Multi-terminal agent cooperative control method, device and system and electronic equipment

Abstract

The embodiment of the invention relates to a multi-terminal agent cooperative control method and device, electronic equipment and a storage medium. The method comprises the steps that instruction information input by a user is acquired; analyzing the instruction information, and determining at least one task to be executed; determining a target agent application corresponding to the at least one task and a target execution end where the target agent application is located; and calling the target agent application from the target execution end to execute the corresponding task, receiving calling result information returned after the target execution end executes the task; and generating feedback information for feeding back the task execution condition to the user based on the calling result information. According to the embodiment of the invention, the to-be-executed task can be allocated to the corresponding equipment, the to-be-executed task is executed by the corresponding agent application on the equipment, and seamless joint and intelligent cooperation of task execution are realized between the vehicle intelligent center and the multi-terminal equipment.

Description

Technical Field

[0001] The present application relates to the field of intelligent vehicle technology, and in particular to a multi-terminal intelligent collaborative control method, device, system and electronic equipment. Background Art

[0002] With the rapid development of smart car technology, in-vehicle systems are no longer isolated information units, but are gradually becoming deeply integrated with multiple devices such as mobile phones and smart homes. Users interact with devices such as mobile phones through the in-vehicle central system, allowing them to control the in-vehicle audio and video entertainment system and various devices on the vehicle. However, current in-vehicle central systems have some shortcomings: first, the collaborative interaction capabilities between the in-vehicle intelligent hub and multiple devices are limited, making it difficult to meet users' increasingly complex intelligent needs; second, there is a lack of an efficient and intelligent collaborative control system and method to achieve seamless connection and intelligent collaboration between the in-vehicle intelligent hub and multiple devices. Summary of the Invention

[0003] In view of this, in order to solve some or all of the above-mentioned technical problems, the embodiments of the present application provide a multi-terminal intelligent body collaborative control method, device, system and electronic device.

[0004] In the first aspect, an embodiment of the present application provides a multi-terminal intelligent agent collaborative control method, which includes: obtaining instruction information input by a user; parsing the instruction information to determine at least one task to be executed; determining the target intelligent agent application corresponding to at least one task, and the target execution terminal where the target intelligent agent application is located; calling the target intelligent agent application from the target execution terminal to execute the corresponding task; receiving the call result information returned by the target execution terminal after executing the task; and generating feedback information for feeding back the task execution status to the user based on the call result information.

[0005] In one possible implementation, the target intelligent agent application is called from the target execution end to execute the corresponding task, including: obtaining the user's corresponding historical record information; matching the task with the historical record information to obtain a first matching result; based on the first matching result, calling the target intelligent agent application from the target execution end to execute the corresponding task.

[0006] In one possible embodiment, based on the first matching result, the target intelligent agent application is called from the target execution end to execute the corresponding task, including: if the first matching result indicates that the historical record information does not contain parameters for executing the corresponding task, outputting a prompt message; obtaining the parameters entered by the user according to the prompt message, and based on the parameters, calling the target intelligent agent application from the target execution end to execute the task.

[0007] In one possible embodiment, based on the first matching result, the target intelligent agent application is called from the target execution end to execute the corresponding task, including: if the first matching result indicates that the historical record information contains parameters for executing the corresponding task, based on the parameters, the target intelligent agent application is called from the target execution end to execute the task.

[0008] In one possible embodiment, determining the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located, includes: matching at least one intelligent agent application annotation included in a preset knowledge base with at least one task to obtain a second matching result; determining the target intelligent agent application annotation corresponding to at least one task based on the second matching result; determining the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located based on the target intelligent agent application annotation.

[0009] In one possible embodiment, the knowledge base is pre-set according to the following steps: a registration operation is performed on the intelligent agent applications respectively set on at least one preset task execution end to parse each intelligent agent application to obtain the intelligent agent application annotation corresponding to each intelligent agent application; and the obtained intelligent agent application annotations are stored in the knowledge base.

[0010] In the second aspect, an embodiment of the present application provides a multi-terminal intelligent collaborative control system, which includes: a vehicle-used intelligent central device and at least two task execution terminals; the vehicle-used intelligent central device and at least two task execution terminals are communicatively connected; the vehicle-used intelligent central device is used to execute the above-mentioned multi-terminal intelligent collaborative control method.

[0011] On the third aspect, an embodiment of the present application provides a multi-terminal intelligent agent collaborative control device, which includes: an acquisition module for acquiring instruction information input by a user; a parsing module for parsing the instruction information and determining at least one task to be executed; a first determination module for determining the target intelligent agent application corresponding to at least one task, and the target execution terminal where the target intelligent agent application is located; a calling module for calling the target intelligent agent application from the target execution terminal to execute the corresponding task; a receiving module for receiving the call result information returned by the target execution terminal after executing the task; and a generation module for generating feedback information for feeding back the task execution status to the user based on the call result information.

[0012] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a memory for storing a computer program; a processor for executing the computer program stored in the memory, and when the computer program is executed, it implements the method of any embodiment of the multi-terminal intelligent body collaborative control method of the first aspect of the present application.

[0013] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements a method as in any embodiment of the multi-terminal intelligent agent collaborative control method of the first aspect mentioned above.

[0014] In a sixth aspect, an embodiment of the present application provides a computer program, which includes a computer-readable code. When the computer-readable code runs on a device, the processor in the device implements a method as in any embodiment of the multi-terminal intelligent agent collaborative control method of the first aspect mentioned above.

[0015] The multi-terminal intelligent agent collaborative control method, device, system and electronic device provided in the embodiments of the present application parse the instruction information input by the user to determine at least one task to be executed, determine the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located, call the target intelligent agent application from the target execution end to execute the corresponding task, and then receive the call result information returned by the target execution end after executing the task, and finally generate feedback information for feeding back the task execution status to the user based on the call result information. The embodiments of the present application realize the intention recognition of the user's instruction information, assign the task to be executed to the corresponding device, and execute it by the corresponding intelligent agent application on the device, thereby achieving more efficient multi-terminal collaborative interaction between the vehicle intelligent hub and devices such as vehicle computers and mobile phones, and realizing seamless docking and intelligent collaboration of task execution between the vehicle intelligent hub and multi-terminal devices. Various intelligent agent applications correspond to the tasks to be executed, thereby realizing modular design and facilitating the expansion of system functions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] One or more embodiments are exemplarily illustrated by pictures in the corresponding drawings. These exemplifications do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are represented as similar elements. Unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0019] Figure 1 A flowchart of a multi-terminal intelligent agent collaborative control method provided in an embodiment of the present application;

[0020] Figure 2 A flowchart of a second multi-agent collaborative control method provided in an embodiment of the present application;

[0021] Figure 3 A flowchart of a third multi-terminal intelligent agent collaborative control method provided in an embodiment of the present application;

[0022] Figure 4 A flowchart of a third multi-terminal intelligent agent collaborative control method provided in an embodiment of the present application;

[0023] Figure 5 A flowchart of a third multi-terminal intelligent agent collaborative control method provided in an embodiment of the present application;

[0024] Figure 6 This is an architecture diagram of a multi-terminal intelligent collaborative control system provided in an embodiment of the present application;

[0025] Figure 7 A schematic diagram of the structure of a multi-terminal intelligent collaborative control device provided in an embodiment of the present application;

[0026] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It is apparent that the described embodiments are only a portion of the embodiments of the present application, rather than all of the embodiments. It should be noted that, unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions, and numerical values ​​described in these embodiments do not limit the scope of the present application.

[0028] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present application are only used to distinguish between different steps, devices, modules and other objects, and neither represent any specific technical meaning nor indicate the logical order between them.

[0029] It should also be understood that in this embodiment, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0030] It should also be understood that any component, data or structure mentioned in the embodiments of the present application can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0031] In addition, the term "and / or" in this application is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the related objects are in an "or" relationship.

[0032] It should also be understood that the description of each embodiment in this application focuses on the differences between the embodiments, and the same or similar aspects can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0033] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0034] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods, and equipment should be considered part of the specification.

[0035] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0036] It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this application can be combined with each other. To facilitate understanding of the embodiments of this application, the application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0037] In order to solve the technical problem in the existing technology that the vehicle intelligent hub cannot efficiently interact with other devices, the present application provides a multi-terminal intelligent body collaborative control method. By setting different intelligent body applications on different device ends, the efficiency of collaborative interaction between the vehicle intelligent hub and car computers, mobile phones and other devices is improved.

[0038] Figure 1A flow chart of a multi-terminal intelligent collaborative control method provided for an embodiment of the present application. This method can be applied to vehicle control, and a vehicle intelligent central system is built in the controller. The vehicle intelligent central system is connected to one or more electronic devices such as smart phones, laptops, smart home appliances, servers, etc., and interacts with these devices. In addition, the execution subject of this method can be hardware or software. When the above-mentioned execution subject is hardware, the execution subject can be one or more of the above-mentioned electronic devices. For example, a single electronic device can execute this method, or multiple electronic devices can cooperate with each other to execute this method. When the above-mentioned execution subject is software, this method can be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0039] like Figure 1 As shown, the method specifically includes:

[0040] Step 101: Obtain instruction information input by the user.

[0041] In some embodiments, the electronic device executing this method can obtain various command information input by the user. For example, the type of command information input by the user may include, but is not limited to, at least one of the following: voice commands, gesture commands, text commands, etc. When this method is applied in a vehicle, the vehicle's on-board system can interact with the user through voice, gestures, etc., and the vehicle-mounted system can obtain the command information input by the user during the interaction.

[0042] Step 102: parse the instruction information to determine at least one task to be executed.

[0043] In some embodiments, the electronic device executing this method can analyze the intent of the instruction information based on its type, thereby identifying the user's needs and determining the task to be performed. For example, if the instruction information is a voice instruction, the vehicle system can perform ASR (Automatic Speech Recognition) processing on the voice instruction and convert it into a text instruction. The vehicle intelligent central system can use the intent recognition model to understand the intent of the text instruction and determine at least one task to be performed.

[0044] As an example, the at least one task mentioned above may include: controlling the equipment on the vehicle (such as adjusting the temperature of the vehicle air conditioner), controlling the user's mobile phone (such as calling the address book on the mobile phone), etc.

[0045] Step 103: Determine the target intelligent agent application corresponding to at least one task and the target execution end where the target intelligent agent application is located.

[0046] In some embodiments, the intelligent agent application is typically a software module with specific functions built based on a large language model. In this embodiment, multiple intelligent agent applications can be pre-set, and these intelligent agent applications are set on various terminal devices. The correspondence between different tasks and intelligent agent applications can be pre-set. Based on this correspondence, the target intelligent agent application corresponding to each task and the target execution terminal with the target intelligent agent application can be determined. The target execution terminal can be the electronic device that executes the present method itself, or it can be another electronic device.

[0047] As an example, if at least one task includes a task of controlling equipment on a vehicle, the target execution end includes a controller of the vehicle system; if at least one task includes a task of controlling a user's mobile phone, the target execution end includes the user's mobile phone.

[0048] As another example, the agent application in this embodiment can be built based on a related agent framework (e.g., LangChain) and a language model (e.g., Deepseek). The exemplary code is as follows:

[0049]

[0050]

[0051] Step 104: call the target agent application from the target execution end to execute the corresponding task.

[0052] In some embodiments, the electronic device executing the method can communicate with the target execution terminal to call the target agent application from the target execution terminal. The target execution terminal runs the target agent according to the received task parameters to perform the corresponding task.

[0053] As an example, if the task to be executed is to adjust the temperature of the vehicle air conditioner, the target execution end is the controller of the vehicle system. The electronic device that executes this method calls the intelligent application set on the vehicle system for controlling the air conditioner, and the vehicle system runs the intelligent application to complete the temperature control of the air conditioner.

[0054] For another example, if the task to be executed is to access a mobile phone's address book, the target execution end is the user's mobile phone. The electronic device executing this method calls an intelligent agent application configured on the user's mobile phone to control the address book. The user's mobile phone then runs the intelligent agent application based on the received parameters to complete the access to the address book.

[0055] As another example, the exemplary code executed using the target agent application (opening the air conditioner agent application) is as follows:

[0056] #User input

[0057] user_input="Turn on the air conditioner and set the temperature to 25 degrees"

[0058] #Agent handles user input

[0059] result=agent.run(user_input)

[0060] Step 105: Receive the call result information returned by the target execution end after executing the task.

[0061] In some embodiments, the target execution end runs the target agent application and, upon completing the task, can return information about the call result. For example, if the task to be executed is to adjust the temperature of the vehicle's air conditioner, the vehicle system will return information indicating that the temperature adjustment has been completed after completing the air conditioner temperature adjustment. For another example, if the task to be executed is to access the information of a contact in the address book, the user's phone will return the contact information required by the user after completing the address book access.

[0062] Step 106: Based on the call result information, feedback information is generated for feeding back the task execution status to the user.

[0063] In some embodiments, the feedback information may be in various forms, and the electronic device may display the feedback information to the user in various forms. For example, the feedback information may be voice information, and the electronic device may aggregate the received call result information, perform TTS (Text to Speech) speech synthesis, obtain voice feedback information, and play the voice feedback information.

[0064] The multi-terminal intelligent agent collaborative control method provided in the embodiment of the present application parses the instruction information input by the user to determine at least one task to be executed, determines the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located, calls the target intelligent agent application from the target execution end to execute the corresponding task, and then receives the call result information returned by the target execution end after executing the task. Finally, based on the call result information, feedback information for feeding back the task execution status to the user is generated. The embodiment of the present application realizes the intention recognition of the user's instruction information, assigns the task to be executed to the corresponding device, and executes it by the corresponding intelligent agent application on the device, thereby achieving more efficient multi-terminal collaborative interaction between the vehicle intelligent hub and devices such as vehicle computers and mobile phones, and realizing seamless docking and intelligent collaboration of task execution between the vehicle intelligent hub and multi-terminal devices. Various intelligent agent applications correspond to the tasks to be executed, thereby realizing modular design and facilitating the expansion of system functions.

[0065] In some optional implementations of this embodiment, such as Figure 2 As shown, step 104 includes:

[0066] Step 1041: Obtain the historical record information corresponding to the user.

[0067] The historical record information may include information recorded for the user's most frequently used operations. For example, the user's commonly set air conditioning temperature, the volume of a multimedia player, recorded contact information, etc. Alternatively, the historical record information may be user profile information, which records the parameters of the user's frequently used operations.

[0068] Step 1042: Match the task with the historical record information to obtain a first matching result.

[0069] Specifically, different tasks may correspond to different historical record information. For example, for a task of controlling an air conditioner, historical record information for the air conditioner control task may be obtained, and for a task of making a phone call, historical record information for the phone call operation record may be obtained.

[0070] Step 1043: Based on the first matching result, call the target agent application from the target execution end to execute the corresponding task.

[0071] The first matching result may indicate whether the historical record contains the required task parameters. Depending on whether the parameters are present, different operations may be performed. For example, if the recorded parameters are available, the task may be executed using them. If the recorded parameters are not available, the parameters may be retrieved from the command information entered by the user.

[0072] This embodiment can memorize the user's historical operations by pre-recording historical record information, so that when calling the target intelligent agent application, the corresponding task can be executed efficiently.

[0073] In some optional implementations of this embodiment, such as Figure 3 As shown, step 1043 includes:

[0074] Step 10431: If the first matching result indicates that the historical record information does not contain parameters for executing the corresponding task, output a prompt message.

[0075] The prompt information may be of various types, such as playing voice, displaying text on the screen, etc.

[0076] Step 10432, obtain the parameters entered by the user according to the prompt information, and based on the parameters, call the target intelligent agent application from the target execution end to execute the task.

[0077] As an example, the user issues a voice command "Help me turn on the air conditioner", and the electronic device executing this method will call the air conditioning control intelligent agent application in the vehicle system. The air conditioning control intelligent agent application will call the corresponding historical record information. If the historical record information does not contain the user's commonly used temperature parameters, the air conditioning control intelligent agent application will feedback relevant information to the electronic device executing this method. The electronic device outputs a voice prompt message "How many degrees does it need to be adjusted to?" The user continues to issue command information and input temperature parameters to the electronic device. The electronic device sends the temperature parameters to the vehicle end again, calls the air conditioning control intelligent agent application, and adjusts the air conditioning temperature according to the temperature parameters.

[0078] In the case where the historical record information does not contain the parameters required for executing the task, this embodiment continues to interact with the user to obtain the parameters, thereby making the method more adaptable to actual scenarios and more efficient in task execution.

[0079] In some optional implementations of this embodiment, such as Figure 3 As shown, step 1043 includes:

[0080] Step 10433: If the first matching result indicates that the historical record information contains parameters for executing the corresponding task, based on the parameters, the target intelligent agent application is called from the target execution end to execute the task.

[0081] Continuing with the above example, if the historical record information contains the temperature parameter that the user is accustomed to, the parameter can be directly called to set the air conditioner temperature to the user's accustomed temperature.

[0082] This embodiment can greatly improve the efficiency of executing tasks by directly calling the parameters when the historical record information contains the task parameters.

[0083] In some optional implementations of this embodiment, such as Figure 4 As shown, step 103 includes:

[0084] Step 1031 : Match at least one agent application annotation included in a preset knowledge base with at least one task to obtain a second matching result.

[0085] The agent application annotations are annotation information written into the method executed by the agent application when setting up various agent applications in advance. These annotation information can be pre-stored in the knowledge base.

[0086] Step 1032: Determine the target agent application annotation corresponding to at least one task according to the second matching result.

[0087] The knowledge base can record the correspondence between different task types and agent application annotations, and the electronic device can determine the target agent application annotation corresponding to each task based on the type of at least one of the above tasks.

[0088] Step 1033 , based on the target agent application annotation, determine the target agent application corresponding to at least one task and the target execution end where the target agent application is located.

[0089] The target agent application annotation includes relevant information about the target agent application and relevant information about the target execution end. The electronic device can determine the target agent and the target execution end based on this information.

[0090] As an example, the method annotation for operating the air conditioning agent application set up in the vehicle can be as follows:

[0091]

[0092] According to the task function represented by the annotation, the electronic device can match the task to be executed with it, thereby determining whether the task to be executed is implemented by the air conditioning operation agent application.

[0093] This embodiment saves the agent application annotations in the knowledge base in advance, so that when matching tasks and agent applications, the target agent application to be called is determined from the knowledge base, which facilitates the matching and dynamic calling of agent applications.

[0094] In some optional implementations of this embodiment, such as Figure 5 As shown, the knowledge base is pre-set according to the following steps:

[0095] Step 501: Perform a registration operation on the intelligent agent applications respectively set on at least one preset task execution terminal to parse each intelligent agent application and obtain the intelligent agent application annotation corresponding to each intelligent agent application.

[0096] Specifically, the registration operation establishes a connection between the electronic device executing the method of this embodiment and the agent application after each agent application is configured. Typically, the method executed by the agent application can be registered in a pre-set tool plug-in. During the registration process, the electronic device analyzes the method executed by the agent application and obtains the corresponding agent application annotation.

[0097] Step 502: store the obtained application annotations of each intelligent agent in the knowledge base.

[0098] This embodiment registers the intelligent agent application in advance, extracts the intelligent agent application annotations therefrom, and saves the intelligent agent annotations in the knowledge base, thereby realizing accurate and efficient saving of the intelligent agent application annotations of different terminals in the knowledge base, thereby improving the efficiency of cross-terminal calls of the intelligent agent application.

[0099] Figure 6 A multi-terminal intelligent collaborative control system is provided in an embodiment of the present application, and the system includes: a vehicle-use intelligent central device 601 and at least two task execution terminals 602; the vehicle-use intelligent central device 601 and at least two task execution terminals 602 are communicatively connected.

[0100] like Figure 6 As shown, the at least two task execution terminals 602 may include a vehicle terminal, a user mobile phone terminal, a cloud server, and other types of terminal devices. The multi-terminal intelligent collaborative control system is usually set on a vehicle cloud platform to realize remote control of the vehicle terminal, mobile phone terminal and other devices. The above-mentioned vehicle intelligent central device 601 is used to execute the above-mentioned multi-terminal intelligent collaborative control method, that is, the vehicle intelligent central device responds to the user's instructions, and according to the task to be executed, determines the target execution terminal and the target intelligent agent application from the at least two task execution terminals. After the target intelligent agent application completes the task, it returns the call result information, and the vehicle intelligent central device feedbacks the task execution status to the user.

[0101] Optionally, the at least two task execution terminals mentioned above, as well as the vehicle intelligent central device and the at least two task execution terminals, can communicate via a soft bus to achieve real-time and efficient transmission and sharing of data.

[0102] The multi-terminal intelligent collaborative control system provided by the embodiments of the present application utilizes a vehicle-based intelligent hub device and multiple intelligent applications on at least two task execution terminals. This allows for more efficient multi-terminal collaborative interaction between the vehicle-based intelligent hub and devices such as vehicle computers and mobile phones, achieving seamless integration and intelligent collaboration in task execution between the vehicle-based intelligent hub and multiple terminal devices. The various intelligent applications correspond to the tasks being executed, thus achieving a modular design and facilitating the expansion of system functionality.

[0103] Figure 7 This is a schematic diagram of the structure of a multi-terminal intelligent collaborative control device provided in an embodiment of the present application. Specifically comprising:

[0104] The acquisition module 701 is used to obtain the instruction information input by the user;

[0105] The parsing module 702 is used to parse the instruction information and determine at least one task to be executed;

[0106] A first determining module 703 is configured to determine a target agent application corresponding to at least one task and a target execution terminal where the target agent application is located;

[0107] The calling module 704 is used to call the target agent application from the target execution end to execute the corresponding task;

[0108] Receiving module 705, used to receive the call result information returned by the target execution end after executing the task;

[0109] The generating module 706 is configured to generate feedback information for feeding back the task execution status to the user based on the calling result information.

[0110] In one possible embodiment, the calling module includes: an acquisition unit for acquiring historical record information corresponding to the user; a matching unit for matching the task with the historical record information to obtain a first matching result; and a calling unit for calling the target intelligent agent application from the target execution end based on the first matching result to execute the corresponding task.

[0111] In one possible embodiment, the calling unit includes: an output sub-unit, used to output a prompt message if the first matching result indicates that the historical record information does not contain parameters for executing the corresponding task; a first calling sub-unit, used to obtain parameters entered by the user according to the prompt message, and based on the parameters, call the target intelligent agent application from the target execution end to execute the task.

[0112] In one possible embodiment, the calling unit includes: a second calling sub-unit, which is used to call the target intelligent agent application from the target execution end based on the parameters to execute the task if the first matching result indicates that the historical record information contains parameters for executing the corresponding task.

[0113] In one possible embodiment, the first determination module includes: a matching unit for matching at least one intelligent agent application annotation included in a preset knowledge base with at least one task to obtain a second matching result; a first determination unit for determining the target intelligent agent application annotation corresponding to at least one task based on the second matching result; and a second determination unit for determining the target intelligent agent application corresponding to at least one task and the target execution end where the target intelligent agent application is located based on the target intelligent agent application annotation.

[0114] In one possible embodiment, the knowledge base is pre-set according to the following steps: a registration operation is performed on the intelligent agent applications respectively set on at least one preset task execution end to parse each intelligent agent application to obtain the intelligent agent application annotation corresponding to each intelligent agent application; and the obtained intelligent agent application annotations are stored in the knowledge base.

[0115] The multi-terminal intelligent collaborative control device provided in this embodiment can be as follows Figure 7 The multi-terminal intelligent body collaborative control device shown in can execute all the steps of the above multi-terminal intelligent body collaborative control methods, thereby achieving the technical effects of the above multi-terminal intelligent body collaborative control methods. Please refer to the above relevant description for details. For the sake of simplicity, it will not be repeated here.

[0116] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 8 The electronic device 800 shown includes: at least one processor 801, a memory 802, at least one network interface 804 and another user interface 803. The various components in the electronic device 800 are coupled together via a bus system 805. It is understood that the bus system 805 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 805 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 805 is not shown in FIG. Figure 8 Various buses are labeled as bus system 805.

[0117] The user interface 803 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touchpad, or a touch screen).

[0118] It is understood that the memory 802 in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 802 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0119] In some embodiments, the memory 802 stores the following elements, executable units, or data structures, or a subset thereof, or an extended set thereof: an operating system 8021 and application programs 8022 .

[0120] The operating system 8021 includes various system programs, such as a framework layer, a core library layer, and a driver layer, for implementing various basic services and processing hardware-based tasks. The application program 8022 includes various application programs, such as a media player and a browser, for implementing various application services. The program implementing the method of the embodiment of the present application can be included in the application program 8022.

[0121] In this embodiment, by calling a program or instruction stored in the memory 802, specifically, a program or instruction stored in the application 8022, the processor 801 is configured to execute the method steps provided in each method embodiment, for example, including:

[0122] Obtain instruction information input by the user; parse the instruction information to determine at least one task to be executed; determine the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located; call the target intelligent agent application from the target execution end to execute the corresponding task; receive the call result information returned by the target execution end after executing the task; based on the call result information, generate feedback information for feeding back the task execution status to the user.

[0123] The methods disclosed in the above embodiments of the present application can be applied to or implemented by processor 801. Processor 801 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 801 or by software instructions. The above processor 801 can be a general-purpose processor, 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, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software units in the decoding processor. The software units can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 802 , and the processor 801 reads the information in the memory 802 and completes the steps of the above method in combination with its hardware.

[0124] It is understood that the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, or other electronic units or combinations thereof for performing the above-mentioned functions of the present application.

[0125] For software implementation, the techniques described above can be implemented by a unit that performs the functions described above. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0126] The electronic device provided in this embodiment may be Figure 8 The electronic device shown in can execute all the steps of the multi-terminal intelligent collaborative control methods described above, and thus achieve the technical effects of the multi-terminal intelligent collaborative control methods described above. Please refer to the above relevant description for details. For the sake of brevity, it will not be repeated here.

[0127] The present application also provides a storage medium (computer-readable storage medium). The storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and the memory may also include a combination of the aforementioned types of memory.

[0128] When one or more programs in the storage medium can be executed by one or more processors, the multi-terminal intelligent agent collaborative control method executed on the electronic device side can be implemented.

[0129] The processor is used to execute the program stored in the memory to implement the following steps of the multi-terminal intelligent agent collaborative control method performed on the electronic device side:

[0130] Obtain instruction information input by the user; parse the instruction information to determine at least one task to be executed; determine the target intelligent agent application corresponding to at least one task, and the target execution end where the target intelligent agent application is located; call the target intelligent agent application from the target execution end to execute the corresponding task; receive the call result information returned by the target execution end after executing the task; based on the call result information, generate feedback information for feeding back the task execution status to the user.

[0131] Professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0132] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0133] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "comprise", "include", "contain" and "have" are inclusive and therefore specify the presence of stated features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the specific order described or illustrated, unless the order of execution is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0134] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A multi-agent collaborative control method, characterized in that: The method comprises: Get the command information entered by the user; parsing the instruction information to determine at least one task to be performed; Determining a target agent application corresponding to each of the at least one task and a target execution end where the target agent application is located; Calling the target agent application from the target execution end to execute the corresponding task; Receive the call result information returned by the target execution end after executing the task; Based on the call result information, feedback information is generated for feeding back the task execution status to the user.

2. The method according to claim 1, characterized in that The calling of the target agent application from the target execution end to execute the corresponding task includes: Obtaining historical record information corresponding to the user; Matching the task with the historical record information to obtain a first matching result; Based on the first matching result, the target agent application is called from the target execution end to execute the corresponding task.

3. The method according to claim 2, characterized in that The calling the target agent application from the target execution end based on the first matching result to execute the corresponding task includes: If the first matching result indicates that the historical record information does not contain parameters for executing the corresponding task, output a prompt message; Obtain the parameters input by the user according to the prompt information, and based on the parameters, call the target agent application from the target execution end to execute the task.

4. The method according to claim 2, characterized in that The calling the target agent application from the target execution end based on the first matching result to execute the corresponding task includes: If the first matching result indicates that the historical record information contains parameters for executing the corresponding task, based on the parameters, the target agent application is called from the target execution end to execute the task.

5. The method according to claim 1, wherein The determining of the target agent application corresponding to each of the at least one task and the target execution end where the target agent application is located includes: Matching at least one agent application annotation included in a preset knowledge base with the at least one task to obtain a second matching result; Determining target agent application annotations corresponding to the at least one task according to the second matching result; According to the target agent application annotation, the target agent application corresponding to the at least one task and the target execution end where the target agent application is located are determined.

6. The method according to claim 5, characterized in that The knowledge base is pre-configured according to the following steps: Performing a registration operation on the intelligent agent applications respectively set on at least one preset task execution end to parse each intelligent agent application and obtain intelligent agent application annotations corresponding to each intelligent agent application; The obtained application annotations of each intelligent agent are stored in the knowledge base.

7. A multi-agent collaborative control system, characterized in that: The system includes: a vehicle-use intelligent central device and at least two task execution terminals; the vehicle-use intelligent central device and the at least two task execution terminals are communicatively connected; The vehicle-use intelligent central device is used to execute the multi-terminal intelligent collaborative control method described in any one of claims 1-6.

8. A multi-terminal intelligent collaborative control device, characterized in that: The device comprises: The acquisition module is used to obtain the instruction information input by the user; A parsing module, configured to parse the instruction information and determine at least one task to be executed; A first determining module is configured to determine a target agent application corresponding to each of the at least one task and a target execution terminal where the target agent application is located; A calling module, configured to call the target agent application from the target execution end to execute the corresponding task; A receiving module, configured to receive the call result information returned by the target execution end after executing the task; A generating module is used to generate feedback information for feeding back the task execution status to the user based on the calling result information.

9. An electronic device, characterized in that: include: memory for storing computer programs; A processor is used to execute the computer program stored in the memory, and when the computer program is executed, it implements the multi-terminal intelligent agent collaborative control method described in any one of claims 1 to 6 above.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the multi-terminal intelligent agent collaborative control method described in any one of claims 1-6 is implemented.

Images