Processing method and vehicle system

Abstract

The invention discloses a processing method and a vehicle system. The processing method comprises the steps of obtaining first instruction information; the first instruction information is used for creating a first task; reasoning content contained in the first instruction information based on a target model to obtain at least one piece of second instruction information; the at least one piece of second instruction information is used for creating a second task, and the second task and the first task have an association relationship; and based on the at least one piece of second instruction information, executing a target operation which is used for creating the second task.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more particularly to a processing method and a vehicle system. Background Art

[0002] In modern smart devices and applications, task automation has become one of the important features to improve user experience. However, most existing task creation methods rely on users to select and configure through voice commands or manually click on the page, which is particularly cumbersome when creating multiple tasks. Summary of the invention

[0003] The technical solutions provided by this application are as follows:

[0004] The first aspect of the present application provides a processing method, comprising:

[0005] Obtaining first instruction information; the first instruction information is used to create a first task;

[0006] Based on the target model, the target model infers the content of the first instruction information to obtain at least one second instruction information; the at least one second instruction information is used to create a second task, and the second task is associated with the first task;

[0007] Based on the at least one second instruction information, a target operation is performed, where the target operation is used to create the second task.

[0008] The at least one second instruction information is obtained by reasoning the content of the first instruction information based on the target model, including:

[0009] Based on the first instruction information, determining a plurality of first key information corresponding to the first task;

[0010] Based on the reasoning of the target model on the plurality of first key information, a plurality of second key information is obtained, wherein the plurality of second key information has a corresponding relationship with the plurality of first key information;

[0011] The second instruction information is determined according to the multiple second key information.

[0012] The determining, based on the first instruction information, a plurality of first key information corresponding to the first task includes:

[0013] Based on the first instruction information, determine a first graph corresponding to the first task, wherein first attribute information of each entity in the first graph is the first key information, and first task information corresponding to the first task can be obtained according to the first attribute information of each entity in the first graph and the relationship information between the entities in the first graph;

[0014] The reasoning of the plurality of first key information based on the target model to obtain the plurality of second key information includes:

[0015] Based on the reasoning of the target model on the first graph, a second graph is obtained, and the second attribute information of each entity in the second graph is the second key information.

[0016] The determining the second instruction information according to the plurality of second key information includes:

[0017] The second graph is input into the target model to obtain the second instruction information generated by the target model.

[0018] The determining, based on the first instruction information, a first graph corresponding to the first task includes:

[0019] The first instruction information is input into the target model to obtain the first map generated by the target model.

[0020] The reasoning of the first graph based on the target model to obtain a second graph includes:

[0021] Constructing a first prompt word according to the first graph, wherein the first prompt word is used to instruct the target model to infer other attribute information of each entity in the first graph through the first attribute information, and outputting a graph including the other attribute information;

[0022] The first prompt word is input into the target model to obtain the second graph generated by the target model.

[0023] Based on the at least one second instruction information, executing the target operation includes any one of the following:

[0024] Based on the at least one second instruction information, create at least one second task;

[0025] The at least one second instruction information is sent to the target application, so that the target application creates at least one second task.

[0026] The creating at least one second task based on the at least one second instruction information includes:

[0027] Based on the at least one second instruction information, determining a plurality of candidate task information;

[0028] Determining target task information from the plurality of candidate task information according to the received selection operation;

[0029] The second task corresponding to the target task information is created.

[0030] After creating at least one second task based on the at least one second instruction information, the method further includes at least one of the following:

[0031] determining an execution order of the first task and the second task;

[0032] The first task and the second task are merged.

[0033] Another aspect of the present application provides a vehicle system, comprising:

[0034] The main body of the vehicle;

[0035] A user interface, used to receive first instruction information; the first instruction information is used to create a first task;

[0036] Controller for:

[0037] Obtain first instruction information; the first instruction information is used to create a first task; based on the target model, inference of the content contained in the first instruction information obtains at least one second instruction information; the at least one second instruction information is used to create a second task, and the second task has an association relationship with the first task; based on the at least one second instruction information, perform a target operation, and the target operation is used to create the second task. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0039] Figure 1 A schematic diagram of a process for a treatment method provided in Example 1 of the present application;

[0040] Figure 2 A schematic diagram of a process flow of a processing method provided in Example 2 of the present application;

[0041] Figure 3 A schematic diagram of a process for a treatment method provided in Example 3 of the present application;

[0042] Figure 4 A schematic diagram of a process for a treatment method provided in Example 4 of the present application;

[0043] Figure 5 A schematic diagram of a process for a treatment method provided in Example 5 of the present application;

[0044] Figure 6 A schematic diagram of a process for a treatment method provided in Example 6 of the present application;

[0045] Figure 7 A schematic diagram of a process for a treatment method provided in Example 9 of the present application;

[0046] Figure 8 A schematic diagram of the structure of a processing device provided in this application. DETAILED DESCRIPTION

[0047] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0048] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0049] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0050] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0051] Reference Figure 1 , is a flow chart of a processing method provided in Example 1 of the present application, such as Figure 1 As shown, the method may include but is not limited to the following steps:

[0052] Step S101, obtaining first instruction information; the first instruction information is used to create a first task.

[0053] In this embodiment, the user may provide the first instruction information to the electronic device through voice input, manual input or other interactive methods. For example, the user may input a voice instruction, and the content of the voice instruction may include: "When the co-driver gets on the car, please broadcast the welcome message 'Please get on the car'", or the user may manually type an instruction on the interface of the electronic device, and the content of the manually typed instruction may include: "When the driver gets on the car, please open NetEase Cloud Music and play songs in the preference list", and the electronic device may use the voice instruction or the manually typed instruction as the first instruction information.

[0054] The task conditions and task actions of the first task can be obtained from the first instruction information. For example, corresponding to the first instruction information "Please announce the welcome message 'Please get in the car' when the co-driver gets in the car", the task conditions of the first task may include: the co-driver gets in the car, and the task actions of the first task may include: playing the welcome message 'Please get in the car'. Alternatively, corresponding to "Please open NetEase Cloud Music and play songs in the preference list when the driver gets in the car", the task conditions may include: the driver gets in the car, and the task actions may include: opening NetEase Cloud Music and playing songs in the preference list in NetEase Cloud Music.

[0055] Based on the task condition and the task action of the first task, the first task may be created.

[0056] Step S102: obtaining at least one second instruction information by inferring the content contained in the first instruction information based on the target model; the at least one second instruction information is used to create a second task.

[0057] The target model can be built based on machine learning, deep learning or other artificial intelligence algorithms. For example, the target model can include a language model with natural language processing capabilities and deep semantic understanding capabilities.

[0058] The second task is associated with the first task. For example, based on the target model's inference of the content included in "Please say welcome message 'Please get in' when the front passenger gets on the car", the second instruction information "Please say welcome message 'Slow down' when the front passenger gets off the car" can be obtained. The second task can be created based on the second instruction information "Please say welcome message 'Slow down' when the front passenger gets off the car". Alternatively, based on the target model's inference of the content included in "Please open NetEase Cloud Music and play songs in the preference list when the main driver gets on the car", the second instruction information "If the music is on, it will be automatically turned off when the main driver gets off the car" can be obtained, and the second task can be created based on the second instruction information "If the music is on, it will be automatically turned off when the main driver gets off the car".

[0059] The second task may include a task condition and a task action. For example, corresponding to the second instruction information "When the co-driver gets off the car, please announce the welcome message 'Please go slowly'", the task condition of the second task may include: when the co-driver gets off the car, and the task action of the second task may include: announce the welcome message 'Please go slowly'. Alternatively, corresponding to "When the driver gets off the car, the music will be automatically turned off if it is on", the task condition may include: when the driver gets off the car and the music is on, and the task action may include automatically turning off the currently playing music.

[0060] Step S103: Based on at least one second instruction information, execute a target operation, where the target operation is used to create a second task.

[0061] After the second task is successfully created, the electronic device can continuously detect whether the task condition of the second task is satisfied. When it is detected that the task condition of the second task is satisfied (for example, the sensor detects that the co-driver or the driver gets off the vehicle), the electronic device can trigger and execute the corresponding task action.

[0062] In this embodiment, by obtaining the first instruction information, at least one second instruction information is obtained based on the reasoning of the content contained in the first instruction information by the target model, and at least one second instruction information can be automatically obtained, which can reduce the user's operation burden. On this basis, based on the at least one second instruction information, the target operation is performed, and the target operation is used to create the second task, which can realize the automatic creation of related tasks, and can reduce the risk caused by manual omission of related instruction information, and enhance the convenience and satisfaction of users when using electronic devices. For example, after the user enters "please broadcast the welcome message 'Please get in the car' when the co-driver gets on the car", the user does not need to enter "please broadcast the welcome message 'Please go slowly' when the co-driver gets off the car", and the first task corresponding to "please broadcast the welcome message 'Please go slowly' when the co-driver gets off the car" can be created. Or, after the user enters "please open NetEase Cloud Music and play songs in the preference list when the main driver gets on the car", the user does not need to enter "the main driver gets off the car if the music is turned on, it will be automatically turned off", and the first task corresponding to "the main driver gets off the car if the music is turned on, it will be automatically turned off", thereby ensuring that the user will not cause unnecessary troubles due to forgetting to turn off the music while enjoying the music.

[0063] As another optional embodiment of the present application, refer to Figure 2 , is a flow chart of a processing method provided in Example 2 of the present application. This example is mainly an implementation method of step S102 in Example 1. Figure 2 As shown, step S102 may include but is not limited to the following steps:

[0064] Step S1021: Based on the first instruction information, determine a plurality of first key information corresponding to the first task.

[0065] Multiple first key information may be associated with the task conditions and task actions of the first task. For example, the multiple first key information determined from "When the co-driver gets in the car, please announce the welcome message 'Please get in the car'" may include: "co-driver", "get in the car" and "please get in the car". "Co-driver", "get in the car" are associated with the task conditions of the first task, and "please get in the car" is associated with the task action of the first task. Alternatively, the multiple first key information determined from "When the main driver gets in the car, please open NetEase Cloud Music and play songs in the preference list" may include "main driver", "get in the car", "open NetEase Cloud Music" and "play songs in the preference list". "Main driver", "get in the car" are associated with the task conditions of the first task, and "open NetEase Cloud Music" and "play songs in the preference list" are associated with the task actions of the first task.

[0066] Step S1022: Inferring the plurality of first key information based on the target model to obtain the plurality of second key information.

[0067] The plurality of second key information may have a corresponding relationship with the plurality of first key information.

[0068] Step S1022 may include:

[0069] Step S11, directly input all the first key information into the target model, and obtain the second key information generated by the target model through overall reasoning based on all the first key information. For example, the first key information "co-pilot", "get in the car" and "please get in the car" can be inferred based on the target model to obtain the second key information "main driver", "back row", "get off the car", "please get off the car" and "please walk slowly".

[0070] Step S1022 may also include:

[0071] Step S12: inferring the first key information associated with the task condition of the first task based on the target model to obtain the second key information associated with the task condition.

[0072] Step S13: Infer the second key information and the first key information associated with the task action of the first task based on the target model to obtain the second key information associated with the task action. For example, infer the first key information "co-pilot" and "get in the car" based on the target model to obtain the second key information "co-pilot get out of the car"; infer the second key information "co-pilot get out of the car" and the first key information "please get in the car" based on the target model to obtain the second key information "play the farewell message 'please go slowly'".

[0073] Step S1023: determine the second instruction information according to the plurality of second key information.

[0074] Corresponding to step S11, the second instruction information can be determined according to the plurality of second key information and the plurality of first key information. For example, the plurality of second key information includes: "driver", "back row", "get off", "please get off" and "please go slowly", and the plurality of first key information can be combined with the first key information "co-driver", "get on" and "please get on" to obtain the second instruction information "co-driver please play the farewell message 'please go slowly' when getting off".

[0075] Corresponding to steps S12-S13, the second key information associated with the task condition and the second key information associated with the task action can be combined to obtain the second instruction information. For example, the second key information associated with the task condition includes: "The co-pilot gets off the car", and the second key information associated with the task action includes "play the farewell message 'Please go slowly'". The two are combined to obtain the second instruction information "Please play the farewell message 'Please go slowly' when the co-pilot gets off the car".

[0076] In this embodiment, based on the first instruction information, multiple first key information corresponding to the first task is determined, and based on the reasoning of the multiple first key information by the target model, multiple second key information is obtained, which helps to reduce redundancy and errors in the reasoning process, and can reduce manual intervention and improve the intelligent level of task processing. On this basis, the second instruction information is determined according to the multiple second key information, which can ensure that the second instruction information is associated with the first task and is more logical.

[0077] As another optional embodiment of the present application, refer to Figure 3 , is a flow chart of a processing method provided in Example 3 of the present application. This example is mainly an implementation method of step S1021 and step S1022 in Example 2, such as Figure 3 As shown, step S1021 may include but is not limited to the following steps:

[0078] Step S10211: Based on the first instruction information, determine the first graph corresponding to the first task, and the first attribute information of each entity in the first graph is the first key information.

[0079] The first task information corresponding to the first task can be obtained according to the first attribute information of each entity in the first graph and the relationship information between the entities in the first graph.

[0080] In this embodiment, entities related to the first task can be identified from the first instruction information, and the first attribute information of each entity can be determined. After identifying the entities related to the first task, the relationship between the entities can be determined. For example, the first instruction information may include: "Please broadcast the welcome message 'Please get in the car' when the co-pilot gets in the car", and the entities related to the first task identified from: "Please broadcast the welcome message 'Please get in the car' when the co-pilot gets in the car" may include: "Cabin position", "Seat status", "Broadcast reminder", and the first attribute information corresponding to "Cabin position", "Seat status", and "Broadcast reminder" are: "Co-pilot", "Get in the car", "Please get in the car", the relationship between "Cabin position" and "Seat status" is "corresponding", and the relationship between "Seat status" and "Broadcast reminder" is "trigger".

[0081] In this embodiment, each entity can be used as a node in the graph, and the first attribute information of the entity can be used as the attribute value of the node. Corresponding edges are drawn according to the relationship between the entities to obtain a first graph.

[0082] The first task information corresponding to the first task can be determined based on the first attribute information of each entity in the first graph and the relationship information between each entity in the first graph. The first task information may include: task conditions and task actions. The task conditions may be used to trigger task actions. For example, the first instruction information may include: "Please announce the welcome message 'Please get in the car' when the co-driver gets in the car." The task conditions of the first task may include: the co-driver gets in the car. The co-driver getting in the car may trigger the "announcement reminder" function and play the voice message of 'Please get in the car'.

[0083] Step S1022 may include:

[0084] Step S10221: Based on the target model, the first graph is inferred to obtain a second graph, and the second attribute information of each entity in the second graph is the second key information.

[0085] In the process of reasoning the first graph based on the target model, the entities in the first graph may not be changed, but the first attribute information of each entity is reasoned to generalize the second attribute information which is different from the first attribute information of the entity.

[0086] For example, each entity in the first graph may include: "cabin position", "seat status", "broadcast reminder", and each entity in the second graph may still include: "cabin position", "seat status", "broadcast reminder". The second attribute information corresponding to "cabin position" in the second graph may include: "driver", "back row", and the second attribute information corresponding to "seat status" may include: "get off", and the second attribute information corresponding to "broadcast reminder" may include: "please get off", "please walk slowly".

[0087] In this embodiment, based on the first instruction information, the first graph corresponding to the first task is determined. The structured representation of the first graph can make the first task information of the first task clearer and more organized, thereby enhancing the target model's ability to understand the first task, so that the target model can reason about the first graph more logically and generalize the second attribute information that is related to but different from the first attribute information. Since the second attribute information is obtained through in-depth reasoning of the first graph by the target model, the second instruction information has high accuracy and reliability, and then based on the second instruction information, the target operation is executed, which can ensure that the created second task has a close association with the first task, meeting the user's expectations and needs.

[0088] As another optional embodiment of the present application, refer to Figure 4 , is a flow chart of a processing method provided in Example 4 of the present application. This example is mainly an implementation method of step S1023 in Example 3. Figure 4 As shown, step S1023 may include but is not limited to the following steps:

[0089] Step S10231, input the second graph into the target model to obtain second instruction information generated by the target model.

[0090] In this embodiment, the second graph can be input into the target model, and the target model can generate second instruction information based on the attribute information of each entity in the second graph and the relationship between each entity. The second instruction information can reflect the task conditions and task actions of the second task.

[0091] In this embodiment, a target prompt word can be constructed based on the first task information and the second graph corresponding to the first task. The target prompt word is used to indicate that the target model infers the task conditions associated with the first task through the second graph, and based on the task action of the first task and the task conditions associated with the first task, infers the task action associated with the first task, and outputs the second instruction information.

[0092] For example, the first instruction information may include: "When the front passenger gets in the car, please broadcast the welcome message 'Please get in the car'", and the first task information corresponding to the first task may include: the task condition "The front passenger gets in the car", and "The front passenger gets in the car" can trigger the task action: turn on the "broadcast reminder" function and play the voice message of 'Please get in the car'. The target model can infer that the task condition associated with the task condition "The front passenger gets in the car" is "The front passenger gets out of the car" based on the second graph; then based on the task action: turn on the "broadcast reminder" function and play the voice message of 'Please get in the car' and the associated task condition "The front passenger gets out of the car", the task action associated with the first task is inferred: turn on the "broadcast reminder" function and play the voice message of 'Please go slowly'. The second instruction information output by the target model may include: "When the front passenger gets in the car, please broadcast the welcome message 'Please go slowly'".

[0093] In this embodiment, since the second graph is a structured representation constructed based on the first graph, the second graph can clearly represent the various entities in the first task, the relationship between the various entities, and the first attribute information and the second attribute information of the various entities. The target model can more accurately understand the task conditions and task actions of the first task by reasoning about the second graph, thereby more logically deriving the task conditions and task actions of the second task associated with the first task. In addition, by inputting the second graph into the target model and relying on the reasoning ability of the target model to generate the second instruction information, this process can reduce manual intervention and cumbersome instruction input, and can improve the intelligence level of associated task creation.

[0094] As another optional embodiment of the present application, refer to Figure 5 , is a flow chart of a processing method provided in Example 5 of the present application. This example is mainly an implementation method of step S10211 in Example 3. Figure 5 As shown, step S10211 may include but is not limited to the following steps:

[0095] Step S21: input the first instruction information into the target model to obtain the first graph generated by the target model.

[0096] In this embodiment, the target model may have the ability to understand, parse and generate structured information. After the first instruction information is input into the target model, the target model may perform entity recognition on the input first instruction information, identify entities related to the first task, and determine the first attribute information of each entity. At the same time, the target model may also extract the relationship between the entities.

[0097] Based on the identified entities and extracted relationships, the target model can generate a first graph. In the first graph, entities can be represented as nodes, and relationships can be represented as edges connecting nodes. Each node can also include first attribute information related to the entity.

[0098] In this embodiment, the target model has undergone a lot of training and optimization. By inputting the first instruction information into the target model, it can ensure a more accurate understanding of the first task, thereby ensuring that the first map automatically generated by the target model is more accurate and improving the efficiency of constructing the first map.

[0099] As another optional embodiment of the present application, refer to Figure 6 , is a flow chart of a processing method provided in Example 6 of the present application. This example is mainly an implementation method of step S10221 in Example 3, such as Figure 6 As shown, step S10221 may include but is not limited to the following steps:

[0100] Step S31: construct a first prompt word according to the first graph, where the first prompt word is used to instruct the target model to infer other attribute information of each entity in the first graph through the first attribute information, and output a graph including the other attribute information.

[0101] In this embodiment, a first prompt word can be constructed based on the content of the first graph. For example, for the first instruction information "Please announce the welcome message 'Please get in the car' when the front passenger gets in the car", the first graph can include the entities "cabin position", "seat status" and "announce reminders", as well as the relationship between the entities and the first attribute information. Based on the first graph, a first prompt word can be constructed, such as "Please infer other possible attribute information of 'cabin position', 'seat status' and 'announce reminders' based on the first attribute information of 'cabin position' and 'seat status'".

[0102] Step S32: input the first prompt word into the target model to obtain a second graph generated by the target model, wherein the second attribute information of each entity in the second graph is the second key information.

[0103] In this embodiment, the target model can perform in-depth analysis and reasoning on the entities and relationships in the first graph according to the first prompt word, infer other attribute information of each entity, and based on the other attribute information of each entity, add new attribute information to each entity in the first graph or update the first attribute information to obtain the second graph.

[0104] For example, the target model can infer other attribute information such as "driver", "back row" etc. based on the "position in the cabin" in the first prompt word, and infer other attribute information such as "get off the car" etc. based on the "seat status" in the first prompt word, and infer other attribute information such as "please get off the car" and "please walk slowly" based on the "broadcast reminder" in the first prompt word. New attribute information can be added to the "position in the cabin" in the first map, that is, "driver", "back row", and new attribute information can be added to the "seat status" in the first map, that is, "get off the car", and new attribute information can be added to the "broadcast reminder" in the first map, that is, "please get off the car" and "please walk slowly" to obtain the second map.

[0105] In this embodiment, the first prompt word can provide a clear reasoning direction for the target model, so that the target model can find the correct reasoning path more quickly, thereby improving the reasoning efficiency. In addition, the first prompt word can ensure that the other attribute information inferred is closely related to the first task and logically reasonable, thereby improving the accuracy of reasoning.

[0106] As another optional embodiment of the present application, a processing method is provided for Embodiment 7 of the present application. This embodiment is mainly an implementation method of Step S103 in Embodiment 1. Step S103 may include but is not limited to any of the following:

[0107] Step S1031: Create at least one second task based on at least one second instruction information.

[0108] In this embodiment, at least one second task may be directly created in the current application based on at least one second instruction information. The at least one second task is associated with the first task.

[0109] In this embodiment, each second instruction information in at least one second instruction information may be parsed to determine the task conditions and task actions included in the second instruction information, and at least one second task may be created based on the task conditions and task actions included in the second instruction information.

[0110] After creating at least one second task, the electronic device may continuously monitor whether the task condition of the second task is satisfied. When the task condition is detected to be satisfied (for example, the sensor detects that the co-driver or the driver gets off the vehicle), the electronic device may trigger and execute the corresponding task action.

[0111] In this embodiment, at least one second task can be directly created in the current application based on at least one second instruction information, which can ensure that the current application can provide more complete and intelligent services.

[0112] Step S1032: Send at least one second instruction information to the target application, so that the target application creates at least one second task.

[0113] In step S1032, the electronic device is not responsible for creating the second task in the current application, but sends at least one second instruction information to the target application, and the target application is responsible for creating the corresponding second task. For example, if the first instruction information is "When the driver gets in the car, please open NetEase Cloud Music and play the songs in the preference list", the second instruction information inferred in the task assistant is "If the music is on when the driver gets out of the car, it will be automatically turned off." The task assistant will not create a second task, but will send the second instruction information to the NetEase Cloud Music application (an implementation method of the target application). After receiving the second instruction information, the NetEase Cloud Music application can create a second task, whose task condition is "The driver gets out of the car and the music is on", and the task action is "Automatically turn off the currently playing music."

[0114] In step S1032 , the detailed process of the target application creating at least one second task can be found in the related introduction of step S1031 , which will not be repeated here.

[0115] In this embodiment, by sending at least one second instruction information to the target application so that the target application creates at least one second task, the work of obtaining the second instruction information and creating the second task is distributed to different applications, which can reduce the risk of overall system crash caused by a single application failure. In addition, the target application can have richer resources and more efficient algorithms, and can create the second task faster. Therefore, entrusting task creation to the target application helps improve the processing efficiency of the overall system.

[0116] As another optional embodiment of the present application, a processing method is provided for Embodiment 8 of the present application. This embodiment is mainly an implementation method of Step S1031 in Embodiment 7. Step S1031 may include but is not limited to the following steps:

[0117] Step S10311: Determine multiple candidate task information based on at least one second instruction information.

[0118] In this embodiment, the task condition and the task action may be extracted from each second instruction information of at least one second instruction information, and a plurality of candidate task information may be determined according to the extracted task condition and task action.

[0119] For example, for the second instruction information "Please announce the welcome message 'Go slowly' when the co-pilot gets off the car", the following multiple candidate task information can be determined:

[0120] Candidate task information 1: When the front passenger door is opened and the passenger is detected leaving, play the preset welcome message "Please take care".

[0121] Candidate task information 2: When the weight on the passenger seat decreases to a certain threshold, the welcome message "Please get off" is played.

[0122] Candidate task information 3: When the passenger seat belt is unlocked and the car door is opened, play the welcome message "Please walk slowly".

[0123] Step S10312: Determine target task information from the plurality of candidate task information according to the received selection operation.

[0124] In step S10312, multiple candidate task information may be displayed to the user, and the user may select one of them as the target task information through interface operations (such as clicking, sliding, etc.). After receiving the user's selection operation, the electronic device may use the selected candidate task information from the multiple candidate task information as the target task information.

[0125] For example, if the user selects candidate task information 1 from the candidate task information 1, 2, and 3, the candidate task information 1 may be used as the target task information.

[0126] Step S10313: Create a second task corresponding to the target task information.

[0127] The implementation method of creating the second task corresponding to the target task information can refer to the relevant introduction of step S1031 in Example 7, which will not be repeated here.

[0128] In this embodiment, the user participates in the selection of the task creation process, which can ensure that the second task finally created is more in line with the user's expectations and habits, which helps to improve the user's satisfaction and trust. In addition, by providing multiple candidate task information and allowing users to choose, task creation errors caused by misunderstanding or misoperation can be reduced, which helps to improve the stability and reliability of task creation. In addition, by generating multiple candidate task information and allowing users to choose, the personalized needs of users in different scenarios can be met, making the creation of the second task more flexible.

[0129] As another optional embodiment of the present application, refer to Figure 7 , is a flow chart of a processing method provided in Example 9 of the present application, such as Figure 7 As shown, the method may include but is not limited to the following steps:

[0130] Step S201, obtaining first instruction information; the first instruction information is used to create a first task;

[0131] Step S202: obtaining at least one second instruction information by inferring the content contained in the first instruction information based on the target model; the at least one second instruction information is used to create a second task, and the second task is associated with the first task;

[0132] Step S203: Create at least one second task based on at least one second instruction information.

[0133] The detailed process of step S203 can refer to the relevant introduction of step S1031 in embodiment 7, which will not be repeated here.

[0134] Step S204: determine the execution order of the first task and the second task.

[0135] In this embodiment, the execution order of the first task and the second task may be determined by at least one of the following methods:

[0136] Step S41: Determine the execution order of the first task and the second task based on the logical relationship (eg, sequence, cause and effect) between the task conditions in the first task and the second task.

[0137] For example, the first task is "When the co-driver gets on the car, please announce the welcome message 'Please get on the car'", and the second task is "When the co-driver gets off the car, please announce the farewell message 'Take care'". According to daily logic, the co-driver getting on the car (the task condition of the first task) usually occurs before the co-driver getting off the car (the task condition of the second task), so the first task can be executed before the second task.

[0138] Step S42: Determine the execution order of the first task and the second task based on the time information in the first task and the second task.

[0139] For example, if the first task is "automatically turn on the car air conditioner at 8 am every day", and the second task is "automatically turn off the car air conditioner at 10 am every day", according to the time information, the first task can be executed before the second task.

[0140] Step S43: Determine the execution order of the first task and the second task based on the dependency relationship between the first task and the second task.

[0141] For example, if the first task is "Driver, please open the navigation and plan a route", and the second task is "Provide voice broadcast according to the navigation prompts", the second task depends on the output of the first task (i.e. the planned route), so the first task can be executed before the second task.

[0142] Step S205: merge the first task and the second task.

[0143] Step S205 may include but is not limited to at least one of the following:

[0144] Step S51: If the first task and the second task have a logical association, merge the first task and the second task into one task.

[0145] For example, the task of "when the co-pilot gets on the car, please announce the welcome message 'Please get on'" and "when the co-pilot gets off the car, please announce the farewell message 'Take care'" can be combined into a compound task of "when the co-pilot gets on the car, announce 'Please get on' and 'Take care'" respectively.

[0146] Step S52: If the first task and the second task occur at the same time point or time period, merge the first task and the second task into one task.

[0147] For example, if the first task is "automatically turn on the car air conditioner at 8 o'clock every morning" and the second task is "automatically play the news at 8 o'clock every morning", the first task and the second task can be combined into a composite task of "automatically turn on the car air conditioner and play the news at 8 o'clock every morning".

[0148] In this embodiment, by determining the execution order of the first task and the second task, it can be ensured that the tasks are executed in the expected logical order, avoiding execution errors or unnecessary duplication of work due to disordered order. In addition, the correct execution order can reduce the waiting time and conflict between tasks, making system resources more effectively utilized, thereby improving the efficiency of overall task execution.

[0149] Merging the first task and the second task can simplify the task management process, reduce the number and complexity of tasks, and make task management more intuitive and easy to understand.

[0150] Next, the processing device provided in the present application is introduced. The processing device introduced below and the processing method introduced above can be referenced to each other.

[0151] Reference Figure 8 The processing device includes: an acquisition module 100, a reasoning module 200 and an execution module 300.

[0152] The obtaining module 100 is used to obtain first instruction information; the first instruction information is used to create a first task.

[0153] The reasoning module 200 is used to infer the content contained in the first instruction information based on the target model to obtain at least one second instruction information; the at least one second instruction information is used to create a second task, and the second task is associated with the first task.

[0154] The execution module 300 is used to execute a target operation based on the at least one second instruction information, where the target operation is used to create the second task.

[0155] The reasoning module 200 may be specifically used for:

[0156] Based on the first instruction information, determining a plurality of first key information corresponding to the first task;

[0157] Based on the reasoning of the target model on the plurality of first key information, a plurality of second key information is obtained, wherein the plurality of second key information has a corresponding relationship with the plurality of first key information;

[0158] The second instruction information is determined according to the multiple second key information.

[0159] The determining, based on the first instruction information, a plurality of first key information corresponding to the first task includes:

[0160] Based on the first instruction information, determine a first graph corresponding to the first task, wherein first attribute information of each entity in the first graph is the first key information, and first task information corresponding to the first task can be obtained according to the first attribute information of each entity in the first graph and the relationship information between the entities in the first graph;

[0161] The reasoning of the plurality of first key information based on the target model to obtain the plurality of second key information includes:

[0162] Based on the reasoning of the target model on the first graph, a second graph is obtained, and the second attribute information of each entity in the second graph is the second key information.

[0163] The reasoning module 200 determines the second instruction information according to the plurality of second key information, which may specifically include:

[0164] The second graph is input into the target model to obtain the second instruction information generated by the target model.

[0165] The reasoning module 200 determines the first graph corresponding to the first task based on the first instruction information, which may specifically include:

[0166] The first instruction information is input into the target model to obtain the first map generated by the target model.

[0167] The reasoning module 200 obtains the second graph by reasoning the first graph based on the target model, which may specifically include:

[0168] Constructing a first prompt word according to the first graph, wherein the first prompt word is used to instruct the target model to infer other attribute information of each entity in the first graph through the first attribute information, and outputting a graph including the other attribute information;

[0169] The first prompt word is input into the target model to obtain the second graph generated by the target model.

[0170] The execution module 300 executes the target operation based on the at least one second instruction information, which may include any one of the following:

[0171] Based on the at least one second instruction information, create at least one second task;

[0172] The at least one second instruction information is sent to the target application, so that the target application creates at least one second task.

[0173] The execution module 300 creates at least one second task based on the at least one second instruction information, which may specifically include:

[0174] Based on the at least one second instruction information, determining a plurality of candidate task information;

[0175] Determining target task information from the plurality of candidate task information according to the received selection operation;

[0176] The second task corresponding to the target task information is created.

[0177] The processing device may further include at least one of the following:

[0178] A determination module, used to determine the execution order of the first task and the second task;

[0179] A merging module is used to merge the first task and the second task.

[0180] In another embodiment of the present application, a vehicle system is provided, which may include: a vehicle body, a user interface, and a controller.

[0181] A user interface, used to receive first instruction information; the first instruction information is used to create a first task;

[0182] Controller for:

[0183] Obtain first instruction information; the first instruction information is used to create a first task; based on the target model, inference of the content contained in the first instruction information obtains at least one second instruction information; the at least one second instruction information is used to create a second task, and the second task has an association relationship with the first task; based on the at least one second instruction information, perform a target operation, and the target operation is used to create the second task.

[0184] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any processing method provided in the embodiment of the present application.

[0185] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0186] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0187] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0188] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A processing method comprising: Obtaining first instruction information; The first instruction information is used to create a first task; Based on the target model, the target model infers the content of the first instruction information to obtain at least one second instruction information; the at least one second instruction information is used to create a second task, and the second task is associated with the first task; Based on the at least one second instruction information, a target operation is performed, where the target operation is used to create the second task.

2. The processing method according to claim 1, wherein the at least one second instruction information is obtained by inferring the content contained in the first instruction information based on the target model, comprising: Based on the first instruction information, determining a plurality of first key information corresponding to the first task; Based on the reasoning of the target model on the plurality of first key information, a plurality of second key information is obtained, wherein the plurality of second key information has a corresponding relationship with the plurality of first key information; The second instruction information is determined according to the multiple second key information.

3. The method according to claim 2, wherein determining the plurality of first key information corresponding to the first task based on the first instruction information comprises: Based on the first instruction information, determine a first graph corresponding to the first task, wherein first attribute information of each entity in the first graph is the first key information, and first task information corresponding to the first task can be obtained according to the first attribute information of each entity in the first graph and the relationship information between the entities in the first graph; The reasoning of the plurality of first key information based on the target model to obtain the plurality of second key information includes: Based on the reasoning of the target model on the first graph, a second graph is obtained, and the second attribute information of each entity in the second graph is the second key information.

4. The method according to claim 3, wherein determining the second instruction information according to the plurality of second key information comprises: The second graph is input into the target model to obtain the second instruction information generated by the target model.

5. The method according to claim 3, wherein determining the first graph corresponding to the first task based on the first instruction information comprises: The first instruction information is input into the target model to obtain the first map generated by the target model.

6. The method according to claim 3, wherein the step of obtaining the second graph by inferring the first graph based on the target model comprises: Constructing a first prompt word according to the first graph, wherein the first prompt word is used to instruct the target model to infer other attribute information of each entity in the first graph through the first attribute information, and outputting a graph including the other attribute information; The first prompt word is input into the target model to obtain the second graph generated by the target model.

7. The processing method according to claim 1, performing a target operation based on the at least one second instruction information comprises any one of the following: Based on the at least one second instruction information, create at least one second task; The at least one second instruction information is sent to the target application, so that the target application creates at least one second task.

8. The processing method according to claim 7, wherein the creating at least one second task based on the at least one second instruction information comprises: Based on the at least one second instruction information, determining a plurality of candidate task information; Determining target task information from the plurality of candidate task information according to the received selection operation; The second task corresponding to the target task information is created.

9. The processing method according to claim 7, after creating at least one second task based on the at least one second instruction information, further comprising at least one of the following: determining an execution order of the first task and the second task; The first task and the second task are merged.

10. A vehicle system comprising: The main body of the vehicle; A user interface, used for receiving first instruction information; The first instruction information is used to create a first task; Controller for: Obtaining first instruction information; The first instruction information is used to create a first task; at least one second instruction information is obtained based on the target model's reasoning about the content contained in the first instruction information; the at least one second instruction information is used to create a second task, and the second task has an association with the first task; based on the at least one second instruction information, a target operation is performed, and the target operation is used to create the second task.

Images