the operating environment information report; Determine a target transport layer security protocol from a plurality of preset transport layer security protocols; The identity authentication request is sent to the third-party service via the target transport layer security protocol.

3. The service processing method based on artificial intelligence according to claim 2, characterized in that: The step of obtaining the operating environment information and constructing a corresponding operating environment information report based on the operating environment information specifically includes: Obtaining a preset information type; wherein the number of the information types includes multiple; Acquire the operating environment information corresponding to each of the information types; Building a corresponding structured report based on all the operating environment information; Get the preset private key; Digitally signing the structured report based on the private key to obtain a corresponding target report; The target report is used as the operating environment information report.

4. The service processing method based on artificial intelligence according to claim 3 is characterized in that: The step of digitally signing the structured report based on the private key to obtain the corresponding target report specifically includes: Get the target hash function; Processing the structured report based on the target hash function to obtain corresponding summary data; Signing the summary data based on the private key to obtain a corresponding signature value; The target report is generated based on the structured report and the signature value.

5. The service processing method based on artificial intelligence according to claim 2, characterized in that: The step of determining the target transport layer security protocol from the preset multiple transport layer security protocols specifically includes: Screening out a first transport layer security protocol having a security vulnerability from the multiple transport layer security protocols; Filtering the first transport layer security protocol from the multiple transport layer security protocols to obtain a corresponding second transport layer security protocol; Obtaining usage effect evaluation values ​​of each of the second transport layer security protocols, and screening out third transport layer security protocols whose usage effect evaluation values ​​are greater than a preset evaluation threshold from all the second transport layer security protocols; Obtaining release time information of each of the third transport layer security protocols; Calculate the time difference between the release time information of each of the third transport layer security protocols and the current time respectively; A fourth transport layer security protocol with the smallest time difference is selected from all the third transport layer security protocols, and the fourth transport layer security protocol is used as the target transport layer security protocol.

6. The service processing method based on artificial intelligence according to claim 1, characterized in that: The step of performing reasoning processing on the target vector data based on the large model in the preset computing environment to obtain corresponding service data specifically includes: Invoking the large model in the confidential computing environment; Performing inference processing on the target vector data based on the large model to obtain an inference result corresponding to the target vector data; The inference result is used as the service data.

7. The service processing method based on artificial intelligence according to claim 1, characterized in that: The step of returning the service data to the user specifically includes: Using the target key to encrypt the service data to obtain corresponding target service data; Obtaining communication information of the user; Based on the communication information, target service data is returned to the user.

8. A service processing device based on artificial intelligence, characterized in that: include: A receiving module, used to receive a service request input by a user; wherein the service request carries the user information and encrypted data of the user; A first sending module, used to send an identity authentication request to a preset third-party service based on a transport layer security protocol, and receive an identity authentication result returned by the third-party service; An extraction module, configured to extract the user information and the encrypted data from the service request if the identity authentication result is authentication passed, and generate a corresponding key acquisition request based on the user information; A second sending module, used to send the key acquisition request to the third-party service, and receive a target key corresponding to the user information returned by the third-party service; A processing module, configured to decrypt the encrypted data based on the target key to obtain initial data, and to perform read and write operations corresponding to the initial data in a vector database in a preset confidential computing environment to obtain corresponding target vector data; An inference module, used for performing inference processing on the target vector data based on a large model in a preset computing environment to obtain corresponding service data; The returning module is used to return the service data to the user.

9. A computer device, characterized in that: It includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the artificial intelligence-based service processing method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the artificial intelligence-based service processing method according to any one of claims 1 to 7.

Images