Space task processing method, electronic device, and storage medium

Abstract

Embodiments of the present application provide a space task processing method, an electronic device and a storage medium, relating to the technical field of artificial intelligence, the method comprising: in response to the existence of a target task in a task set of a target space satisfying an execution condition, determining description information of the target task according to a digital model of the target space, the digital model being used to describe a plurality of attributes of the target space, the plurality of attributes including a task attribute of the task set; calling a large language model, and determining execution information of the target task according to the description information; and executing the target task according to the execution information. In the technical solution of the embodiments of the present application, digital representation of the space is realized, thereby realizing intelligent processing of the space task and improving the intelligent management level of the space.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method for processing space missions, an electronic device, and a storage medium. Background Technology

[0002] As people's demands for quality of life continue to rise, the automated control of spatial comfort in living and working environments has gradually become a research hotspot. However, due to factors such as the diversity of spatial data, the uncertainty of spatial uses, and the variability of spatial events, there is currently no mature solution to improve the level of intelligent spatial control. Summary of the Invention

[0003] This application provides a space mission processing method, electronic device, and storage medium to alleviate or solve one or more technical problems existing in the prior art.

[0004] In a first aspect, embodiments of this application provide a method for processing space missions, including:

[0005] In response to the existence of a target task that meets the execution conditions in the task set of the target space, the description information of the target task is determined according to the digital model of the target space. The digital model is used to describe multiple attributes of the target space, including the task attributes of the task set.

[0006] The large language model is invoked to determine the execution information of the target task based on the description information;

[0007] The target task is executed based on the execution information.

[0008] Secondly, embodiments of this application provide a processing apparatus for a space mission, comprising:

[0009] The first determining module is configured to, in response to the existence of a target task satisfying the execution conditions in the task set of the target space, determine the description information of the target task according to the digital model of the target space, wherein the digital model is used to describe multiple attributes of the target space, and the multiple attributes include the task attributes of the task set;

[0010] The calling module is used to call the large language model and determine the execution information of the target task based on the description information;

[0011] An execution module is used to execute the target task based on the execution information.

[0012] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor implements any of the methods of embodiments of this application when executing the computer program.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method of any one of the embodiments of this application.

[0014] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, implements any of the methods described in the embodiments of this application.

[0015] In the technical solution provided in this application, multiple attributes of the target space are described by a digital model, enabling a comprehensive and accurate definition of the target space based on the digital model, thus achieving a digital representation of the space. Since the multiple attributes of the target space described by the digital model include task attributes of the task set, when there are target tasks in the task set of the target space that meet the execution conditions, the description information of the target task can be accurately determined based on the digital model. This allows the large language model to be invoked to determine the execution information of the target task based on the description information and execute the target task. In other words, by combining the digital model of the target space with the large language model, the automated and intelligent processing of tasks in the target space can be achieved based on the comprehensive spatial description and the powerful understanding capabilities of the large language model, thereby improving the level of intelligent management of the target space.

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application, it can be implemented according to the contents of the specification. In order to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0017] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the various drawings denote the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings depict only some embodiments according to this application and should not be construed as limiting the scope of this application.

[0018] Figure 1 A schematic diagram of a space mission processing scenario provided in an embodiment of this application is shown;

[0019] Figure 2 A flowchart illustrating the space mission processing method provided in an embodiment of this application is shown;

[0020] Figure 3 A schematic diagram of the digital model provided in an embodiment of this application is shown;

[0021] Figure 4 A schematic diagram of spatial elements provided in an embodiment of this application is shown;

[0022] Figure 5 A schematic diagram of a space mission processing method provided in an embodiment of this application is shown;

[0023] Figure 6 A block diagram of a space mission processing apparatus provided in an embodiment of this application is shown;

[0024] Figure 7 A block diagram of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0025] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the concept or scope of this application. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0026] First, the terms used in the embodiments of this application are explained as follows:

[0027] Large Language Model (LLM): A neural network based on Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies, capable of understanding, generating, and reasoning about human language.

[0028] Digital model: A data structure that describes spatial attributes, which can define the intelligentization and linkage strategies of space from dimensions such as basic information, spatial elements, spatial events, spatial tasks, and spatial tools.

[0029] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and all of them fall within the protection scope of the embodiments of this application.

[0030] To enhance user comfort in environments such as homes and offices, several intelligent space management methods have been proposed. One approach involves using algorithms configured in smart devices to identify the surrounding environment and then controlling the device based on the identification results. This method is simple and easy to implement, requiring no additional software or hardware support, but it can only control the device itself and cannot interact with other devices. Another approach involves smart devices collecting environmental information and sending it to the cloud. Various algorithms in the cloud process the information and then send control commands to the devices via the network. However, this method requires developing different algorithms for different scenarios. A third approach standardizes device access and command issuance through an IoT platform and allows for the addition of linkage rules on the platform side, achieving a degree of automation and intelligence. However, these linkage rules rely on hard-coded or fixed processes, lacking flexibility and sufficient intelligence.

[0031] In view of this, embodiments of this application provide a method for processing space tasks, an electronic device, and a storage medium, aiming to realize the digital representation of space, thereby achieving automated and intelligent processing of tasks in space and improving the level of intelligent management of space. The following is a detailed description.

[0032] Figure 1 The illustration shows an application scenario diagram of a space mission processing method provided in an embodiment of this application, such as... Figure 1 As shown, the scenario includes electronic devices, which can be terminal devices such as mobile phones, tablets, desktop computers, laptops, and vehicle terminals, or physical servers, cloud servers that perform cloud computing, etc. Figure 1 The example given is a physical server; it should be understood that... Figure 1 For illustrative purposes only and not as a limitation, this scenario may include more or fewer components. As an example, the scenario may also include a client that a user can operate to send spatial task processing requests to an electronic device. As another example, the scenario may also include a third-party platform to which the electronic device can send instruction information, instructing the third-party platform to send control commands to devices in the target space, thereby completing the target task in the target space.

[0033] In some implementations, a digital module of the target space can be pre-created to describe multiple attributes of the target space through the digital model, including the task attributes of each task in the task set of the target space. In response to the existence of a target task that meets the execution conditions in the task set of the target space, the electronic device determines the description information of the target task based on the digital model of the target space; and invokes the large language model to determine the execution information of the target task based on the description information, and executes the target task based on the execution information.

[0034] Therefore, by describing multiple attributes of the target space using a digital model, the target space can be comprehensively and accurately defined based on the digital model, achieving a digital representation of the space. Since the multiple attributes of the target space described by the digital model include the task attributes of the task set, when there are target tasks in the task set of the target space that meet the execution conditions, the description information of the target task can be accurately determined based on the digital model. This allows the large language model to be invoked to determine the execution information of the target task based on the description information and execute the target task. In other words, by combining the digital model of the target space with the large language model, the automated and intelligent processing of tasks in the target space can be achieved based on the comprehensive spatial description and the powerful understanding capabilities of the large language model, thus improving the level of intelligent management of the target space.

[0035] It should be noted that the application scenarios or examples provided in the embodiments of this application are for ease of understanding, and the embodiments of this application do not specifically limit the application of the technical solutions. In addition, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0036] The technical solution of this application and how it solves the aforementioned technical problems are described in detail below with specific embodiments. The listed specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0037] Figure 2 A flowchart illustrating the space mission processing method provided in an embodiment of this application is shown. Figure 2 The method shown can be used by Figure 1 Electronic devices in the process perform, such as Figure 2 As shown, the method may include steps S201 to S203.

[0038] Step S201: In response to the existence of target tasks that meet the execution conditions in the task set of the target space, the description information of the target tasks is determined according to the digital model of the target space. The digital model is used to describe multiple attributes of the target space, including the task attributes of the task set.

[0039] In some implementations, at least one task to be executed in the target space can be created in advance based on at least one task creation request for the target space, resulting in a task set for the target space. A digital model of the target space is then created based on the task attributes of this task set and other pre-acquired spatial attributes of the target space. Furthermore, it is determined whether a target task satisfying the execution conditions exists in the task set of the target space, and if so, its descriptive information is determined based on the digital model of the target space.

[0040] The target space can be any physical space such as a room, office, floor, entire building, or parking lot. The task set for each target space can include different tasks. For example, if the target space is a room, the task set could include cleaning tasks, equipment startup tasks (such as turning on the air conditioner or humidifier), equipment shutdown tasks, opening curtains tasks, and turning on lights tasks. As another example, if the target space is an entire building, the task set could include smoke detection tasks, leak detection tasks, equipment startup tasks, and personnel access detection tasks. The target spaces and their task sets will not be listed exhaustively here; they can be set as needed in practical applications.

[0041] Step S202: Invoke the large language model and determine the execution information of the target task based on the description information.

[0042] In some implementations, multiple training samples can be pre-determined based on a digital model of the target space. Each training sample includes a description and label of the corresponding task, and the label may include execution information of the corresponding task. The existing large language model is then fine-tuned using these multiple training samples. Accordingly, after determining the description of the target task, the electronic device can invoke the fine-tuned large language model and determine the execution information of the target task based on the description. The description of the target task may include at least one of the following: task name, task content, and corresponding control instructions. The execution information indicates the execution method of the target task, and accordingly, the execution information may include indication information of the execution method.

[0043] It should be noted that the large language model can be deployed on electronic devices or other devices. When the large language model is deployed on other devices, an interface can be provided to the electronic device, which can then call the large language model through this interface. The fine-tuning training process of the large language model can be found in relevant technologies, and will not be detailed in this application.

[0044] Step S203: Execute the target task based on the execution information.

[0045] In some implementations, the execution method can be determined based on the execution information, and the target task can be executed according to the execution method to obtain the execution result. In order to facilitate the subsequent traceability of the task execution, in some implementations, an execution record of the target task can also be generated based on information such as the execution time and time result of the target task, and the execution record can be saved.

[0046] In the technical solution provided in this application, multiple attributes of the target space are described by a digital model, enabling a comprehensive and accurate definition of the target space based on the digital model, thus achieving a digital representation of the space. Since the multiple attributes of the target space described by the digital model include task attributes of the task set, when there are target tasks in the task set of the target space that meet the execution conditions, the description information of the target task can be accurately determined based on the digital model. This allows the large language model to be invoked to determine the execution information of the target task based on the description information and execute the target task. In other words, by combining the digital model of the target space with the large language model, the automated and intelligent processing of tasks in the target space can be achieved based on the comprehensive spatial description and the powerful understanding capabilities of the large language model, thereby improving the level of intelligent management of the target space.

[0047] To fully and comprehensively describe the target space and enable flexible linkage of various devices within it, in some implementations, a digital model of the target space is first created based on a digital model creation request. That is, before step S201, the method may further include: receiving a digital model creation request, which includes attribute information corresponding to multiple attributes of the target space; and generating a digital model of the target space based on the attribute information.

[0048] In some implementations, such as Figure 3As shown, the target space has multiple attributes, including the aforementioned task attributes, and may also include any number of basic attributes, feature attributes, event attributes, and tool attributes. Among these, the task attribute is used to characterize at least one task (also referred to as a spatial task) contained in the target space, that is, to characterize at least one task in the task set of the target space. The attribute information of the task attribute is the attribute information of each task. The attribute information of any task may include at least one of the following: task identifier (such as task name, task number, etc.), task content (i.e., task description, including monitoring indicators, etc.), execution strategy (such as scheduled execution, event-triggered execution, etc.), control command (i.e., the linkage command required to execute when the task is executed), and triggering event (such as the event that triggers the corresponding task, the event triggered when the task is executed, etc.). For example, if a task in the space is to turn off the air conditioner at 9 pm, then the task name could be "Air Conditioner Turn-Off Task," the task content could be "Turn off the air conditioner at 9 pm," the execution strategy could be "Scheduled Execution," the control command could be "Command 1" to control the air conditioner to turn off, and the triggering event could be the event that triggers the task, that is, the event that reaches 9 pm.

[0049] Basic attributes are used to characterize the fundamental information of a digital model, such as Figure 3 As shown, this basic information can include the name, description, and type of the digital model. The model description describes the main content of the model, such as the main tools and tasks associated with it. The model type characterizes the type of the target space; for example, a digital model for an office could be classified as an "office type," and a digital model for a parking lot could be classified as a "parking lot type."

[0050] Feature attributes are used to characterize multiple features (also called spatial features) contained in a target space. The attribute information of a feature attribute is the attribute information of each individual feature. The attribute information of any feature can include at least one of the following: the feature's name, description (meaning of the feature, e.g., the description of a temperature feature represents the temperature of the target space), constraint data (such as temperature threshold, humidity threshold, etc.), unit (such as temperature in degrees Celsius), data type (such as integer, Boolean, enumeration, etc.), last update time, and contained sub-features. For example... Figure 4 As shown, the target space includes multiple elements such as basic elements, environmental elements, equipment elements, and usage elements. The sub-elements of the basic elements include area, volume, and orientation. The sub-elements of the environmental elements include temperature, humidity, and carbon dioxide concentration. The sub-elements of the equipment elements include air conditioners, refrigerators, humidifiers, etc. The sub-elements of the usage elements include target tenants (e.g., businesses, individuals), rental duration, and rental amount.

[0051] Event attributes are used to characterize events corresponding to a task set. These events can be events that trigger tasks within the task set, or events that can be triggered when executing tasks within the task set. The attribute information of an event attribute is the attribute information of each event. The attribute information of any event includes at least one of the following: event name, event description (i.e., event content), trigger source (i.e., the object that triggers the event), whether it propagates, trigger time, event value (the numerical value corresponding to the event), and source space. Among these, whether it propagates indicates whether the event propagates layer by layer when there is spatial nesting (e.g., a building has multiple floors, a floor has multiple rooms, etc.). The source space is the space where the event occurs (e.g., a specific room). For example, if the target space is a building, and an event is "When the smoke concentration in any room within the building reaches 150 micrograms per cubic meter, a smoke alarm event is triggered," then the event name could be "Smoke Alarm Event," the event description could be "When the smoke concentration reaches 150 micrograms per cubic meter, a smoke alarm event is triggered," the trigger source could be smoke, whether it propagates could be "Yes," the trigger time could be the time when the smoke concentration reaches 150 micrograms per cubic meter, the event value could be 150, and the source space could be that room. It is evident that by defining events in the target space within the digital model, the layer-by-layer transmission of events between nested spaces can be achieved, thereby better maintaining the security and order of the target space.

[0052] Tool attributes are used to characterize the tools used when performing at least one task in a set of tasks. The attribute information of a tool attribute is the attribute information of each tool used. The attribute information of any tool includes at least one of the following: tool name, tool description (which can be used to describe the purpose of the tool, etc.), and tool parameters (such as the input parameters, output parameters, etc.).

[0053] The generated digital model can be a pre-structured data structure storing the aforementioned attribute information. Therefore, by creating a digital model of the target space, it is possible to comprehensively and accurately describe the target space from multiple dimensions, achieving digital representation and comprehensive perception of the target space. Furthermore, based on the powerful reasoning capabilities of this digital model and the large language model, different tasks within the target space can be managed without resorting to traditional workflow and task orchestration for each task. This significantly improves the level of intelligent task management, making spatial interaction more flexible and intelligent, thus enhancing the overall intelligent management of the target space. In addition, for different spaces with the same attributes, the digital model can be quickly migrated and copied without repeatedly performing the digital model creation operation.

[0054] In order to flexibly execute tasks in the target space, such as Figure 5 As shown, it provides task triggering methods such as event triggering, timed triggering, and manual triggering. To accurately implement event triggering, such as... Figure 5As shown, multiple data acquisition devices can be deployed in the target space, and each device can save the collected monitoring data to a second database in real time. Accordingly, the method may also include:

[0055] In response to the arrival of the detection period, based on the digital model and monitoring data of the target space, it is determined whether a target task exists in the task set of the target space, and the monitoring data is collected by the acquisition device located in the target space; and / or, for any timed task in the task set, if the execution time of the timed task arrives at the current time, it is determined that a target task exists in the task set; and / or, if a task processing request for the target space is received, it is determined that a target task exists in the task set.

[0056] In some implementations, the electronic device can periodically detect, according to a detection cycle, whether there are target tasks in the task set of the target space that meet the execution conditions, based on the digital model of the target space and the monitoring data of the target space stored in a second database. Specifically, when the detection cycle arrives, for any task in the task set, the monitoring elements and constraint data corresponding to the task are obtained from the digital model of the target space, and the target monitoring data corresponding to the monitoring elements are obtained from the monitoring data of the target space; if the target monitoring data is not less than the constraint data, it is determined that there are target tasks in the task set that meet the execution conditions.

[0057] More specifically, when the electronic device determines that a detection cycle has arrived, for any task in the task set, it retrieves the associated task content from the digital model based on the task's task identifier, extracts monitoring elements and constraint data from the task content, and uses these as the monitoring elements and constraint data for that task. Furthermore, it retrieves the last updated target monitoring data corresponding to the monitoring element from the monitoring data stored in the second database, determines whether the target monitoring data is less than the corresponding constraint data, and if so, determines that an event has been formed to trigger the task, and identifies the task as a target task that meets the execution conditions; that is, there exists a target task in the task set that meets the execution conditions.

[0058] In some implementations, the task content may not include constraint data. In this case, the constraint data corresponding to the monitoring elements can be obtained from the elements contained in the digital model.

[0059] For example, if the task content of a certain task is to turn on the air conditioner when the temperature reaches 27 degrees, then the monitoring element is determined to be temperature, the constraint data is 27 degrees, and the target monitoring data obtained from the second database is 28 degrees, then the task is determined to be a target task that meets the execution conditions.

[0060] It should be noted that there can be one or more monitoring elements. When there are multiple monitoring elements, there are also multiple constraint data, and there is a one-to-one correspondence between multiple monitoring elements and multiple constraint data.

[0061] Therefore, based on the monitoring data stored in the digital model and the second database, it is determined whether an event has been formed that triggers the task, thus realizing the event triggering method for the task.

[0062] Considering that in some implementations, the task set may include scheduled tasks, the electronic device can, in some implementations, also obtain the execution time of any scheduled task in the task set from a digital model in real time, and determine that the scheduled task is a target task that meets the execution conditions when the current time reaches that execution time; that is, there is a target task in the task set that meets the execution conditions. For example, if a scheduled task is to turn on the lights at 7 pm, then when the current time is 7 pm, this task is determined to be the target task. Thus, by monitoring the time in real time for scheduled tasks, a time-triggered method for tasks is implemented.

[0063] Considering that in practical applications, a task may need to be executed due to special circumstances, the user can manually trigger it. Accordingly, upon receiving a task processing request from the user, the electronic device identifies the task corresponding to the task identifier in the request as the target task that meets the execution conditions; that is, there is a target task in the task set that meets the execution conditions. It should be noted that the user can directly operate the electronic device to select a target task and submit a task processing request, or the user can operate their terminal device to select a target task. The terminal device, in response to the user's selection, sends a task processing request to the electronic device based on the task identifier of the selected target task. Correspondingly, after executing the target task, the electronic device can also send the execution result of the target task to the client. This implements a manual task triggering method.

[0064] In other words, this application provides multiple triggering methods for tasks. In practical applications, the appropriate triggering method can be selected according to the situation, thereby realizing flexible triggering of tasks.

[0065] As mentioned earlier, the digital model includes attribute information of task attributes. In order for the large language model to fully understand the target task, in some implementations, the aforementioned determination of the description information of the target task based on the digital model of the target space may include: obtaining the target attribute information corresponding to the task identifier of the target task from the attribute information of the task attributes included in the digital model; and generating the description information of the target task based on the target attribute information.

[0066] Specifically, after determining the target task, the target attribute information corresponding to the task identifier can be obtained from the digital model, and description information in a preset format can be generated based on the target attribute information. As mentioned earlier, the target attribute information may include at least one of the following: task name, task content, control instructions, execution strategy, etc.

[0067] For example, the task name, task content, and control instructions of the target task are obtained from the target attribute information, and then concatenated to obtain the description information of the target task. The specific format and content of the description information can be set as needed in practical applications, and this application does not impose specific limitations on them.

[0068] Therefore, by obtaining the target attribute information of the target task from the digital model and generating the description information of the target task based on the target attribute information, the accuracy and comprehensiveness of the description information are ensured, enabling the large language model to fully understand the target task, thereby ensuring the accuracy of the target task execution.

[0069] To enable large language models to understand the target task more easily and accurately, in some implementations, such as Figure 5 As shown, a knowledge base can also be pre-built, storing relevant data to assist the large language model in reasoning. This data can include task-related professional knowledge such as terminology explanations, industry standards, and industry regulations. Furthermore, to more conveniently handle the target task, such as... Figure 5 As shown, the tool information set can also be input into a large language model to analyze whether a target tool exists to perform the target task. Accordingly, the aforementioned invocation of the large language model to determine the execution method of the target task based on the description information can include:

[0070] The target knowledge corresponding to the description information is obtained from the knowledge base. The target knowledge is used to assist the large language model in analyzing the target task. Based on the description information, target knowledge and prompt word template, prompt words are generated. The prompt words are used to prompt the rules for determining the execution information. The prompt words and tool information set are input into the large language model to obtain the execution information of the target task.

[0071] Specifically, a mapping between task descriptions and knowledge identifiers can be pre-established. Accordingly, the target knowledge identifiers corresponding to the target information of the target task can be obtained from this mapping, and the knowledge corresponding to high-level target knowledge identifiers can be identified as target knowledge. Alternatively, keywords can be extracted from the description information, and the target knowledge associated with those keywords can be obtained from the knowledge base. Furthermore, the description information and target knowledge are populated into a pre-configured prompt word template to obtain prompt words. This prompt word and tool information set are output to a large language model. The large language model analyzes whether executing the target task requires calling a tool based on the prompt words, and generates execution information for the target task based on the analysis results, which is then output. The tool information set includes multiple tool information entries, and the tool corresponding to any one of these tool information entries is used to execute the corresponding task. It should be noted that some tasks in the task set can be executed by tools, while others are executed by electronic devices.

[0072] Therefore, by acquiring target knowledge from the knowledge base and inputting prompt words generated based on the target knowledge and descriptive information into the large language model, the large language model can more fully and accurately understand the target task, thereby outputting accurate execution methods and ensuring the effective execution of the target task.

[0073] Furthermore, such as Figure 5 As shown, a target tool can be invoked to execute a target task and trigger a target event. In other words, the aforementioned execution of a target task based on execution information can include: if the execution information includes tool information, invoking the target tool corresponding to the tool information and executing the target task through the target tool; or if the execution information includes event information, triggering the target event corresponding to the event information.

[0074] The tool can be any form, such as an interface, application, or mini-program. When the execution information includes tool information, the target tool corresponding to the tool information is invoked. This target tool then retrieves the associated data of the target task from the first database and executes the target task based on the associated data. Alternatively, the target tool can send instruction information to a third-party platform, which instructs the third-party platform to send control commands to the target device in the target space.

[0075] In practical applications, the execution of the target task may require the use of relevant data in the first database. In this case, the target tool can be invoked to obtain the associated data of the target task from the first database and execute the target task based on the associated data.

[0076] Some devices in the target space can access a third-party platform via IoT functionality, and the third-party platform can send control commands to these devices. Correspondingly, when the target task requires operation of these devices, the electronic devices can invoke the target tool to send instruction information to the third-party platform. The third-party platform then sends control commands to the target devices in the target space based on this instruction information. The instruction information may include device information of the target device, control methods, and the control command itself. The third-party platform may include multiple business systems to handle different business processes. The specific content of the instruction information and the specific form of the third-party platform can be set as needed in practical applications; this application does not impose specific limitations on them.

[0077] For example, the target device is a smart air conditioner. The electronic device can send instruction information through the target toolbox third-party platform to instruct the smart air conditioner to be adjusted to 25 degrees. Then the third-party platform can send a temperature adjustment command to the smart air conditioner so that the smart air conditioner can adjust the temperature of the target space to 25 degrees.

[0078] Therefore, by including tool information in the execution information, the execution efficiency and accuracy of the target task can be improved.

[0079] Considering that in practical applications, the execution of some tasks may trigger other events, the corresponding target event is triggered when the execution information includes event information. For example, in a smart parking lot, after completing the parking payment task, a vehicle release event can be triggered to allow the vehicle to leave the smart parking lot. Therefore, by triggering the target event, not only is the effective execution of the target task guaranteed, but intelligent management of the target space is also achieved.

[0080] Corresponding to the application scenarios and methods provided in the embodiments of this application, the embodiments of this application also provide a processing apparatus for space missions, which can be applied to... Figure 1 The electronic devices shown, such as Figure 6 As shown, the device includes:

[0081] The first determining module 601 is configured to, in response to the existence of a target task satisfying the execution conditions in the task set of the target space, determine the description information of the target task according to the digital model of the target space, wherein the digital model is used to describe multiple attributes of the target space, and the multiple attributes include the task attributes of the task set;

[0082] Module 602 is used to invoke the large language model and determine the execution information of the target task based on the description information;

[0083] The execution module 603 is used to execute the target task according to the execution information.

[0084] In some embodiments, the device further includes a second determining module for:

[0085] In response to the arrival of the detection period, based on the digital model and the monitoring data of the target space, it is determined whether the target task exists in the task set, wherein the monitoring data is collected by an acquisition device located in the target space; and / or, for any timed task in the task set, if the execution time of the timed task arrives at the current time, it is determined that the target task exists in the task set; and / or, upon receiving a task processing request for the target space, it is determined that the target task exists in the task set.

[0086] In some implementations, the second determining module is specifically used for:

[0087] For any task in the task set, obtain the monitoring elements and constraint data corresponding to the task from the digital model; obtain the target monitoring data corresponding to the monitoring elements from the monitoring data of the target space; if the target monitoring data is not less than the constraint data, determine that the target task exists in the task set.

[0088] In some implementations, the digital model includes attribute information of the task attributes, and the first determining module 601 is specifically used for:

[0089] Obtain the target attribute information corresponding to the task identifier of the target task from the attribute information. The target attribute information includes at least one of the following: task name, task content, and control instructions. Generate the description information of the target task based on the target attribute information.

[0090] In some implementations, the calling module 602 is specifically used for:

[0091] The target knowledge corresponding to the description information is obtained from the knowledge base. The target knowledge is used to assist the large language model in analyzing the target task. Based on the description information, the target knowledge, and the prompt word template, prompt words are generated. The prompt words are used to prompt the rules for determining the execution information. The prompt words and tool information set are input into the large language model to obtain the execution information of the target task.

[0092] In some implementations, the execution module 603 is specifically used for:

[0093] If the execution information includes tool information, the target tool corresponding to the tool information is invoked, and the target task is executed through the target tool; if the execution information includes event information, the target event corresponding to the event information is triggered.

[0094] In some embodiments, the execution module 603 is further specifically used to: obtain the associated data of the target task from the first database through the target tool, and execute the target task according to the associated data; or, send instruction information to a third-party platform through the target tool, the instruction information being used to instruct the third-party platform to send control commands to the target device in the target space.

[0095] In some embodiments, the apparatus further includes a creation module for receiving a creation request for the digital model. The creation request includes attribute information corresponding to the plurality of attributes, which further include any number of feature attributes, event attributes, and tool attributes. The feature attributes are used to characterize the plurality of features contained in the target space, the event attributes are used to characterize the events corresponding to the task set, and the tool attributes are used to characterize the tools used when performing at least one task in the task set. The digital model is generated based on the attribute information.

[0096] The functions of each module in the devices of this application embodiment can be found in the corresponding descriptions of the methods described above, and they have corresponding beneficial effects, which will not be repeated here. Furthermore, the device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components illustrated as modules may or may not be physical modules; 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 application solution according to actual needs.

[0097] Figure 7 This is a block diagram of an electronic device used to implement embodiments of this application. For example... Figure 7 As shown, the electronic device includes a memory 701 and a processor 702. The memory 701 stores a computer program that can run on the processor 702. When the processor 702 executes the computer program, it implements the method described in the above embodiments. The number of memories 701 and processors 702 can be one or more. In a specific implementation, the electronic device may also include a communication interface 703 for communicating with external devices and performing data exchange and transmission.

[0098] In practical implementation, if the memory 701, processor 702, and communication interface 703 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0099] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0100] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method provided in this application.

[0101] This application provides a computer program product, including a computer program that, when executed by a processor, implements the method provided in this application.

[0102] This application also provides a chip including a processor for calling and executing instructions stored in a memory, causing a communication device with the chip installed to perform the method provided in this application.

[0103] This application also provides a chip, including: an input interface, an output interface, a processor, and a memory. The input interface, output interface, processor, and memory are connected through an internal connection path. The processor is used to execute code in the memory. When the code is executed, the processor is used to execute the method provided in the application embodiment.

[0104] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0105] Further, optionally, the aforementioned memory may include read-only memory and random access memory. The memory may be volatile memory or non-volatile memory, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Sync Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0106] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0108] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0109] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. Furthermore, the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functionality involved.

[0110] The logic and / or steps described in the flowchart or otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0111] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware, the program being stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.

[0112] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. This storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0113] The above description is merely an exemplary embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope described in this application, and these should all be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for processing space missions, characterized in that, include: In response to the existence of target tasks that meet the execution conditions in the task set of the target space, the description information of the target task is determined according to the digital model of the target space. The digital model is used to describe multiple attributes of the target space. The multiple attributes include task attributes and event attributes of the task set. The event attributes are used to characterize the events corresponding to the task set. The large language model is invoked to determine the execution information of the target task based on the description information; Execute the target task according to the execution information; The step of executing the target task according to the execution information includes: triggering the target event corresponding to the event information when the execution information includes event information.

2. The method according to claim 1, characterized in that, The method further includes: In response to the arrival of the detection period, based on the digital model and the monitoring data of the target space, it is detected whether the target task exists in the task set, wherein the monitoring data is collected by the acquisition device located in the target space; And / or, for any timed task in the task set, if the execution time of the timed task arrives at the current time, it is determined that the target task exists in the task set; And / or, upon receiving a task processing request for the target space, determine that the target task exists in the task set.

3. The method according to claim 2, characterized in that, The step of detecting whether the target task exists in the task set based on the digital model and the monitoring data of the target space includes: For any task in the task set, obtain the monitoring elements and constraint data corresponding to the task from the digital model; Obtain the target monitoring data corresponding to the monitoring element from the monitoring data of the target space; If the target monitoring data is not less than the constraint data, it is determined that the target task exists in the task set.

4. The method according to any one of claims 1 to 3, characterized in that, The digital model includes attribute information of the task attributes, and the step of determining the descriptive information of the target task based on the digital model of the target space includes: Obtain the target attribute information corresponding to the task identifier of the target task from the attribute information, wherein the target attribute information includes at least one of the following: task name, task content, and control instructions; Based on the target attribute information, a description of the target task is generated.

5. The method according to any one of claims 1 to 3, characterized in that, The invocation of the large language model, based on the description information, to determine the execution information of the target task includes: The target knowledge corresponding to the description information is obtained from the knowledge base, and the target knowledge is used to assist the large language model in analyzing the target task; Based on the description information, the target knowledge, and the prompt word template, prompt words are generated, and the prompt words are used to prompt the rules for determining the execution information; The set of prompt words and tool information is input into the large language model to obtain the execution information of the target task.

6. The method according to claim 5, characterized in that, The step of executing the target task based on the execution information further includes: If the execution information includes tool information, the target tool corresponding to the tool information is invoked, and the target task is executed through the target tool.

7. The method according to claim 6, characterized in that, The execution of the target task through the target tool includes: The target tool retrieves the associated data of the target task from the first database and executes the target task based on the associated data. Alternatively, the target tool may send instruction information to a third-party platform, the instruction information being used to instruct the third-party platform to send control commands to the target device in the target space.

8. The method according to claim 1, characterized in that, Before the existence of a target task satisfying the execution conditions in the task set of the target space, the method further includes: The system receives a creation request for the digital model. The creation request includes attribute information corresponding to the plurality of attributes. The plurality of attributes also include at least one of feature attributes and tool attributes. The feature attributes are used to characterize the plurality of features contained in the target space, and the tool attributes are used to characterize the tool used when performing at least one task in the task set. The digital model is generated based on the attribute information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor, when executing the computer program, implements the method of any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

Images