Communication method and device and storage medium

Abstract

The invention provides a communication method and device and a storage medium, and aims to improve the accuracy and continuity of reply of a call agent and improve the use experience of a user. The method comprises the following steps: acquiring text data of an nth round of interaction of a first call of a user and text data of n-1 rounds of interaction before the nth round of interaction; sending first information to the DCAS, wherein the first information is used for requesting to obtain historical call information of the user; receiving second information from the DCAS, wherein the second information comprises first historical call information of the user; sending third information to the LLM, wherein the third information comprises the text data of the nth round of interaction, the text data of the (n-1) th round of interaction and the first historical call information; and receiving fourth information from the LLM, wherein the fourth information comprises a reasoning result corresponding to the nth round of interaction.

Description

Technical Field

[0001] This application relates to the field of communications, and in particular, to a communication method, apparatus, and storage medium. Background Art

[0002] An agent is a basic concept in the field of artificial intelligence. It refers to a system that can operate autonomously and interact with its environment. The original intention of developing agents is to simulate the intelligent behavior of humans or other organisms, aiming to automatically solve problems or execute tasks. Large language models (LLMs) have powerful learning and planning capabilities, can handle more complex and abstract tasks, and demonstrate excellent performance in natural language understanding, reasoning and decision-making, etc. In the context of LLMs, agents can have the functions of autonomous understanding, planning and decision-making, and executing complex tasks.

[0003] The call assistant is a new service scenario under the new call network architecture, and the call assistant is implemented based on the call agent. However, in the current implementation, each call initiated by the user to the call assistant is regarded as a new call, and the information available for the call agent to reason is limited, which will affect the user experience. Summary of the Invention

[0004] This application provides a communication method, apparatus, and storage medium, aiming to improve the accuracy and coherence of the call agent's response and enhance the user experience.

[0005] In a first aspect, a communication method is provided. This method can be applied to a subscriber AI agent function (SAAF), or a module in the SAAF, such as a circuit or chip in the SAAF. Hereinafter, this method is described by taking its application to the SAAF as an example.

[0006] The method includes: obtaining the text data of the nth round of interaction of the user's first call and the text data of the n - 1 rounds of interaction before the nth round of interaction; sending a first message to a data channel application server (DCAS), where the first message is used to request to obtain the user's historical call information; receiving a second message from the DCAS, where the second message includes the user's first historical call information; sending a third message to the LLM, where the third message includes the text data of the nth round of interaction, the text data of the n - 1 rounds of interaction, and the first historical call information; receiving a fourth message from the LLM, where the fourth message includes the reasoning result corresponding to the nth round of interaction.

[0007] Among them, the first call refers to a current call between the user and the call assistant, and the nth round of interaction refers to a current round of interaction between the user and the call assistant. A call may include one or more rounds of interaction.

[0008] In this application, the DCAS stores the historical call information of the user, and the historical call information includes the text data of the historical calls initiated by the user before the first call. After the SAAF obtains the text data of the nth round of interaction of the user's first call, it can obtain the first historical call information of the user from the DCAS. Furthermore, the SAAF can use the text data of the nth round of interaction, the text data of the previous n - 1 rounds of interaction, and the first historical call information as the input of the LLM, so that the LLM can more accurately understand the text data of the nth round of interaction in combination with the first historical call information and output more accurate and more coherent reasoning results.

[0009] Combined with the first aspect, in some implementation manners of the first aspect, the first information includes the range of the historical calls of the user requested to be obtained, and the first historical call information is the historical call information of the user within the range of the historical calls.

[0010] In this application, the first information includes the range of the historical calls of the user requested to be obtained, so that the DCAS can determine the first historical call information within the range of the historical calls from the historical call information of the user and send the first historical call information to the SAAF. This is beneficial to obtaining effective historical call information, avoiding redundancy and burden on the reasoning of the LLM, and reducing signaling overhead.

[0011] Combined with the first aspect, in some implementation manners of the first aspect, the first information includes the text data of the nth round of interaction, and the text data of the nth round of interaction is used to determine the first historical call information.

[0012] In this application, the first information includes the text data of the nth round of interaction, so that the DCAS can determine the first historical call information with the closest semantics to the text data of the nth round of interaction from the historical call information of the user and send the first historical call information to the SAAF. This is beneficial to obtaining effective historical call information, avoiding redundancy and burden on the reasoning of the LLM, and reducing signaling overhead.

[0013] Combined with the first aspect, in some implementation manners of the first aspect, the first information includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

[0014] It can be understood that there may be historical call information of multiple users stored in the DCAS. Therefore, the first information includes the identifier of the user, so that the DCAS can determine the first historical call information related to the user from the historical call information of multiple users. This is beneficial to obtaining effective historical call information and reducing signaling overhead.

[0015] In combination with the first aspect, in some implementation manners of the first aspect, the first information includes a first parameter, and the first parameter is used to perform restoration processing on the historical call information of the user. Among them, the first parameter can also be referred to as a restoration parameter.

[0016] It can be understood that in order to improve data security, the historical call information stored in the DCAS can be protected historical call information. Correspondingly, when the SAAF obtains the historical call information of the user, it can carry the first parameter to instruct the DCAS to perform restoration processing on the historical call information of the user requested to be obtained.

[0017] In combination with the first aspect, in some implementation manners of the first aspect, the restoration processing includes decryption, decoding, or de - obfuscation.

[0018] In combination with the first aspect, in some implementation manners of the first aspect, the method further includes: sending a fifth information to the DCAS, where the fifth information is used to request to store the text data of the first call of the user; receiving a sixth information from the DCAS, where the sixth information is used to indicate that the text data of the first call has been stored.

[0019] After the first call ends, the SAAF can request the DCAS to store the text data of the first call, so as to obtain the text data of the first call from the DCAS in subsequent calls, help the LLM better understand the user's intention, and provide more accurate and coherent inference results.

[0020] In combination with the first aspect, in some implementation manners of the first aspect, the fifth information includes the identifier of the user. In this way, the DCAS can associate the identifier of the user with the text data of the first call, and the text data of the first call of the user can be obtained more efficiently subsequently.

[0021] In combination with the first aspect, in some implementation manners of the first aspect, the fifth information includes a second parameter, and the second parameter is used to perform protection processing on the text data of the first call. Among them, the second parameter can also be referred to as a protection parameter.

[0022] In this application, the text data of the first call can be protected through the second parameter, which is beneficial to storing the text data of the first call of the user securely and improving data security.

[0023] In connection with the first aspect, in some implementations of the first aspect, the protection process includes encryption, encoding, or obfuscation.

[0024] Among them, the encryption process makes it difficult to crack the text data even if it is leaked during storage or transmission. The encoding process can convert the text data into a specific encoding format, increasing the complexity and security of the text data. The obfuscation process can make the text data difficult to directly identify and understand by performing specific transformations on the text data.

[0025] In a second aspect, a communication method is provided. This method can be applied to DCAS or a module in DCAS, such as a circuit or chip in DCAS. Hereinafter, this method applied to DCAS will be described as an example.

[0026] The method includes: receiving first information from the SAAF, the first information being used to request to obtain the historical call information of a user; and sending second information to the SAAF, the second information including the first historical call information of the user.

[0027] In the present application, the historical call information of the user is stored in DCAS. After the SAAF obtains the text data of the nth round of interaction of the first call of the user, it can obtain the first historical call information of the user from DCAS. Furthermore, the SAAF can use the text data of the nth round of interaction, the text data of the previous n - 1 rounds of interaction, and the first historical call information as the input of the LLM, so that the LLM can more accurately understand the text data of the nth round of interaction in combination with the first historical call information and output more accurate and better - coherent inference results.

[0028] In connection with the second aspect, in some implementations of the second aspect, the first information includes the range of the historical calls of the user requested to be obtained, and the first historical call information is the historical call information of the user within the range of the historical calls.

[0029] In connection with the second aspect, in some implementations of the second aspect, the first information includes the text data of the nth round of interaction of the first call of the user, and the text data of the nth round of interaction is used to determine the first historical call information.

[0030] In connection with the second aspect, in some implementations of the second aspect, the first information includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

[0031] In connection with the second aspect, in some implementations of the second aspect, the first information includes a first parameter, and the first parameter is used to perform a restoration process on the historical call information of the user. Among them, the first parameter can also be called a restoration parameter.

[0032] In combination with the second aspect, in some implementations of the second aspect, the restoration process includes decryption, decoding, or de - obfuscation.

[0033] In combination with the second aspect, in some implementations of the second aspect, the method further includes: receiving fifth information from the SAAF, where the fifth information is used to request storing the text data of the first call of the user; storing the text data of the first call based on the fifth information; and sending sixth information to the SAAF, where the sixth information is used to indicate that the text data of the first call has been stored.

[0034] In combination with the second aspect, in some implementations of the second aspect, the fifth information includes the identifier of the user. Storing the text data of the first call based on the fifth information includes: using the identifier of the user as the key and the text data of the first call as the value, and storing the text data of the first call in the form of key - value pairs. In this application, DCAS persistently stores the text data of the first call in the form of key - value pairs, making the historical call information stored in DCAS persistently available.

[0035] In combination with the second aspect, in some implementations of the second aspect, the fifth information includes a second parameter, where the second parameter is used to perform protection processing on the text data of the first call. Storing the text data of the first call based on the fifth information includes: storing the text data of the first call after performing protection processing based on the second parameter. This helps to improve the security of the data and prevent the historical call information of the user from being leaked or tampered with.

[0036] In combination with the second aspect, in some implementations of the second aspect, the protection processing includes encryption, encoding, or obfuscation.

[0037] It should be understood that the technical solutions of the second aspect of this application correspond to those of the first aspect of this application, and the beneficial effects obtained by each aspect and the corresponding feasible implementations are similar and will not be elaborated here.

[0038] In a third aspect, a communication device is provided for executing the method in any one of the possible implementations in any of the above aspects. Specifically, the device includes modules for executing the method in any one of the possible implementations in any of the above aspects.

[0039] In one design, the device may include modules corresponding one - by - one to the methods / operations / steps / actions described in any of the above aspects. The module may be a hardware circuit, software, or a combination of hardware circuit and software.

[0040] In another design, the device is a communication chip, and the communication chip may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

[0041] In another design, the device is an SAAF or a DCAS, and the SAAF or DCAS may include a transmitter for sending information or data and a receiver for receiving information or data.

[0042] In another design, the device is used to execute the method in any one of the possible implementations of any of the above aspects, and the device may be configured in an SAAF or a DCAS.

[0043] In a fourth aspect, a communication device is provided, including at least one processor, and the at least one processor is used to call and run a computer program from a memory, so that the device executes the method in any one of the possible implementations of any of the above aspects.

[0044] Optionally, the device further includes a memory, and the memory can be used to store instructions and data. The memory is coupled to the processor, and when the processor executes the instructions stored in the memory, the methods described in the above aspects can be implemented.

[0045] Optionally, the device further includes a transmitter (transmitting device) and a receiver (receiving device). The transmitter and the receiver can be separately provided or integrated together, and are called a transceiver (transceiving device).

[0046] In a fifth aspect, a computer program product is provided, and the computer program product includes: a computer program (which can also be called code or instruction). When the computer program is run, it enables a computer to execute the method in any one of the possible implementations of any of the above aspects.

[0047] In a sixth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program (which can also be called code or instruction). When it runs on a computer, it enables the computer to execute the method in any one of the possible implementations of any of the above aspects.

[0048] In a seventh aspect, the present application provides a chip system, and the chip system includes at least one processor, which is used to support the implementation of the functions involved in any one of the possible implementations of any of the above aspects. For example, receiving or processing the data involved in the above method, etc.

[0049] In a possible design, the chip system further includes a memory, and the memory is used to store program instructions and data. The memory is located inside or outside the processor.

[0050] Optionally, the chip system can be composed of chips or can include chips and other discrete devices.

[0051] In an eighth aspect, the present application provides a communication system, including a SAAF for implementing the method described in the first aspect and any possible implementation manner of the first aspect, and a DCAS for implementing the method described in the second aspect and any possible implementation manner of the second aspect. Optionally, the communication system further includes an LLM.

[0052] It should be understood that the technical solutions of the third aspect to the eighth aspect of the present application correspond to those of the first aspect to the second aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation manners are similar, and will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 is a schematic diagram of the composition of an LLM-based agent;

[0054] Figure 2 is a schematic diagram of a call assistant service;

[0055] Figure 3 is a schematic diagram of the network architecture of a call agent provided by an embodiment of the present application;

[0056] Figure 4 is a schematic diagram of the interaction between a user and a call assistant provided by an embodiment of the present application;

[0057] Figure 5 is a schematic flowchart of a communication method provided by an embodiment of the present application;

[0058] Figure 6A and Figure 6B is a schematic diagram of the interaction between a user and a call assistant provided by an embodiment of the present application;

[0059] Figure 7 and Figure 8 is a schematic block diagram of a communication device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0061] Before introducing the technical solutions provided by the embodiments of the present application, the following points are explained.

[0062] First, in the embodiments shown below, each term and English abbreviation, such as agent, large language model (LLM), data channel application server (DCAS), user agent function (SAAF), etc., are exemplary examples given for convenience of description, and should not constitute any limitation to the present application. The present application does not exclude the possibility of defining other terms that can achieve the same or similar functions in existing or future protocols.

[0063] Second, in the embodiments shown below, the first, second, and various numerical numbers are only used for convenience of description to distinguish identical or similar items with basically the same functions and effects. For example, the first information and the second information are only used to distinguish different information, and do not limit the order thereof, nor are they used to limit the scope of the embodiments of the present application. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and the terms "first", "second", etc. do not necessarily mean different.

[0064] Third, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c, where a, b, and c can be single or multiple.

[0065] Fourth, in the present application, "indication" can include direct indication and indirect indication, can also include explicit indication and implicit indication, and can also include for determination. When it is described that a certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A. In the present application, the information indicated by the indication information is called the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated, etc. The information to be indicated can also be indirectly indicated by indicating other information, where there is an association relationship between the other information and the information to be indicated. It is also possible to only indicate a part of the information to be indicated, while the other parts of the information to be indicated are known or pre-agreed. For example, the indication of specific information can also be achieved by relying on the arrangement order of each information pre-agreed (such as protocol regulations), thereby reducing the indication overhead to a certain extent. In addition, the information to be indicated can be sent as a whole, or can be divided into multiple sub-information and sent separately, and the sending periods and / or sending times of these sub-information can be the same or different. The present application does not limit the specific manner of indication. It can be understood that for the sender of the indication information, the indication information can be used to indicate the information to be indicated, and for the receiver corresponding to the indication information, the indication information can be used to determine the information to be indicated.

[0066] One piece of information in this application is used to indicate one or more items, or it can be replaced with that this information indicates one or more items, or this information includes one or more items.

[0067] Fifth, in this application, "when", "if", and "in case" all refer to that the device will perform corresponding processing under certain objective circumstances, rather than limiting time, and it is not required that the device must have a judgment action when implemented, nor does it mean there are other limitations. Without special instructions, "if" and "in case" can be replaced, "when" and "in the case of" can be replaced. "When" and "if" / "in case" can be replaced.

[0068] Sixth, in this application, words such as "exemplarily" or "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "exemplarily" or "for example" in this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplarily" or "for example" is intended to present relevant concepts in a specific manner.

[0069] Seventh, "send information / data" only indicates the direction of information / data transfer, including direct sending through the communication interface of the device (such as the air interface (abbreviated as the air interface), etc.). "Send" can also be understood as the "output" of the module interface. "Send" can include indirect sending by the processing unit through the communication interface, that is, after the processing unit outputs information / data through the module interface, it is transmitted to the communication interface of the device and sent out by it. "Receive information / data" only indicates the direction of information / data transfer, including direct reception by the communication interface. "Receive" can also be understood as the "input" of the module interface. "Receive information / data" can include indirect reception by the processing unit through the communication interface, that is, after the communication interface receives information / data, it is transmitted to the module interface of the processing unit and input to the processing unit by this module interface. "Send information / data to... (such as a terminal device)" can be understood as the destination of this information is the terminal device. It can include directly or indirectly sending information / data to the terminal device. "Receive information / data from... (such as a terminal device)" can be understood as the source of this information is the terminal device, and it can include directly or indirectly receiving information / data from the terminal device. Necessary processing may be performed on the information / data between the source and destination of the information / data sending, such as format change, etc., but the destination can understand the valid information / data from the source. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0070] In other words, sending and receiving can be carried out between devices. For example, between a terminal device and a network device; it can also be carried out within a device. For example, sending or receiving between components, modules, chips, software modules or hardware modules within a device through a bus, trace or interface.

[0071] Eighth, in this application, the solutions in each embodiment can be reasonably combined and used, and the explanations or descriptions of various terms, similar operations, or steps that appear in the embodiments can be referred to or explained with each other in each embodiment, which is not limited herein.

[0072] For ease of understanding, the related technologies and concepts involved in this application are introduced below.

[0073] 1. LLM-based agent.

[0074] An agent is a basic concept in the field of artificial intelligence, referring to a system that can operate autonomously and interact with the environment. The original intention of developing agents is to simulate the intelligent behaviors of humans or other organisms, aiming to automatically solve problems or execute tasks. LLM has powerful learning and planning capabilities, can handle more complex and abstract tasks, and demonstrates excellent performance in aspects such as natural language understanding and reasoning decision-making. In the context of LLM, an agent can have the functions of autonomous understanding, planning decision-making, and executing complex tasks. The agent mentioned below can be understood as an LLM-based agent.

[0075] In this application, an agent can also be referred to as an artificial intelligence agent (AI agent).

[0076] As Figure 1 shown, in an LLM-based agent, LLM acts as the "brain" of the agent. The agent can be further extended to include several key components: planning, memory, tool use, and action. A brief introduction to these parts is given below.

[0077] Planning: Introduce a problem-solving thinking mode similar to that of humans for the agent, decompose complex tasks into a series of simple subtasks, and then solve them one by one. This method reduces the difficulty of solving tasks at once, helps improve the efficiency and effectiveness of problem-solving, and enhances the agent's adaptability to complex environments and the reliability of operations. To generate effective planning solutions, the agent can generate multiple candidate solutions simultaneously and select the best one for execution. When dealing with complex tasks, the agent can also perform iterative optimization based on real-time feedback information from the environment, thus solving problems involving complex reasoning more efficiently. According to different ways of handling tasks, planning can include "one-time" decomposition of tasks and generation of steps (referred to as Planning A), and "iterative" decomposition of tasks and generation of steps (referred to as Planning B). Among them, Planning A includes, for example, chain of thought (CoT), plan and solve (PS), and Planning B includes, for example, reasoning and acting (ReAct), tree of thought (ToT).

[0078] Memory: The human memory system is a complex and efficient information processing system that can store new knowledge and recall and use the stored information when needed to assist in coping with the current environment and making decisions. Similarly, in the agent, the memory component constitutes the core storage unit of the agent, mainly used to store the historical interaction records between the agent and the environment and can be retrieved and used at any time. Memory can also include short-term memory and long-term memory. Among them, short-term memory corresponds to historical context, and the LLM can remember and learn within a certain context length. Long-term memory refers to the larger knowledge base that the LLM can access, usually combined with retrieval-augmented generation (RAG) technology. With the vector database as the carrier, it obtains updates from the vector database and expands the knowledge base of the LLM to complete the context information when the LLM answers questions and improve the accuracy of the answers.

[0079] Tool Use: For information missing in the LLM, such as real-time weather, real-time search results, mathematical reasoning ability, etc., the agent obtains additional information by calling external application programming interfaces (APIs). Tools can be functions, API calls, or separately designed solutions, and can also include code interpreters, etc.

[0080] Action: This is the part where the agent actually executes decisions or responses. Facing different tasks, the agent can choose the actions to be executed during decision-making, such as memory retrieval, reasoning, learning, programming, etc. Actions also include the environmental perception ability. The agent's environmental perception ability allows it to receive the results of external tool calls or real-time environmental information, so as to respond more flexibly to different situations.

[0081] 2. Prompt Engineering

[0082] Prompt engineering is used to design effective input prompts to guide the LLM to generate high-quality and relevant answers. This input prompt can be called a prompt, and the agent and the LLM interact using the prompt. Table 1 is an example of the components of a prompt.

[0083] Table 1

[0084]

[0085]

[0086] 3. Call Assistant Service

[0087] The call assistant service is a brand-new business scenario under the new call network architecture, which is realized based on call agents. As Figure 2 shown, the call assistant service can include intelligent answering on behalf (abbreviated as "chat on behalf"), intelligent assistance (abbreviated as "chat assistance"), emotional chatting companion (abbreviated as "chat companion"), personal assistant / enabling three parties (abbreviated as "call entry"). Each major category can include multiple vertical domain business scenarios (abbreviated as "vertical domains"), such as actor calls, meal ordering assistants, and service hall assistants.

[0088] Except for intelligent answering on behalf, the vertical domain scenarios of other services involve human-machine interaction calls, such as user calling the machine / call assistant (consumer to machine, C2M) or the machine / call assistant calling the user (machine to consumer, M2C). During the call, the user interacts with the call agent through voice interaction. For example, in the meal ordering assistant vertical domain: the user feeds back requirements such as taste preferences and delivery addresses to the call agent through multi-round interactions; in the actor call vertical domain: the user communicates with the actor about the latest movies, music and other topics in multi-round interactions; in the hotel assistant vertical domain: the user communicates with the call agent about price, reservation time and other information through multi-round interactions.

[0089] The call agent tries to remember as much content as possible from the multi-round interactions with the user during the current call, caching the user's questions, opinions, and needs in the context memory component of the current call. This enables better understanding of the user's intent in the next round of interaction, allows for more accurate responses to the user's questions, ensures logical coherence between past and next interactions, and provides the user with a more efficient communication experience.

[0090] Figure 3 It is a schematic diagram of the network architecture of a call agent provided by an embodiment of this application. As Figure 3 shown, examples of some network elements in this network architecture are as follows: AI agent management function (AAMF), SAAF, subscriber vector database function (SVDF), DCAS, media function (MF), data channel signaling function (DCSF), voice over long-term evolution application server (VoLTE AS), interrogating-call session control function (I-CSCF) in the internet protocol multimedia subsystem (IMS), proxy-call session control function (P-CSCF) in the IMS, serving-call session control function (S-CSCF) in the IMS, IMS access media gateway (IMS-AGW), LLM.

[0091] Among them, the AAMF is responsible for allocating SAAF and SVDF instances to the user when the user powers on or requests a service.

[0092] The SAAF is the call agent and is responsible for the logical functions of the user agent.

[0093] The SVDF is responsible for storing the vectorized general information of the user and the personalized data of the user.

[0094] The DCAS is used to provide the logical orchestration of the data channel (DC) service.

[0095] MF is used to provide DC service media capabilities such as rendering and voice translation.

[0096] DCSF is responsible for managing DC media channels and DC service triggering, and providing a northbound interface for service calls.

[0097] The VoLTE AS is responsible for handling call signaling and control, including call establishment, maintenance, and termination.

[0098] Since the LLM itself is designed to be stateless, under the new call network architecture, every time a user makes a call to a call assistant, it will be considered a new call, so the call agent needs to re-understand the user's needs. Figure 4 As shown in the figure, the user elaborated on a problem in detail during a call and had an in-depth discussion with the call assistant (SAAF). However, when the user made another call, the call assistant could not obtain the content of the previous call and required the user to describe the problem again, wasting the user's time and energy. At the same time, this lack of memory of past call content cannot make full use of the context of past calls, resulting in the accuracy and coherence of the call assistant's response being affected, reducing the user's communication experience.

[0099] In view of this, an embodiment of the present application provides a communication method, in which DCAS is used to store the historical context of the user's past calls. SAAF can obtain the historical context of the past calls from DCAS, and send the call content of the current call and the historical context of the past calls to LLM. In this way, LLM can better understand the user's intention based on the call content of the current call and the historical context of the past calls, improve the accuracy and coherence of the response, and bring an efficient communication experience to the user.

[0100] In the following embodiments, SAAF may be replaced by a multi-modal communication function (MCF), and DCAS may be replaced by a service application server (service application server).

[0101] Figure 5 It is a schematic flow chart of a communication method 500 provided in an embodiment of the present application. The steps of method 500 can be interactively executed by SAAF (or a module in SAAF, such as a processor, chip, chip system, circuit, etc.) and DCAS (or a module in DCAS, such as a processor, chip, chip system, circuit, etc.), and LLM. In addition, the processing performed by a single execution subject can also be divided into multiple execution subjects, which can be logically and / or physically separated.

[0102] Method 500 includes but is not limited to S501 to S505. Optionally, method 500 further includes S506 and S507. Each step is introduced in detail below.

[0103] S501, the SAAF obtains the text data of the nth round of interaction of the user's first call and the text data of the n - 1 rounds of interaction before the nth round of interaction.

[0104] Wherein, the first call refers to a current call of the user with the call assistant, and the nth round of interaction refers to a current round of interaction between the user and the call assistant. A call can include one or more rounds of interaction.

[0105] Optionally, before the SAAF obtains the text data of the nth round of interaction of the user's first call, the SAAF can receive the audio data of the nth round of interaction of the user's first call from the MF. After that, the SAAF can use automatic speech recognition (ASR) technology to convert the audio data of the nth round of interaction into text data, so as to obtain the text data of the nth round of interaction.

[0106] Optionally, the SAAF obtains the text data of the n - 1 rounds of interaction before the nth round of interaction, including: the SAAF obtains the text data of the n - 1 rounds of interaction before the nth round of interaction from its own memory.

[0107] S502, the SAAF sends a first message to the DCAS, and the first message is used to request to obtain the historical call information of the user. Accordingly, the DCAS receives the first message.

[0108] In the application embodiment, the historical call information of the user is stored in the DCAS. In order to effectively utilize the historical call information of the user and improve the accuracy and coherence of the call assistant's reply, the SAAF can request the historical call information of the user from the DCAS after obtaining the text data of the nth round of interaction of the user's first call. Subsequently, the SSAF can use the historical call information of the user as part of the input of the LLM for the LLM to reason about the text data of the nth round of interaction. Wherein, the historical call information includes the text data of at least one historical call before the first call, and each historical call includes one or more rounds of interaction.

[0109] S503, the DCAS sends a second message to the SAAF, and the second message includes the first historical call information of the user. Accordingly, the SAAF receives the second message.

[0110] Based on the request of the SAAF, the DCAS determines the first historical call information from the historical call information of the user and sends the first historical call information of the user to the SAAF.

[0111] S504, The SAAF sends the third information to the LLM. The third information includes the text data of the nth round of interaction, the text data of the previous n - 1 rounds of interaction before the nth round of interaction, and the first historical call information. Accordingly, the LLM receives the third information.

[0112] Interaction between the SAAF and the LLM can be based on prompts. For example, as shown in the examples of the components of the prompts above, the prompt can include short - term memory and long - term memory. The SAAF can use the text data of the nth round of interaction and the text data of the previous n - 1 rounds of interaction before the nth round of interaction as the content of the short - term memory of the prompt, and use the first historical call information as the content of the long - term memory of the prompt.

[0113] S505, The LLM sends the fourth information to the SAAF. The fourth information includes the inference result corresponding to the nth round of interaction. Accordingly, the SAAF receives the fourth information.

[0114] After receiving the third information, the LLM generates an inference result corresponding to the text information of the nth round of the first call based on the content included in the third information, and sends the inference result to the SAAF.

[0115] In the application embodiment, the historical call information of the user is stored in the DCAS. After obtaining the text data of the nth round of the first call of the user, the SAAF can obtain the first historical call information of the user from the DCAS, and send the text data of the first call and the first historical call information to the LLM. In this way, the LLM can better understand the text information of the nth round of interaction of the user by combining the first historical call information and the text information of the previous n - 1 rounds of interaction before the nth round of interaction, making the inference result of the text information of the nth round of interaction more accurate, improving the accuracy and coherence of the reply, and bringing an efficient communication experience to the user.

[0116] It can be understood that, optionally, after receiving the inference result corresponding to the nth round of interaction, the SAAF uses text - to - speech (TTS) technology to convert the inference result into speech. Further, the SAAF encapsulates the converted speech into real - time transport (RTP) data and then sends it to the MF, which forwards it to the user.

[0117] Since the DCAS may store the historical call information of multiple users, the first information can include the identification of the user, such as the trace identification of the user. The identification of the user is used to determine the first historical call information of the user from the historical call information of multiple users.

[0118] To improve data security, DCAS can store the historical call information of the user after performing protection processing on it. The protection processing may include encryption, encoding, or obfuscation. Correspondingly, when SAAF sends a first message to DCAS to request the historical call information of the user, the first message may include a first parameter, which is used to perform restoration processing on the historical call information of the user. The restoration processing may include decryption, decoding, or de-obfuscation.

[0119] It can be understood that if the protection processing is encryption, the corresponding restoration processing is decryption; if the protection processing is encoding, the corresponding restoration processing is decoding; if the protection processing is obfuscation, the corresponding restoration processing is de-obfuscation.

[0120] Since DCAS may store a large amount of historical call information of the user who initiated the first call, some of the historical call information may have little or no relevance to the text information of the nth round of interaction of the first call of the user. Therefore, in order to save signaling overhead and obtain effective historical call information, there are two possible implementation methods as follows.

[0121] In one possible implementation, the first message may include the range of the historical calls of the user requested to be obtained, and the first historical call information is the historical call information of the user within the range of the historical calls.

[0122] For example, the range of the historical calls is the N historical calls before the first call, where N is a positive integer. SAAF requests to obtain the historical call information of the user for the N historical calls before the first call. That is to say, the first historical call information is the historical call information of the user within the N historical calls before the first call. For example, when N = 3, the first historical call information is the historical call information of the user's 3 historical calls, and these 3 historical calls may be the 3 historical calls closest to the first call among the user's multiple historical calls.

[0123] For example, the range of the historical calls is the historical call information within the first time period. SAAF requests to obtain the historical call information of the user within the first time period. That is to say, the first historical call information is the historical call information of the user within the first time period. For example, when the first time period is 1 week, the first historical call information is the historical call information of the user within the most recent week before the first call.

[0124] As Figure 6AAs shown, during a call, the user inputs the audio data of the nth round of interaction. After SAAF obtains the audio data of the nth round of interaction, it converts the audio data of the nth round of interaction into text data. Then, SAAF requests DCAS to obtain the historical call information of the user's N previous calls or the historical call information within the first duration before this call of the user. Based on this request, DCAS returns to SAAF the historical call information of the user's N previous calls or the historical call information within the first duration before this call. Further, SAAF composes the text data of the nth round of interaction, the text data of the previous n - 1 rounds of interaction, and the historical call information of the previous N calls or the historical call information within the first duration into a prompt and sends it to the LLM. The LLM performs reasoning on the text data of the nth round of interaction based on this prompt and outputs a reasoning result.

[0125] In another possible implementation, the first information includes the text data of the nth round of interaction of the user's first call, and the text data of the nth round of interaction is used to determine the first historical call information. In this implementation, SAAF sends the text information of the nth round of interaction of the user's first call to DCAS. DCAS, based on the text information of the nth round of interaction of the user's first call, obtains the first historical call information that is semantically closest to the text information of the nth round of interaction of the user's first call. This is beneficial for obtaining effective historical call information and saving signaling overhead.

[0126] Among them, DCAS can use semantic analysis technology to determine the first historical call information that is semantically closest to the text information of the nth round of interaction. For example, the semantic analysis technology is natural language processing (NLP) processing, vector matching, or best matching 25 (BM25) retrieval.

[0127] As Figure 6B As shown, during a call, the user inputs the audio data of the nth round of interaction. After SAAF obtains the audio data of the nth round of interaction, it converts the audio data of the nth round of interaction into text data. Then, SAAF requests DCAS to obtain the historical call information that is semantically closest to the text data of the nth round of interaction. Among them, the request includes the text data of the nth round of interaction. DCAS, based on this request, returns to SAAF the historical call information that is semantically closest to the text data of the nth round of interaction. Further, SAAF composes the text data of the nth round of interaction, the text data of the previous n - 1 rounds of interaction, and the historical call information that is semantically closest to the text data of the nth round of interaction into a prompt and sends it to the LLM. The LLM performs reasoning on the text data of the nth round of interaction based on this prompt and outputs a reasoning result.

[0128] It can be understood that the above two implementation manners can be combined with each other to determine the first historical call information. For example, the first historical call is the historical call information of N historical calls within the first duration. For another example, the first historical call information is the historical call information of the N historical calls within the first duration that is semantically closest to the text data of the nth round of interaction. For yet another example, the first historical call information is the historical call information of the N historical calls before the first call that is semantically closest to the text data of the nth round of interaction.

[0129] In another possible implementation, the first historical call information includes M historical contexts (or text information of M rounds of historical interaction) of the user before the first call, and the M historical contexts are determined from one or more historical calls before the first call. For example, the first call is the Tth call of the user, M = 10. If the (T - 1)th call of the user includes 12 contexts, the first historical call information includes the 10 contexts closest to the Tth call among the 12 contexts of the (T - 1)th call of the user; if the (T - 1)th call of the user includes 6 contexts and the (T - 2)th call of the user includes 4 contexts, the first historical call information includes the 6 contexts of the (T - 1)th call of the user and the 4 contexts of the (T - 2)th call of the user.

[0130] As an example, a round of interaction (or a round of question and answer) of the user can be regarded as a context. For example, {User: What is the price of XX car? Call assistant: The current price of this car is XXX} is a context.

[0131] It can be understood that before S501, Figure 3Multiple network elements in the shown network architecture interact to complete the service setup process and the call establishment process. For example, when a user uses a terminal device to initiate a new call, the terminal device interacts with the DCAS to complete the process of subscribing to or setting up the call assistant service. When the user has a need, the user can use the terminal device to call the call assistant number. In response to the user's call, the VoLTE AS can interact with the DCSF to complete basic call negotiation, including call event notification, control, and user identification. Further, the VoLTE AS instructs the MF to create media resources and sends the user's identification to the MF. After the media resources are created, the SAAF starts the call assistant. During the call phase, the MF receives the audio data of the nth round of interaction of the user through the DCSF. Further, the DCSF sends a request to the MF to copy the audio data of the nth round of interaction of the user, and the request also indicates to send the copied audio data to the SAAF. Accordingly, the MF performs an audio data copy negotiation process with the SAAF based on this request. For example, information such as the port, uniform resource locator (URL), and format (encoding method) of the audio data is negotiated. Further, the MF sends the audio data of the nth round of interaction of the user to the SAAF based on the negotiation content. Further, the SAAF can convert the audio data of the nth round of interaction of the user into text data that the LLM can recognize.

[0132] Optionally, method 500 further includes S506: The SAAF sends fifth information to the DCAS, and the fifth information is used to request storing the text data of the first call of the user. Accordingly, the DCAS receives the fifth information and stores the text data of the first call of the user based on the fifth information. Wherein, the fifth information includes the text data of the first call of the user. Optionally, method 500 further includes S507: The DCAS sends sixth information to the SAAF, and the sixth information is used to indicate that the text data of the first call of the user has been stored.

[0133] After the SAAF starts the call assistant, the SAAF can apply for a block of memory for the first call to store the text data of each round of the first call. After the first call ends, the SAAF can request the DCAS to store the text data of the first call and clear the memory applied for the first call by the SAAF, releasing the memory resources occupied by the text data of the first call.

[0134] After the first call ends, the first call serves as the historical call of the subsequent calls of the user, and the text data of the first call can serve as the historical call information of the subsequent calls of the user. Subsequently, the SAAF can obtain the text data of the first call to help the LLM better understand the text data of the user's subsequent calls and provide a more accurate and coherent response to the user.

[0135] During the subsequent call process of the user, in order for SAAF to efficiently obtain the text data of the user's first call, the fifth information may include the identifier of the user. In this way, DCAS can associate the user with the text data of the first call. During the subsequent call process of the user, DCAS can determine the text data of the first call associated with the user based on the identifier of the user.

[0136] In a possible implementation, DCAS stores the text data of the user's first call in the form of key-value pairs, with the identifier of the user as the key and the text data of the first call as the value.

[0137] To improve data security, the fifth information may include a second parameter, which is used to perform protection processing on the text data of the first call. Optionally, the protection processing includes encryption, encoding, or obfuscation. After receiving the fifth information, DCAS can, based on the second parameter, perform protection processing on the text data of the first call and then store it. Further, during the subsequent call process, SAAF can send a restoration parameter to DCAS, which is used to perform restoration processing on the text data of the first call. The restoration processing includes decryption, decoding, or de-obfuscation. It can be understood that the technical means adopted for the protection processing / restoration processing described in this application are possible examples, and this application does not limit the technical means adopted for the protection processing / restoration processing.

[0138] The second parameter can be an encryption parameter, an encoding parameter, or an obfuscation parameter.

[0139] Among them, encryption processing makes it difficult for the text data to be cracked even if it is leaked during storage or transmission. For example, DCAS can use symmetric or asymmetric encryption algorithms to encrypt the text data of the first call. Encoding processing can convert the text data into a specific encoding format, increasing the complexity and security of the text data. Obfuscation processing can make the text data difficult to be directly recognized and understood by performing specific transformations on the text data.

[0140] It can be understood that if the second parameter is an encryption parameter, DCAS encrypts the text data of the first call based on this encryption parameter when storing the text data of the first call. Correspondingly, when SAAF requests to obtain the text data of the first call, it needs to send a decryption parameter corresponding to this encryption parameter to DCAS, and DCAS decrypts the text data of the first call based on this decryption parameter; if the second parameter is an encoding parameter, DCAS encodes the text data of the first call based on this encoding parameter when storing the text data of the first call. Correspondingly, when SAAF requests to obtain the text data of the first call, it needs to send a decoding parameter corresponding to this encoding parameter to DCAS, and DCAS decodes the text data of the first call based on this decoding parameter; if the second parameter is a confusion parameter, DCAS confuses the text data of the first call based on this confusion parameter when storing the text data of the first call. Correspondingly, when SAAF requests to obtain the text data of the first call, it needs to send a de - confusion parameter corresponding to this confusion parameter to DCAS, and DCAS de - confuses the text data of the first call based on this de - confusion parameter.

[0141] It can be understood that the various digital numbers involved in the embodiments of the present application are only for convenience of description and do not limit the scope of the embodiments of the present application. The magnitude of the sequence numbers of the above - mentioned processes does not mean the order of execution, and the order of execution of each process should be determined by its function and internal logic.

[0142] In the above - mentioned embodiments provided by the present application, the method provided by the embodiments of the present application is introduced by taking the execution of SAAF, DCAS, and LLM as examples. In the present application, each embodiment can be implemented independently or implemented in combination based on certain internal relationships; in each embodiment, different implementation manners can be implemented in combination or independently. To implement each function in the method provided by the embodiments of the present application, the steps executed by SAAF, DCAS, or LLM can be implemented by SAAF, DCAS, or LLM itself, or can be implemented by different functional entities that make up SAAF, DCAS, or LLM. To implement each function in the method provided by the embodiments of the present application, SAAF, DCAS, or LLM can include a hardware structure and / or software module, and implement the above - mentioned functions in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module. Whether a certain function among the above - mentioned functions is executed in the form of a hardware structure, a software module, or a combination of a hardware structure and a software module depends on the specific application and design constraints of the technical solution.

[0143] In the above text, in combination with Figure 5 , the communication method according to the embodiments of the present application is described in detail. Next, in combination with Figure 7 and Figure 8, a communication device according to an embodiment of the present application is described in detail.

[0144] As Figure 7 shown, the communication device 700 includes a processing module 710 and a transceiver module 720. The transceiver module 720 may also be referred to as a communication interface or a communication module.

[0145] The device 700 may be used to perform the actions executed by SAAF or DCAS in the above method embodiments. Alternatively, the device 700 is a component (such as a chip) configured in SAAF or DCAS. The processing module 710 is used to perform the processing-related operations of SAAF or DCAS in the above method embodiments. The transceiver module 720 is used to perform the reception and transmission-related operations of SAAF or DCAS in the above method embodiments.

[0146] Optionally, the transceiver module 720 may include a transmission module and a reception module. The transmission module is used to perform the transmission operation in the above method embodiments. The reception module is used to perform the reception operation in the above method embodiments.

[0147] It should be noted that the device 700 may include a transmission module but not a reception module. Alternatively, the device 700 may include a reception module but not a transmission module. Specifically, it depends on whether the above solution executed by the device 700 includes a transmission action and a reception action.

[0148] Optionally, the device 700 is used to perform the Figure 5 actions executed by SAAF or DCAS in the embodiments shown above. Specifically, reference may be made to the relevant introduction in the embodiments shown above Figure 5 and details are not described herein again.

[0149] Optionally, the device 700 may further include a storage module, which may be used to store data, and / or used to store computer programs or instructions. The processing module 710 may read the computer programs / instructions and / or data in the storage module so that the device 700 can implement the above method embodiments.

[0150] When the device 700 is used to implement as Figure 5When implementing the function of SAAF in the method embodiment shown, the processing module 710 is used to: obtain the text data of the nth round of interaction of the user's first call and the text data of the previous n - 1 rounds of interaction before the nth round of interaction; the transceiver module 720 is used to: send a first message to DCAS, the first message is used to request to obtain the historical call information of the user; receive a second message from DCAS, the second message includes the first historical call information of the user; send a third message to LLM, the third message includes the text data of the nth round of interaction, the text data of the n - 1 rounds of interaction and the first historical call information; and, receive a fourth message from LLM, the fourth message includes the inference result corresponding to the nth round of interaction.

[0151] Optionally, the first message includes the range of the historical calls of the user requested to be obtained, and the first historical call information is the historical call information of the user within the range of the historical calls.

[0152] Optionally, the first message includes the text data of the nth round of interaction, and the text data of the nth round of interaction is used to determine the first historical call information.

[0153] Optionally, the first message includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

[0154] Optionally, the first message includes a first parameter, and the first parameter is used to perform restoration processing on the historical call information of the user.

[0155] Optionally, the restoration processing includes decryption, decoding or de - obfuscation.

[0156] Optionally, the transceiver module 720 is used to: send a fifth message to DCAS, the fifth message is used to request to store the text data of the user's first call; and, receive a sixth message from DCAS, the sixth message is used to indicate that the text data of the first call has been stored.

[0157] Optionally, the fifth message includes the identifier of the user.

[0158] Optionally, the fifth message includes a second parameter, and the second parameter is used to perform protection processing on the text data of the first call.

[0159] Optionally, the protection processing includes encryption, encoding or obfuscation.

[0160] When the device 700 is used to implement the function of DCAS in the method embodiment as Figure 5 shown, the transceiver module 720 is used to: receive a first message from SAAF, the first message is used to request to obtain the historical call information of the user; and, send a second message to SAAF, the second message includes the first historical call information of the user.

[0161] Optionally, the first information includes the range of the historical calls of the user requested to be obtained, and the first historical call information is the historical call information of the user within the range of the historical calls.

[0162] Optionally, the first information includes the text data of the nth round of interaction of the first call of the user, and the text data of the nth round of interaction is used to determine the first historical call information.

[0163] Optionally, the first information includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

[0164] Optionally, the first information includes a first parameter, and the first parameter is used to perform a restoration process on the historical call information of the user.

[0165] Optionally, the restoration process includes decryption, decoding, or de - obfuscation.

[0166] Optionally, the transceiver module 720 is configured to: receive fifth information from the SAAF, where the fifth information is used to request storing the text data of the first call of the user; the processing module 710 is configured to: based on the fifth information, store the text data of the first call; the transceiver module 720 is further configured to: send sixth information to the SAAF, where the sixth information is used to indicate that the text data of the first call has been stored.

[0167] Optionally, the fifth information includes the identifier of the user. The processing module 710 is configured to: use the identifier of the user as the key, use the text data of the first call as the value, and store the text data of the first call in the form of key - value pairs.

[0168] Optionally, the fifth information includes a second parameter, and the second parameter is used to perform a protection process on the text data of the first call. The processing module 710 is configured to: perform a protection process on the text data of the first call based on the second parameter and then store it.

[0169] Optionally, the protection process includes encryption, encoding, or obfuscation.

[0170] It can be understood that the division of modules in the above device is only a division of logical functions. Each function can correspond to a functional module, or two or more functions can be integrated into one functional module. In actual implementation, all or part of the modules can be integrated into one physical entity, or distributed among different physical entities. In addition, the above functional modules can be implemented in the form of hardware, or in the form of software, or in the form of a combination of hardware and software. Whether a certain function is executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described function for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0171] For a more detailed description of each step, reference can be made to the relevant description in the method embodiment above, and details will not be repeated here.

[0172] Figure 8 is a schematic block diagram of another communication device 800 provided by an embodiment of the present application, as Figure 8 shown, the device 800 includes one or more processors 810 and an interface circuit 820. The one or more processors 810 and the interface circuit 820 are coupled to each other. It can be understood that the interface circuit 820 can be a transceiver or an input / output interface. Optionally, the device 800 may further include a memory 830, which is used to store instructions executed by the processor 810, or used to store input data required for the processor 810 to run instructions, or used to store data generated after the processor 810 runs instructions. Sometimes, the interface circuit 820 can also be understood as a part of the one or more processors 810. In this case, the device 800 includes the one or more processors 810.

[0173] Optionally, in one design, the processor 810 may include a computer program (which can also be referred to as code or instructions), and this program can be run on the processor 810, so that the device 800 executes the methods performed by SAAF or DCAS in the above method embodiments. In another possible design, the device 800 includes a circuit ( Figure 8 not shown), and this circuit is used to implement the functions of SAAF or DCAS in the above method embodiments.

[0174] The one or more processors 810 and the memory 830 can be separately provided or integrated, and the present application does not make any limitation on this.

[0175] When the device 800 is used to implement Figure 5When implementing the method shown, the one or more processors 810 are used to implement the functions of the above-mentioned processing module 710, and the interface circuit 820 is used to implement the functions of the above-mentioned transceiver module 720. Whether the communication interface 820 is used for sending or receiving specifically depends on whether the device 800 executes a sending action or a receiving action in the implemented solution.

[0176] When the above-mentioned device 800 is a chip applied to SAAF, the SAAF chip implements the functions of SAAF in the above-mentioned method embodiment. The SAAF chip receives information from DCAS. It can be understood that this information is first received by other modules (such as a radio frequency module or an antenna) in the SAAF and then sent by these modules to the SAAF chip. The SAAF chip sends information to DCAS. It can be understood that this information is first sent to other modules (such as a radio frequency module or an antenna) in the SAAF and then sent by these modules to DCAS.

[0177] When the above-mentioned device 800 is a chip applied to DCAS, the DCAS chip implements the functions of DCAS in the above-mentioned method embodiment. The DCAS chip receives information from SAAF. It can be understood that this information is first received by other modules (such as a radio frequency module or an antenna) in the DCAS and then sent by these modules to the DCAS chip. The DCAS chip sends information to SAAF. It can be understood that this information is first sent to other modules (such as a radio frequency module or an antenna) in the DCAS and then sent by these modules to SAAF.

[0178] An embodiment of the present application further provides a computer-readable storage medium for storing a computer program. When the computer program runs on a computer, the computer can be made to execute the method in the above-mentioned embodiment. Or rather, the computer program includes instructions for implementing the method in the above-mentioned embodiment.

[0179] An embodiment of the present application further provides a computer program product, including: a computer program or instructions. When the computer program or instructions run on a computer, the computer is made to execute the method in the above-mentioned embodiment.

[0180] An embodiment of the present application further provides a device. The device can be a chip and includes at least one processor for supporting the implementation of the method in the above-mentioned embodiment. For example, receiving or processing data involved in the method in the above-mentioned embodiment, etc.

[0181] An embodiment of the present application also provides a communication system, including a SAAF and a DCAS. The SAAF can execute the method in the above embodiment, and the DCAS can execute the method in the above embodiment. Optionally, the communication system further includes an LLM. Optionally, the communication system further includes one or more of the following: a terminal device, a DCSF, an MF, and a VoLTE AS.

[0182] It should be understood that in the embodiment of the present application, the processor may be a central processing unit, and the processor may also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0183] In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by the combination of the hardware and software modules in the processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor executes the instructions in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0184] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0185] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0186] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0187] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0188] In addition, in each embodiment of this application, the functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0189] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0190] As described above, the above are only the specific implementation manners of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application and should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, Including: Obtain the text data of the nth round of interaction of the user's first call and the text data of the n - 1 rounds of interaction before the nth round of interaction; Send a first message to the Data Channel Application Server (DCAS), where the first message is used to request to obtain the historical call information of the user; Receive a second message from the DCAS, where the second message includes the first historical call information of the user; Send a third message to the Large Language Model (LLM), where the third message includes the text data of the nth round of interaction, the text data of the n - 1 rounds of interaction, and the first historical call information; Receive a fourth message from the LLM, where the fourth message includes the inference result corresponding to the nth round of interaction.

2. The method according to claim 1, characterized in that The first message includes the range of the historical calls of the user for which acquisition is requested, and the first historical call information is the historical call information of the user within the range of the historical calls.

3. The method according to claim 1 or 2, characterized in that, The first message includes the text data of the nth round of interaction, and the text data of the nth round of interaction is used to determine the first historical call information.

4. The method according to any one of claims 1 to 3, characterized in that, The first message includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

5. The method according to any one of claims 1 to 4, characterized in that, The first message includes a first parameter, and the first parameter is used to perform a restoration process on the historical call information of the user.

6. The method according to claim 5, characterized in that, The restoration process includes decryption, decoding, or de - obfuscation.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Send a fifth message to the DCAS, where the fifth message is used to request to store the text data of the user's first call; Receive a sixth message from the DCAS, where the sixth message is used to indicate that the text data of the first call has been stored.

8. The method according to claim 7, wherein The fifth message includes the identifier of the user.

9. The method according to claim 7 or 8, characterized in that, The fifth message includes a second parameter, and the second parameter is used to perform a protection process on the text data of the first call.

10. The method according to claim 9, characterized in that, The protection process includes encryption, encoding, or obfuscation.

11. A communication method, characterized in that, Including: Receive a first message from the User Agent Function (SAAF), where the first message is used to request to obtain the historical call information of the user; Send a second message to the SAAF, where the second message includes the first historical call information of the user.

12. The method according to claim 11, wherein The first message includes the range of the historical calls of the user for which acquisition is requested, and the first historical call information is the historical call information of the user within the range of the historical calls.

13. The method according to claim 11 or 12, characterized in that, The first message includes the text data of the nth round of interaction of the user's first call, and the text data of the nth round of interaction is used to determine the first historical call information.

14. The method according to any one of claims 11 to 13, characterized in that, The first message includes the identifier of the user, and the identifier of the user is used to determine the first historical call information from the historical call information of multiple users.

15. The method according to any one of claims 11 to 14, characterized in that, The first message includes a first parameter, and the first parameter is used to perform a restoration process on the historical call information of the user.

16. The method according to claim 15, wherein The restoration process includes decryption, decoding, or de - obfuscation.

17. The method according to any one of claims 11 to 16, characterized in that, The method further includes: Receive a fifth message from the SAAF, where the fifth message is used to request to store the text data of the user's first call; Based on the fifth message, store the text data of the first call; Send a sixth message to the SAAF, where the sixth message is used to indicate that the text data of the first call has been stored.

18. The method according to claim 17, wherein The fifth message includes the identifier of the user; Storing the text data of the first call based on the fifth message includes: Using the identifier of the user as the key and the text data of the first call as the value, and storing the text data of the first call in the form of key-value pairs.

19. The method according to claim 17 or 18, wherein The fifth message includes a second parameter, where the second parameter is used to perform protection processing on the text data of the first call; Storing the text data of the first call based on the fifth message includes: Performing protection processing on the text data of the first call based on the second parameter and then storing it.

20. The method according to claim 19, wherein The protection processing includes encryption, encoding, or obfuscation.

21. A communication device, characterized in that, Includes a module for implementing the method according to any one of claims 1 to 10, or a module for implementing the method according to any one of claims 11 to 20.

22. A communication device, characterized in that, Includes a processor, where the processor is coupled to a memory, and the memory is used to store programs or instructions. When the programs or instructions are executed by the processor, the method according to any one of claims 1 to 10 is executed, or the method according to any one of claims 11 to 20 is executed.

23. A computer-readable storage medium, characterized in that, For storing a computer program, when the computer program runs on a computer, the method according to any one of claims 1 to 10 is executed, or the method according to any one of claims 11 to 20 is executed.

24. A computer program product, characterized in that, Includes: A computer program or instruction, when the computer program or instruction is run, the method according to any one of claims 1 to 10 is executed, or the method according to any one of claims 11 to 20 is executed.

Images