Personality-based dialogue processing methods and systems, intelligent agents, and electronic devices.

Abstract

This disclosure provides a dialogue processing method and system, intelligent agent, and electronic device based on personality characteristics. The dialogue processing method applied to the master intelligent agent includes the following steps: responding to target information input by the user in the current dialogue round, determining the user's target sub-personality characteristics based on the perceived current scene and the user's master personality characteristics; and processing the target information based on the master personality characteristics and the target sub-personality characteristics. In processing the target information input by the user in the current dialogue round, this disclosure combines the user's master personality characteristics with the target sub-personality characteristics determined in the current scene to assign personality characteristics, enabling the provision of personalized services that match the current scene, satisfying the user's emotional needs in different scenarios, and improving the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a dialogue processing method and system based on personality characteristics, an intelligent agent, and an electronic device. Background Technology

[0002] With the rapid development of artificial intelligence technology, native operating systems driven by AI are gradually becoming the cornerstone of the next generation of human-computer interaction. These systems construct a collaborative ecosystem covering multiple terminal devices such as smartphones, smart glasses, smart home assistants, and in-vehicle systems. Within this ecosystem, each terminal device is typically driven by a specific intelligent agent with different functional focuses.

[0003] Currently, to achieve brand experience consistency, multi-terminal ecosystems typically use a uniform personality configuration for agents across all devices. However, this approach becomes rigid and unsuitable when faced with frequently changing user behavior scenarios and complex task transitions. For example, when interacting with an in-vehicle agent while driving, users need a concise, efficient, and safe "professional assistant" personality; while at home, interacting with a family assistant might require a relaxed, humorous, and emotionally resonant "life companion" personality. Forcing a uniform personality designed for mobile scenarios results in stiff and impersonal interactions in home settings; conversely, using a uniformly relaxed personality becomes redundant and unprofessional in efficient scenarios like driving or working. This leads to contextual mismatches in agent responses, failing to meet users' emotional needs in different scenarios and thus degrading the user experience. Summary of the Invention

[0004] The technical problem to be solved by this disclosure is to overcome the shortcomings of the existing technology in which uniform personality traits cannot meet the emotional needs of users in different scenarios, and to provide a dialogue processing method and system, intelligent agent and electronic device based on personality traits.

[0005] This disclosure solves the above-mentioned technical problems through the following technical solution:

[0006] The first aspect of this disclosure provides a dialogue processing method based on personality characteristics, applied to a controlling intelligent agent, the dialogue processing method comprising the following steps:

[0007] In response to the target information input by the user in this round of dialogue, the target sub-personality characteristics of the user are determined based on the perceived current scene and the user's primary personality characteristics;

[0008] The target information is processed based on the master personality characteristics and the target sub-personality characteristics.

[0009] Optionally, the dialogue processing method further includes: synchronously sending the master personality feature and the target sub-personality feature to at least one executive agent corresponding to the user;

[0010] The processing of the target information based on the master personality characteristics and the target sub-personality characteristics specifically includes:

[0011] Obtain historical content that matches the target information;

[0012] Based on the historical content, formulate processing tasks corresponding to the target information;

[0013] A target agent is determined from at least one executive agent corresponding to the user, and the processing task is dispatched to the target agent;

[0014] Receive and output the results of the target intelligent agent performing the processing task based on the master personality characteristics and the target sub-personality characteristics.

[0015] Optionally, obtaining historical content matching the target information specifically includes:

[0016] Convert the target information into a vector;

[0017] Query the historical content that matches the vector in the vector database and the knowledge graph, respectively.

[0018] Optionally, the dialogue processing method further includes: obtaining reference information; the reference information includes contextual information in the current dialogue and / or preset sub-personality characteristics corresponding to the current scenario;

[0019] The step of determining the user's target sub-personality characteristics based on the perceived current scene and the user's primary personality characteristics specifically includes: determining the user's target sub-personality characteristics based on the perceived current scene, the user's primary personality characteristics, and the reference information.

[0020] Optionally, the user's dominant personality traits are obtained based on a personality model, and the dialogue processing method further includes:

[0021] The user's behavioral intent is generated based on each round of dialogue;

[0022] The personality model is updated based on the user's behavioral intentions.

[0023] A second aspect of this disclosure provides an intelligent agent, comprising:

[0024] The determination module is used to determine the user's target sub-personality characteristics in response to the target information input by the user in the current round of dialogue, based on the perceived current scene and the user's main personality characteristics.

[0025] The processing module is used to process the target information based on the master personality characteristics and the target sub-personality characteristics.

[0026] Optionally, the intelligent agent further includes: a sending module, configured to synchronously send the master personality feature and the target sub-personality feature to at least one executing intelligent agent corresponding to the user;

[0027] The processing module specifically includes:

[0028] The acquisition unit is used to acquire historical content that matches the target information;

[0029] A formulating unit is used to formulate processing tasks corresponding to the target information based on the historical content.

[0030] A dispatching unit is configured to determine a target agent from at least one executing agent corresponding to the user, and dispatch the processing task to the target agent.

[0031] The output unit is used to receive and output the result of the target intelligent agent performing the processing task based on the master personality characteristics and the target sub-personality characteristics.

[0032] Optionally, the acquisition unit is specifically used to convert the target information into a vector, and to query historical content that matches the vector in the vector database and the knowledge graph, respectively.

[0033] Optionally, the intelligent agent further includes: an acquisition module, used to acquire reference information; the reference information includes context information in the current round of dialogue and / or preset sub-personality characteristics corresponding to the current scene;

[0034] The determining module is specifically used to determine the user's target sub-personality characteristics based on the perceived current scene, the user's primary personality characteristics, and the reference information.

[0035] Optionally, the user's dominant personality traits are obtained based on a personality model, and the intelligent agent further includes an update module for generating the user's behavioral intentions based on each round of dialogue and updating the personality model based on the user's behavioral intentions.

[0036] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein the processor executes the computer program to implement the dialogue processing method described in the first aspect.

[0037] A fourth aspect of this disclosure provides a dialogue processing system based on personality characteristics, including a data access module, the electronic device described in the third aspect, and at least one terminal device, wherein the terminal device is used to communicate with the electronic device through the data access module;

[0038] The intelligent agent on the terminal device is used to receive the target information input by the user in the current round of dialogue and send the target information to the main intelligent agent on the electronic device.

[0039] The master control agent on the electronic device is used to synchronously send the user's master personality characteristics and target sub-personality characteristics to the agent on the terminal device.

[0040] The fifth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dialogue processing method described in the first aspect.

[0041] A sixth aspect of this disclosure provides a computer program product including a computer program that, when executed by a processor, implements the dialogue processing method described in the first aspect.

[0042] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this disclosure.

[0043] The positive and progressive effects of this disclosure are as follows: In the process of processing the target information input by the user in this round of dialogue, the user's main personality characteristics and the target sub-personality characteristics determined in the current scenario are combined to assign personality characteristics to the user, which can provide the user with personalized services that match the current scenario, meet the user's emotional needs in different scenarios, and improve the user experience. Attached Figure Description

[0044] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0045] Figure 1 A structural block diagram of a dialogue processing system based on personality characteristics provided for an exemplary embodiment of this disclosure;

[0046] Figure 2 A flowchart illustrating a dialogue processing method based on personality traits, provided as an exemplary embodiment of this disclosure;

[0047] Figure 3 A flowchart illustrating step S12 provided for an exemplary embodiment of this disclosure;

[0048] Figure 4 This is a structural block diagram of a dialogue processing device based on personality characteristics, provided as an exemplary embodiment of the present disclosure.

[0049] Figure 5 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present disclosure. Detailed Implementation

[0050] The present disclosure is further illustrated below by way of embodiments, but the present disclosure is not limited to the scope of the embodiments described herein.

[0051] The prefixes such as "first" and "second" used in this disclosure are merely for distinguishing different descriptive objects and do not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes used to distinguish descriptive objects in this disclosure does not constitute a limitation on the described objects. The description of the described objects is given in the claims or the context of the embodiments, and should not be construed as an unnecessary limitation. Furthermore, in the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0052] In this embodiment of the disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good morals.

[0053] like Figure 1 As shown, the personality-based dialogue processing system disclosed in this embodiment includes an electronic device 11, a data access module 12, and at least one terminal device 13. The terminal device 13 communicates with the electronic device 11 via the data access module 12. Each terminal device and electronic device is driven by a specific intelligent agent. In this embodiment, the intelligent agent on the electronic device is the master intelligent agent, and the intelligent agent on the terminal device is the executive intelligent agent. In some examples, these intelligent agents integrate a Large Language Model (LLM). In some examples, the terminal device can be a smartphone, smart glasses, a smart home assistant, an in-vehicle system, etc. In some examples, the data access module can be a gateway.

[0054] Figure 2This is a flowchart illustrating a personality-based dialogue processing method as an exemplary embodiment of the present disclosure. This dialogue processing method can be executed by a dialogue processing device, which can be implemented through software and / or hardware. The dialogue processing device can be part of an electronic device (e.g., a master intelligent agent on the electronic device) or all of it. The dialogue processing method provided in this embodiment is described below with the master intelligent agent as the executing entity.

[0055] like Figure 2 As shown, the dialogue processing method based on personality characteristics provided in this embodiment may include the following steps S11~S12:

[0056] Step S11: In response to the target information input by the user in this round of dialogue, determine the user's target sub-personality characteristics based on the perceived current scene and the user's primary personality characteristics.

[0057] In this dialogue, the target information input by the user can include questions, instructions, creation and generation requests, statements, and declarations. In practical applications, an intelligent agent on the terminal device receives the dialogue initiated by the user and the information input in each round of dialogue, and forwards the received information to the master intelligent agent on the electronic device via a data access module. In specific implementations, each user corresponds to a unique user ID. In some examples, the data access module forwards the received information to the master intelligent agent after verifying the user's identity (i.e., verifying the user ID).

[0058] In some examples, the scenarios mentioned above include meeting assistant scenarios, intelligent reminder scenarios, emotional companionship scenarios, learning assistance scenarios, and travel assistant scenarios. In some examples, the current scene can be perceived by calling a scene recognition engine. In specific implementations, the scene recognition engine can perceive the current scene based on input information such as hardware input information, software input information, location information, and time information of the terminal device. In some examples, the scene recognition engine integrates a large language model, which perceives the current scene based on the aforementioned input information. In some examples, the hardware input information of the terminal device can include sound collected by the microphone, images captured by the camera, acceleration measured by the accelerometer, etc. In some examples, the software information of the terminal device can include the currently activated application type, the current system state such as sleep mode, do not disturb mode, etc., and the user's behavior patterns in the application, etc. In some examples, the location information of the terminal device can include office, train station, museum, outdoors, etc. In some examples, the time information of the terminal device can include morning, noon, afternoon, night, etc.

[0059] The personality traits involved in this disclosure include, but are not limited to, user expression style preferences (e.g., euphemistic expression, clear logic, humor, etc.), emotional tone (e.g., optimistic, cautious, empathetic, etc.), language habits (e.g., preference for analogies, use of questions, emphasis on details, etc.), long-term values ​​(e.g., efficiency first, results-oriented, safety first, etc.), tone of voice, and speaking speed. The primary personality trait of a user refers to a long-term, stable personality trait that does not change with different scenarios or devices, and this primary personality trait corresponds one-to-one with the user ID. The target sub-personality trait of a user refers to a short-term, flexible personality trait that changes with the current scenario.

[0060] In some examples, the user's dominant personality traits are actively set by the user. In some examples, the user's dominant personality traits are obtained based on a personality model. In some examples, the user's interaction information with various terminal devices, the user's behavioral characteristics, the user's actively set preference tags, the perceived current scene, and style tags predicted based on context can be used as input information for the personality model. The personality model processes the input information to obtain the user's dominant personality traits. The interaction information between the user and various terminal devices can include the user's historical dialogues with agents on each terminal device. The user's behavioral characteristics can include actions such as whether the user accepts recommendations or interrupts the agent's reasoning process. In some examples, the aforementioned personality model integrates a large language model, and the user's dominant personality traits are obtained by processing the input information based on the large language model.

[0061] Step S12: Process the target information based on the master personality characteristics and the target sub-personality characteristics. In specific implementation, during the processing of the target information, the user's master personality characteristics and the target sub-personality characteristics determined in the current scenario are combined to assign personality characteristics to the user. This can provide the user with personalized services that match the current scenario, meet the user's emotional needs in different scenarios, and improve the user experience.

[0062] In an optional implementation, the dialogue processing method further includes: synchronously sending the master personality feature and the target sub-personality feature to at least one executive agent corresponding to the user. It should be noted that each executive agent integrates a large language model and is capable of independently completing complex natural language understanding and generation tasks. In some examples, the at least one executive agent may include agents on the aforementioned terminal device and / or other agents besides those on the aforementioned terminal device. In specific implementations, each executive agent corresponds to a unique agent ID. In this implementation, as... Figure 3 As shown, step S12 specifically includes the following steps S21~S24:

[0063] Step S21: Obtain historical content that matches the target information.

[0064] Step S22: Formulate a processing task corresponding to the target information based on the historical content.

[0065] Step S23: Determine the target agent from at least one execution agent corresponding to the user, and dispatch the processing task to the target agent. In specific implementations, the target agent can be determined based on the functions of different execution agents and the requirements of the processing task.

[0066] In some examples, the number of target agents is one. In specific implementations, the processing task is directly assigned to the target agent.

[0067] In some examples, the number of target agents is two or more. In specific implementations, the processing task is broken down into sub-tasks with different requirements, and the sub-tasks are dispatched to the target agents corresponding to the different requirements.

[0068] Step S24: Receive and output the result of the target intelligent agent performing the processing task based on the master personality characteristics and the target sub-personality characteristics. In a specific implementation, the target intelligent agent performs the processing task based on the master personality characteristics and the target sub-personality characteristics, and feeds back the result of performing the processing task to the master intelligent agent.

[0069] In one example, a user engages in a dialogue through Agent 1 on a terminal device. Agent 1 receives target information input by the user during the current dialogue round and sends this target information to a data access module. The data access module verifies the user's identity based on the user ID carried in the target information. After successful verification, the target information is forwarded to the controlling agent Agent 2. Agent 2 formulates a processing task based on historical content matching the target information, breaks it down into three sub-tasks, and dispatches them to executing agents Agent 3, Agent 4, and Agent 5 respectively. After completing the sub-tasks, Agent 3, Agent 4, and Agent 5 report the execution results back to Agent 2. Finally, Agent 2 returns the execution results to Agent 1 through the data access module, thus completing the dialogue process between the user and Agent 1.

[0070] In one optional implementation, step S21 specifically includes: converting the target information into a vector, and querying historical content matching the vector in both a vector database and a knowledge graph. In a specific implementation, the target information is converted into a semantic vector, and historical content matching the semantic vector is queried from the vector database; and the target information is converted into a node vector, and historical content matching the node vector is queried from the knowledge graph.

[0071] In some examples, the vector database and knowledge graph can be queried by calling the memory management service. The vector database stores semantic vectors containing historical dialogues and their corresponding processing results, preference selections, and other information. The knowledge graph uses the user ID as the root node and stores structured information such as user preferences, behavioral paths, and task measurements. In some examples, the knowledge graph stores structured information in the form of triples, such as (User A, Preference, Concise Expression), (User A, Execute Task, Schedule Reminder), (User A, Reject, Lengthy Suggestion), etc.

[0072] In this implementation, combining a vector database and a structured knowledge graph for dual information storage enhances the semantic expressiveness and knowledge controllability of the dialogue processing system.

[0073] In an optional implementation, the dialogue processing method further includes: obtaining reference information; the reference information includes contextual information in the current dialogue and / or preset sub-personality characteristics corresponding to the current scenario. In this implementation, in order to make the target sub-personality characteristics more closely match the user's actual needs, step S11 specifically includes: determining the user's target sub-personality characteristics based on the perceived current scenario, the user's dominant personality characteristics, and the reference information.

[0074] In practice, each round of dialogue corresponds to a unique dialogue ID, and the context information of the current round of dialogue can be obtained based on the dialogue ID. In some examples, the context information of the current round of dialogue can be obtained by querying the vector database and knowledge graph through the memory management service.

[0075] In practice, different scenarios can be pre-defined to correspond to preset sub-personality traits. In some examples, the preset sub-personality traits corresponding to the meeting assistant scenario include conciseness, formality, and conclusion orientation; the preset sub-personality traits corresponding to the emotional companionship scenario include slow speech and comforting content; the preset sub-personality traits corresponding to the travel assistant scenario include clear instructions and rapid feedback; and the preset sub-personality traits corresponding to the static companionship scenario include non-disturbing and maintaining a consistent tone of voice.

[0076] In an optional implementation, the dialogue processing method further includes: generating the user's behavioral intent based on each round of dialogue, and updating the personality model based on the user's behavioral intent. It should be noted that updating the personality model means that its output primary personality traits will also be updated. When the user's primary personality traits are updated, the controlling agent synchronously sends the primary personality traits to all executing agents corresponding to the user, so that each executing agent can adopt a unified primary personality trait.

[0077] Based on the above embodiments of the dialogue processing method, this disclosure also provides a dialogue processing apparatus based on personality characteristics, such as... Figure 4 As shown, the system includes a determining module 41 and a processing module 42. The determining module is used to determine the user's target sub-personality characteristics based on the perceived current scene and the user's primary personality characteristics in response to the target information input by the user in the current round of dialogue. The processing module is used to process the target information based on the primary personality characteristics and the target sub-personality characteristics.

[0078] In one alternative implementation, such as Figure 4 As shown, the dialogue processing device further includes a sending module 43, used to synchronously send the master personality feature and the target sub-personality feature to at least one executive agent corresponding to the user. In this implementation, the processing module specifically includes an acquisition unit, a formulation unit, a dispatch unit, and an output unit. The acquisition unit is used to acquire historical content matching the target information. The formulation unit is used to formulate a processing task corresponding to the target information based on the historical content. The dispatch unit is used to determine the target agent from at least one executive agent corresponding to the user and dispatch the processing task to the target agent. The output unit is used to receive and output the result of the target agent executing the processing task based on the master personality feature and the target sub-personality feature.

[0079] In one optional implementation, the acquisition unit is specifically used to convert the target information into a vector, and to query historical content that matches the vector in the vector database and the knowledge graph, respectively.

[0080] In one alternative implementation, such as Figure 4 As shown, the dialogue processing device further includes an acquisition module 44, used to acquire reference information; the reference information includes context information in the current round of dialogue and / or preset sub-personality characteristics corresponding to the current scene. In this implementation, the determining module is specifically used to determine the user's target sub-personality characteristics based on the perceived current scene, the user's dominant personality characteristics, and the reference information.

[0081] In one alternative implementation, the user's dominant personality traits are obtained based on a personality model, and the dialogue processing device further includes an update module for generating the user's behavioral intentions based on each round of dialogue and updating the personality model based on the user's behavioral intentions.

[0082] It should be noted that the dialogue processing device in this embodiment can be a separate chip, chip module or electronic device, or it can be a chip or chip module integrated into an electronic device.

[0083] Regarding the various modules / units included in the dialogue processing device described in this embodiment, they may be software modules / units, hardware modules / units, or a combination of both.

[0084] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs.

[0085] Figure 5 This is a schematic diagram of an electronic device provided as an exemplary embodiment of the present disclosure. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the steps of the aforementioned dialogue processing method. Figure 5 The electronic device 3 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0086] The components of the electronic device 3 may include, but are not limited to: at least one processor 4, at least one memory 5, and a bus 6 connecting different system components (including memory 5 and processor 4).

[0087] Bus 6 includes a data bus, an address bus, and a control bus.

[0088] The memory 5 may include volatile memory, such as random access memory (RAM) 51 and / or cache memory 52, and may further include read-only memory (ROM) 53.

[0089] The memory 5 may also include a program tool 55 having a set (at least one) of program modules 54, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0090] Processor 4 executes various functional applications and data processing, such as the dialogue processing method described above, by running computer programs stored in memory 5.

[0091] Electronic device 3 can also communicate with one or more external devices 7 (e.g., keyboard, pointing device, etc.). This communication can be performed through input / output (I / O) interface 8. Furthermore, electronic device 3 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 9. Figure 5 As shown, network adapter 9 communicates with other modules of electronic device 3 via bus 6. It should be understood that, although... Figure 5 Not shown, it can be combined with electronic device 3 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0092] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0093] An exemplary embodiment of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described dialogue processing method.

[0094] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0095] In possible implementations, this disclosure can also be implemented as a computer program product comprising a computer program that, when executed by a processor, implements the steps of the above-described dialogue processing method.

[0096] The computer program for executing the present disclosure can be written in any combination of one or more programming languages, and the computer program can be executed entirely on an electronic device, partially on an electronic device, as a stand-alone software package, partially on an electronic device and partially on a remote device, or entirely on a remote device.

[0097] While specific embodiments of this disclosure have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of this disclosure is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of this disclosure, but all such changes and modifications fall within the scope of protection of this disclosure.

Claims

1. A dialogue processing method based on personality traits, characterized in that, Applied to a master control agent running on an electronic device, the dialogue processing method includes the following steps: In response to the target information input by the user in this round of dialogue, the target sub-personality characteristics of the user are determined based on the perceived current scene and the user's primary personality characteristics; The target information is processed based on the master personality characteristics and the target sub-personality characteristics; The dialogue processing method further includes: synchronously sending the master personality feature and the target sub-personality feature to at least one execution agent corresponding to the user, wherein the execution agent runs on a terminal device; The processing of the target information based on the master personality characteristics and the target sub-personality characteristics specifically includes: Obtain historical content that matches the target information; Based on the historical content, formulate processing tasks corresponding to the target information; A target agent is determined from at least one executive agent corresponding to the user, and the processing task is dispatched to the target agent; Receive and output the results of the target intelligent agent performing the processing task based on the master personality characteristics and the target sub-personality characteristics.

2. The dialogue processing method as described in claim 1, characterized in that, The acquisition of historical content matching the target information specifically includes: Convert the target information into a vector; Query the historical content that matches the vector in the vector database and the knowledge graph, respectively.

3. The dialogue processing method as described in claim 1, characterized in that, The dialogue processing method further includes: obtaining reference information; the reference information includes contextual information in the current round of dialogue and / or preset sub-personality characteristics corresponding to the current scenario; The step of determining the user's target sub-personality characteristics based on the perceived current scene and the user's primary personality characteristics specifically includes: determining the user's target sub-personality characteristics based on the perceived current scene, the user's primary personality characteristics, and the reference information.

4. The dialogue processing method as described in any one of claims 1-3, characterized in that, The user's dominant personality traits are obtained based on a personality model, and the dialogue processing method further includes: The user's behavioral intent is generated based on each round of dialogue; The personality model is updated based on the user's behavioral intentions.

5. A master control intelligent agent, characterized in that, The main control agent runs on the electronic device, and the main control agent includes: The determination module is used to determine the user's target sub-personality characteristics in response to the target information input by the user in the current round of dialogue, based on the perceived current scene and the user's main personality characteristics. The processing module is used to process the target information based on the master personality characteristics and the target sub-personality characteristics; The sending module is used to synchronously send the master personality feature and the target sub-personality feature to at least one execution agent corresponding to the user, wherein the execution agent runs on the terminal device; The processing module includes: The acquisition unit is used to acquire historical content that matches the target information; A formulating unit is used to formulate processing tasks corresponding to the target information based on the historical content. A dispatching unit is configured to determine a target agent from at least one executing agent corresponding to the user, and dispatch the processing task to the target agent. The output unit is used to receive and output the result of the target intelligent agent performing the processing task based on the master personality characteristics and the target sub-personality characteristics.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the dialogue processing method according to any one of claims 1-4.

7. A dialogue processing system based on personality traits, characterized in that, It includes a data access module, an electronic device as described in claim 6, and at least one terminal device, wherein the terminal device is used to communicate with the electronic device through the data access module; The execution agent on the terminal device is used to receive the target information input by the user in the current round of dialogue and send the target information to the main control agent on the electronic device. The master control agent on the electronic device is used to synchronously send the user's master personality characteristics and target sub-personality characteristics to the execution agent on the terminal device.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the dialogue processing method according to any one of claims 1-4.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the dialogue processing method as described in any one of claims 1-4.

Images