Object control method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an object control method and device, electronic equipment and a storage medium, environment parameters of a target control object are obtained, and the environment parameters represent the state of the target control object relative to a reference object in an operation environment where the target control object is located; processing the environmental parameters and a corresponding cue word text through a language processing model, and generating a target control instruction for the target control object, the cue word text being used for describing a generation logic of the target control instruction based on a natural language; and executing the target control instruction to control the target control object to move. The environment parameters are obtained, the language processing model and the prompt word text are combined, the corresponding target control instruction is generated to control the target control object, the control logic of the target control object does not need to be designed from the code level, and therefore the flexibility of the control logic is greatly improved, the development cost and steps are reduced, and the development efficiency is improved. The performance of a control object is improved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to an object control method, device, electronic device, and storage medium. Background Art

[0002] At present, with the development of intelligent control technology, both virtual objects in the program and equipment objects in reality can achieve a certain degree of intelligent response under program control, thereby improving the performance of the controlled objects.

[0003] However, in the prior art, the implementation scheme of the control logic of the controlled object is usually implemented based on a pre-designed program code, which has problems such as complicated development process of the control logic and difficulty in flexible change, thus affecting the performance of the controlled object. Summary of the invention

[0004] The embodiments of the present disclosure provide an object control method, device, electronic device and storage medium to overcome the problem that the development process of control logic is complicated and difficult to flexibly change.

[0005] In a first aspect, an embodiment of the present disclosure provides an object control method, including:

[0006] Acquire environmental parameters of a target control object, wherein the environmental parameters represent the state of the target control object relative to a reference object in the operating environment of the target control object; process the environmental parameters and corresponding prompt word texts through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used to describe the generation logic of the target control instruction based on natural language; execute the target control instruction to control the activity of the target control object

[0007] In a second aspect, an embodiment of the present disclosure provides an object control device, including:

[0008] An acquisition module, used for acquiring environmental parameters of a target control object, wherein the environmental parameters represent a state of the target control object relative to a reference object in an operating environment where the target control object is located;

[0009] A processing module, used for processing the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used for describing the generation logic of the target control instruction based on natural language;

[0010] The execution module is used to execute the target control instruction to control the activity of the target control object.

[0011] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0012] The memory stores computer-executable instructions;

[0013] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the object control method as described in the first aspect and various possible designs of the first aspect.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the object control method described in the first aspect and various possible designs of the first aspect is implemented.

[0015] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the object control method as described in the first aspect and various possible designs of the first aspect.

[0016] The object control method, device, electronic device and storage medium provided in this embodiment obtain environmental parameters of the target control object, wherein the environmental parameters represent the state of the target control object relative to the reference object in the operating environment of the target control object; process the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used to describe the generation logic of the target control instruction based on natural language; and execute the target control instruction to control the activity of the target control object. By obtaining environmental parameters representing the state of the target control object, and combining the language processing model and the prompt word text to generate the corresponding target control instruction to control the target control object, the process of directly generating control logic based on natural language is realized, without the need to design the control logic of the target control object from the code level, thereby greatly improving the flexibility of the control logic, reducing development costs and steps, and improving the performance of the control object. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 An application scenario diagram of the object control method provided by the embodiment of the present disclosure;

[0019] Figure 2Schematic diagram of the process of the object control method provided in the embodiment of the present disclosure Figure 1 ;

[0020] Figure 3 for Figure 2 A schematic diagram of a process for obtaining a prompt word text in the illustrated embodiment;

[0021] Figure 4 A schematic diagram of a process for generating a prompt word text provided by an embodiment of the present disclosure;

[0022] Figure 5 A schematic diagram of a vehicle control method provided by an embodiment of the present disclosure using the object control method provided by an embodiment of the present disclosure;

[0023] Figure 6 Schematic diagram of the process of the object control method provided in the embodiment of the present disclosure Figure 2 ;

[0024] Figure 7 for Figure 6 A flowchart of a possible implementation of step S206 in the illustrated embodiment;

[0025] Figure 8 A schematic diagram of a process for generating a target control instruction provided by an embodiment of the present disclosure;

[0026] Fig. 9 for Figure 6 A flowchart of another possible implementation of step S206 in the illustrated embodiment;

[0027] Fig.10 A schematic diagram of another process of generating a target control instruction provided by an embodiment of the present disclosure;

[0028] Fig.11 A structural block diagram of an object control device provided by an embodiment of the present disclosure;

[0029] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure;

[0030] Fig.13 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0032] It should be noted that 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 disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] The application scenarios of the embodiments of the present disclosure are explained below:

[0034] Figure 1 This is an application scenario diagram of the object control method provided in the embodiment of the present disclosure. The object control method provided in the embodiment of the present disclosure can be applied to applications with control functions. More specifically, it can be applied to application scenarios for controlling virtual objects or physical device objects, such as game AI control, smart home appliance control, robot control, and vehicle control. The executor of this embodiment can be a terminal device running the above-mentioned application with control functions, or a server that deploys the service end corresponding to the above-mentioned application, or other electronic devices that perform similar functions. Figure 1 As shown in the figure, taking the application scenario of controlling objects in the game as an example, the execution subject of the method provided in this embodiment is a terminal device, such as the smart phone shown in the figure, which runs a game application. In the game application, a target control object is set, such as a non-player character (NPC) 11 in the game. The non-player character 11 has an independent behavior logic (control logic), which can implement corresponding behavior actions according to the player's operation or the scene and environmental information in the game. For example, as shown in the figure, when the player character 12 controlled by the player approaches the non-player character, the non-player character 11 will show a "smiling" expression.

[0035] In the prior art, the design of control logic for the above non-player characters is usually implemented by developers through program codes in game applications. The pre-designed program codes are used to control the non-player characters to respond to the trigger conditions. However, the program codes of the game applications need to be written in advance. When the control logic of the above non-player characters needs to be updated, the control logic needs to be modified at the code level, which makes the development and update of the control logic of such control objects difficult and costly, and the control logic cannot be updated flexibly, which in turn affects the performance and performance of the control objects.

[0036] The embodiments of the present disclosure provide an object control method to solve the above problems.

[0037] refer to Figure 2 , Figure 2 Schematic diagram of the process of the object control method provided in the embodiment of the present disclosure Figure 1 The method of this embodiment can be applied in a terminal device or a server. The object control method includes:

[0038] Step S101: Acquire environmental parameters of a target control object, where the environmental parameters represent a state of the target control object relative to a reference object in the operating environment where the target control object is located.

[0039] For example, reference Figure 1As shown in the schematic diagram of the application scenario, the object control method provided in this embodiment can be applied to the development stage (testing stage) of the target application (such as a game application) with the object control function, and can also be applied to the running stage of the target application. Taking the running stage of the target application as an example, specifically, after the terminal device runs the target application, after the trigger condition is met, the target control object can be controlled by calling a separate thread, wherein the target control object is, for example, a non-game player in the game application. First, the terminal device (or server) obtains the environmental parameters of the target control object, and the environmental parameters represent the state of the target control object relative to the reference object in the running environment where the target control object is located, wherein the state of the target control object relative to the reference object can include motion states such as relative speed and acceleration, and can also include azimuth states such as position, distance, and angle. Specifically, for example, environmental parameters #1, environmental parameters #2, and environmental parameters #3 corresponding to non-game players are obtained. Among them, environmental parameter #1 represents the coordinates of the non-game player in the game environment (relative to the reference point); environmental parameter #2 represents the distance between the non-game player and the player character controlled by the player in the game environment; environmental parameter #3 represents the relative distance between the non-game player and a specific object (such as a moving vehicle) in the game environment. From the above examples, it can be seen that the environmental parameters of the target control object are information that represents the state of the target control object relative to the reference object (such as the reference point, player character, and specific object in the above examples).

[0040] Furthermore, the state refers to the properties of the target control object in the operating environment, such as the speed, distance, etc. in the above examples, and can also include the color of the target control object, the duration of the action, the pending actions to be performed, etc., which can all be implementation methods of the state, and examples are not given one by one here. Further, the reference object refers to a reference object in the operating environment, which can be a specific object visible in the operating environment, that is, a specific reference object, such as a specific object. It can also be a preset object that is invisible in the operating environment, that is, general reference information, such as a starting time point, a starting position, an invisible object with a standard color, etc. In one possible implementation method, the reference object can be 0, and the environmental parameter is the state of the target control object represented by a numerical value or an identifier. In addition, environmental parameters can also represent information such as device status, data status, environmental conditions, etc., and examples are not given one by one.

[0041] Furthermore, the environmental parameters can be obtained from the operating environment. The operating environment can be a model obtained by modeling multiple objects including the target control object, which can fully describe the states of multiple objects including the target control object; by calling the state acquisition interface (API) corresponding to the target control object, the environmental parameters of the target control object can be obtained. Among them, the operating environment can be run locally on the terminal device (client) or on the server (server) that the terminal device communicates with. When the executor of the method provided in this embodiment is a terminal device, the environmental parameters of the target control object can be obtained by accessing an external server, which can be set as needed. Afterwards, the subsequent steps are performed according to the obtained environmental parameters.

[0042] Step S102: Processing the environmental parameters and the corresponding prompt word texts through the language processing model to generate target control instructions for the target control object. The prompt word texts are used to describe the generation logic of the target control instructions based on natural language.

[0043] Step S103: Execute the target control instruction to control the activity of the target control object.

[0044] Exemplarily, after obtaining the environmental parameters characterizing the state of the target control object, the terminal device further controls the behavior of the target control object according to the environmental parameters. Specifically, the terminal device generates a target control instruction for controlling the target control object by calling a language processing model to process the environmental parameters and the corresponding prompt text. Among them, the prompt text is used to describe the generation logic of the target control instruction based on natural language. Specifically, the prompt is a kind of information used to guide the content output by the model. The prompt text is usually composed of multiple text segments, and the description of the generation logic of the target control instruction is realized through one or more generation requirements and restrictions defined by each text segment. For example, "generate control instructions through Python language", or "the control object is an enthusiastic person". The above prompt text can be preset in the target application, or it can be input in real time by the user through the input interface provided by the target application.

[0045] Furthermore, the terminal device then inputs the environmental parameters and the corresponding prompt word text into a language processing model, and generates a target control instruction that matches the environmental parameters through the language processing model, wherein the language processing model can be a pre-trained large language model (LLM) that can generate accurate control instructions in a short time, thereby realizing automatic control of the target control object based on the user's intention (determined by the prompt word text). Afterwards, after obtaining the target control instruction generated by the language processing model, the target control instruction is executed by the target application, thereby realizing the activity control of the target control object in the operating environment, so that the state of the target control object changes (or does not change), for example, the target control object moves, changes color, triggers a specific action, etc.

[0046] The prompt word text input into the language processing model may be preset or may be input in real time by the user through an interface provided by the target application. Figure 3 As shown, before step S102, the following steps are performed to obtain the prompt word text:

[0047] Step S100A: receiving a user configuration instruction during the running of the running environment.

[0048] Step S100B: Generate prompt word text according to the user configuration instruction.

[0049] Exemplarily, the process of the terminal device running the operating environment may be the process of the terminal device running the target application and the target application generating the operating environment, that is, in the process of running the target application, the terminal device receives the user configuration instructions input by the user through the input interface, thereby generating a prompt word text. Figure 4 A schematic diagram of a process for generating a prompt word text provided by an embodiment of the present disclosure, such as Figure 4 As shown, taking the game scene as an example, during the operation of the game application, when the target operation link is triggered manually or automatically, the "NPC creation" page is displayed in the interactive interface of the game application, and an editable text box and corresponding instructions are displayed in the page. For example, as shown in the figure, an instruction text is displayed in the interactive interface: "Please describe the characteristics of the NPC character you want to create". After that, the user enters the description text in the input text box, and the terminal device generates the corresponding prompt text according to the description text. And in the subsequent steps, for example, the prompt text guides the language processing model to generate the corresponding target control instruction, so as to achieve the purpose of "characters with different characteristics" being able to produce different "reactions".

[0050] Figure 5 A schematic diagram of a vehicle control method provided by an embodiment of the present disclosure using the object control method provided by the embodiment of the present disclosure is provided below in combination with Figure 5 The above process is further introduced as follows: Figure 5 As shown, in a target vehicle (shown as vehicle A in the figure) with assisted driving and automatic driving functions, a vehicle machine device 51 (terminal device) for driving control of the target vehicle is provided. The vehicle machine device 51 controls the target vehicle by executing the object control method provided in this embodiment. Specifically, as shown in the figure, for example, the vehicle machine device 51 collects environmental information through sensors designed on the target vehicle to obtain environmental parameters of the target control object, such as the driving speed and acceleration of the target vehicle. Afterwards, the vehicle machine device inputs a language processing model based on the prompt word information and environmental parameters input by the user, obtains a target control instruction for controlling the target vehicle, and controls the vehicle to move to the right and accelerate forward by executing the target control instruction, so that the target vehicle completes the action of overtaking the adjacent vehicle (shown as vehicle B in the figure) from the left.

[0051] In this embodiment, by obtaining the environmental parameters of the target control object, the environmental parameters represent the state of the target control object relative to the reference object in the operating environment where the target control object is located; processing the environmental parameters and the corresponding prompt word text through the language processing model to generate a target control instruction for the target control object, and the prompt word text is used to describe the generation logic of the target control instruction based on natural language; executing the target control instruction to control the activity of the target control object. By obtaining the environmental parameters representing the state of the target control object, and combining the language processing model and the prompt word text to generate the corresponding target control instruction to control the target control object, the process of directly generating the control logic based on natural language is realized, without the need to design the control logic of the target control object from the code level, thereby greatly improving the flexibility of the control logic, reducing the development cost and steps, and improving the performance of the control object.

[0052] refer to Figure 6 , Figure 6 Schematic diagram of the process of the object control method provided in the embodiment of the present disclosure Figure 2 In this embodiment Figure 2 On the basis of the illustrated embodiment, steps S101-S102 are further refined, and the object control method includes:

[0053] Step S201: Obtain a target time interval, where the target time interval is determined based on scenario information corresponding to the operating environment.

[0054] Step S202: Based on the target time interval, call the environment function at least once to obtain the environment parameters of the target control object.

[0055] Exemplarily, in order to make the target control object continuously active in the operating environment, the state of the target control object needs to be updated in real time. In one possible implementation, the environmental parameters can be collected based on a fixed target time interval, for example, every 1 second, and the corresponding target control instructions can be generated using a language processing model to achieve continuous activity of the target control object; and in another possible implementation, the target time interval can be dynamically set based on the scene information corresponding to the operating environment. For example, still taking the game scene as an example, when the game environment in the game application is a rapidly changing scene, such as "racing", "fighting action" and other scenes, a shorter target time interval is determined to obtain the corresponding environmental parameters more frequently, so that the response speed of the target control object is faster and meets the requirements of rapidly changing scenes; and when the game environment in the game application is a slowly changing scene, such as "character dialogue" and other scenes, a longer target time interval is determined to obtain environmental parameters at a lower frequency, thereby saving system resources and network resources and reducing server operation pressure.

[0056] Furthermore, based on the target time interval determined according to the scene information, the corresponding target function is called to obtain the environmental parameters of the target control object, wherein the target function is an interface function for obtaining the environmental parameters of the target control object from the running environment, which is preset in the client and server of the target application. The specific implementation method of the target function is not limited here.

[0057] Further, the environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter represents the positional relationship of the target control object relative to the reference object; and the second environmental parameter represents the motion relationship of the target control object relative to the reference object. Exemplarily, after obtaining the environmental parameters by calling the environmental function, the environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter represents the current positional information of the target control object, and the second environmental parameter represents the current operating information of the target control object. The first environmental information and the second environmental information can be used to describe the motion state of the target control object. In a more specific application scenario, such as in the operating environment of a racing game, the first environmental information of the target control object can represent the track where the target control object (such as the target racing car) is located; and the second environmental information represents the distance and speed difference between the target control object and the vehicle in front.

[0058] In this embodiment, by representing the environmental parameters through the first environmental parameter and the second environmental parameter, a more accurate description of the state of the target control object can be achieved, so that the target control instructions generated subsequently can control the target control object to move based on the above-mentioned first environmental parameter and the second environmental parameter, and realize highly complex actions such as "avoiding vehicles", "chasing vehicles", and "overtaking".

[0059] Optionally, after step S202, the method further includes:

[0060] Step S203: Update the target time interval according to the environmental parameters.

[0061] Exemplarily, on the other hand, after obtaining the environmental parameters, the target time interval can be dynamically updated according to the environmental parameters, such as the first environmental parameters and the second environmental parameters in the above example. For example, when the target vehicle (target control object) is close to other vehicles in the same lane (determined by the second environmental parameter), the target time interval is shortened, thereby increasing the control frequency of the target vehicle, so that the target vehicle has higher dynamic response performance, thereby achieving the purpose of improving the performance of the target control object.

[0062] Step S204: Obtain prompt word text, the prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate a target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameters and the candidate function.

[0063] Step S205: obtaining at least one function to be selected according to the first prompt information through a language processing model.

[0064] Step S206: Determine a target function corresponding to the environment parameters from at least one candidate function according to the second prompt information and the environment parameters through the language processing model, and construct a target control instruction based on the target development language using the target function.

[0065] Exemplarily, further, a prompt word text is obtained for guiding the language processing model to output the target control instruction. In a possible implementation, the prompt word text can be generated based on the user configuration instruction. Figure 2 This has been introduced in the illustrated embodiment and will not be repeated here. In another possible implementation, the prompt word text is pre-generated and stored locally on the terminal device or in the server. The application scenario corresponding to this implementation is the application development and testing scenario. That is, the developer sets the prompt word text in advance, thereby realizing a fixed generation logic for generating target control instructions based on environmental parameters.

[0066] Exemplarily, the prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate a target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameter and the candidate function. Specifically, the content of the first prompt information is, for example:

[0067] "Control instructions can be generated through the following functions:

[0068] def func_1();

[0069] def func_2();

[0070] def func_3();

[0071] ……”.

[0072] The content of the second prompt information is, for example:

[0073] “lane_pos: the lane the vehicle is in;

[0074] By comparing your car with the lane_pos in car_info, you can determine whether your car is in the same lane;

[0075] dist: The distance between your car and the car. When dist is less than {min_dist} and your car is in the same lane as the car, you need to change lanes to avoid a collision.

[0076] The function that controls the forward and backward movement of the car is func_1();

[0077] The function that controls the left and right movement of the car is func_2();

[0078] ……”.

[0079] Referring to the examples of the first prompt information and the second prompt information, the first prompt information provides a plurality of optional functions, namely, the selected functions, and generates the target control instruction through one or more of the selected functions. The second prompt information provides the rules for how to select the selected functions based on the environmental parameters, namely, the mapping relationship between the environmental parameters and the selected functions. After the language processing model obtains at least one selected function according to the first prompt information, it uses the environmental parameters to select the target function corresponding to the environmental parameters based on the mapping relationship between the environmental parameters and the selected functions represented by the second prompt information. Finally, the target functions are combined to obtain the corresponding execution statement, namely, the target control instruction. For example, the content of the target control instruction is:

[0080] "func_1();

[0081] func_2();

[0082] ……”.

[0083] The meaning represented by the target control instruction is, for example, to control the target vehicle to accelerate forward and change lanes to the left. Afterwards, the terminal device executes the target control instruction output by the language processing model to achieve control of the target control object. In this embodiment, by constructing the prompt word text through the first prompt information and the second prompt information, an accurate description of the generation logic of the target control instruction can be achieved, so that the generated target control instruction can be more accurate and effective, better match the user's intention, and thus improve the performance of the target control object.

[0084] Furthermore, in a possible implementation method, the selected function is a parameterless function, that is, a function without input parameters. By directly calling the parameterless function, the corresponding function function can be realized. For example, function func_1() is a parameterless function. After executing the function func_1(), the function of controlling the target vehicle (target control object) to "accelerate" can be realized; function func_2() is another parameterless function. After executing the function func_2(), the function of controlling the target vehicle (target control object) to "decelerate" can be realized.

[0085] Specifically, Figure 7 As shown, the specific implementation of step S206 includes:

[0086] Step S2061: Obtain a corresponding parameter-free target function from at least one candidate function through a language processing model according to the second prompt information and environmental parameters.

[0087] Step S2062: Generate target control instructions according to the parameter-free target function.

[0088] Figure 8 A schematic diagram of a process for generating a target control instruction provided by an embodiment of the present disclosure, such as Figure 8As shown, exemplarily, first, the language processing model determines multiple candidate functions according to the first prompt information, such as func_1(), func_2(), func_3(), and func_4() shown in the figure; wherein, still taking the application scenario of the running environment as a racing game as an example, exemplarily, function func_1() is used to control the acceleration of the target control object, function func_2() is used to control the deceleration of the target control object; function func_3() is used to control the target control object to change lanes to the left; function func_4() is used to control the target control object to change lanes to the right. Afterwards, the language processing model selects func_2() and func_3(), i.e., the parameterless target function, from the multiple candidate functions func_1(), func_2(), func_3(), and func_4() indicated by the above-mentioned first prompt information according to the second prompt information and environmental parameters. Afterwards, according to the parameter-free target functions func_2() and func_3(), corresponding target control instructions {fun_2(), func_3()} are constructed, indicating that functions func_2() and func_3() are executed in sequence to control the target control object in the operating environment to slow down and change lanes to the left.

[0089] In another possible implementation, the function to be selected is a parameterized function, and the language processing model configures the function to be selected based on the environment parameters, thereby obtaining the target function and constructing the corresponding target control instruction. Fig. 9 As shown, another specific implementation of step S206 includes:

[0090] Step S2063: Determine at least one parameterized function and target parameters corresponding to the parameterized function through a language processing model according to the second prompt information and environmental parameters.

[0091] Step S2064: configure the parameter function based on the target parameters, obtain the target function, and generate the target control instruction according to the target function.

[0092] Fig.10 Another schematic diagram of a process for generating a target control instruction provided by an embodiment of the present disclosure is as follows: Fig.10As shown, exemplarily, first, the language processing model determines multiple candidate functions according to the first prompt information, such as func_1(), func_2(), and func_3() shown in the figure; wherein, still taking the application scenario of the running environment as a racing game as an example, exemplarily, the function func_1() is used to control the acceleration and deceleration of the target control object; the function func_2() is used to control the lane change of the target control object; and the function func_3() is used to control the color change of the target control object. Afterwards, the language processing model selects func_1(), func_2(), that is, the parameterized functions, and the target parameters corresponding to each parameterized function, that is, the parameter "Power" corresponding to func_1() and the parameter "Right" corresponding to func_2(), from the candidate functions func_1(), func_2(), and func_3() indicated by the above first prompt information according to the second prompt information and the environmental parameters. Afterwards, the corresponding parameterized functions are configured based on the target parameters to obtain the target functions func_1 ("Power") and func_2 ("Right"). After that, the corresponding target control instruction {func_1("Power"); func_2("Right")} is constructed based on the above target function, which means that the functions func_1("Power") and func_2("Right") are executed successively to control the target control object in the operating environment to accelerate and change lanes to the right.

[0093] Further, optionally, the prompt word text includes a third prompt information, and the third prompt information is used to indicate the target development language corresponding to the operating environment. Specifically, the third prompt information is information for indicating the expression language of the target control instruction generated by the language processing model. Through the third prompt information, the target control instruction based on the target development language can be output according to the language processing mode, and the target development language is, for example, Python language, C language, etc. Thereby, the generated target control instruction can be directly executed in the target application, and the execution efficiency of the target control instruction is improved, so that the target control object can respond more quickly and improve the performance of the target control object.

[0094] Step S207: Execute the target control instruction to control the activity of the target control object.

[0095] In this embodiment, the implementation method of step S207 is the same as that of the present disclosure. Figure 2 The implementation of step S103 in the illustrated embodiment is the same and will not be described in detail here. After executing step S207, the process may return to step S201 and repeat the above steps to achieve continuous control of the target control object.

[0096] Corresponding to the object control method of the above embodiment, Fig.11This is a structural block diagram of an object control device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown.

[0097] Reference Fig.11 , the object control device 3 comprises:

[0098] An acquisition module 31 is used to acquire environmental parameters of a target control object, where the environmental parameters represent a state of the target control object relative to a reference object in the operating environment of the target control object;

[0099] A processing module 32, used to process the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used to describe the generation logic of the target control instruction based on natural language;

[0100] The execution module 33 is used to execute the target control instruction to control the activity of the target control object.

[0101] In one embodiment of the present disclosure, the prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate a target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameters and the candidate functions; when the processing module 32 processes the environmental parameters and the corresponding prompt word text through the language processing model to generate a target control instruction for the target control object, it is specifically used to: the language processing model obtains at least one candidate function according to the first prompt information; the language processing model determines the target function corresponding to the environmental parameters from at least one candidate function according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function.

[0102] In one embodiment of the present disclosure, when the processing module 32 determines the target function corresponding to the environmental parameters from at least one candidate function according to the second prompt information and the environmental parameters through the language processing model, and generates the target control instruction using the target function, it is specifically used for: the language processing model obtains the corresponding parameter-free target function from at least one candidate function according to the second prompt information and the environmental parameters; and generates the target control instruction according to the parameter-free target function.

[0103] In one embodiment of the present disclosure, when the processing module 32 determines the target function corresponding to the environmental parameters from at least one candidate function according to the second prompt information and the environmental parameters through the language processing model, and generates the target control instruction using the target function, it is specifically used for: the language processing model determines at least one parameterized function and the target parameters corresponding to the parameterized function according to the second prompt information and the environmental parameters; configures the parameterized function based on the target parameters to obtain the target function, and generates the target control instruction according to the target function.

[0104] In one embodiment of the present disclosure, the environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter represents the positional relationship of the target control object relative to the reference object; and the second environmental parameter represents the motion relationship of the target control object relative to the reference object.

[0105] In one embodiment of the present disclosure, the prompt word text includes third prompt information, and the third prompt information is used to indicate the target development language corresponding to the operating environment; when the processing module 32 processes the environment parameters and the corresponding prompt word text through the language processing model to generate the target control instructions for the target control object, it is specifically used for: the language processing model generates the target control instructions based on the target development language according to the environment parameters and the corresponding prompt word text.

[0106] In one embodiment of the present disclosure, the acquisition module 31 is specifically used to: acquire a target time interval, where the target time interval is determined based on scene information corresponding to the operating environment; and based on the target time interval, call an environment function at least once to obtain environment parameters of a target control object.

[0107] In one embodiment of the present disclosure, after obtaining the environmental parameters of the target control object, the acquisition module 31 is further used to: update the target time interval according to the environmental parameters.

[0108] In one embodiment of the present disclosure, the acquisition module 31 is further used to: receive a user configuration instruction during the operation of the operation environment; and generate a prompt word text according to the user configuration instruction.

[0109] The acquisition module 31, the processing module 32 and the execution module 33 are connected in sequence. The object control device 3 provided in this embodiment can execute the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be described in detail in this embodiment.

[0110] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is shown in FIG. Fig.12 As shown, the electronic device 4 includes:

[0111] A processor 41, and a memory 42 communicatively connected to the processor 41;

[0112] The memory 42 stores computer executable instructions;

[0113] The processor 41 executes the computer execution instructions stored in the memory 42 to implement the following Figure 2-Figure 10 The object control method in the illustrated embodiment.

[0114] Optionally, the processor 41 and the memory 42 are connected via a bus 43 .

[0115] For related instructions, please refer to Figure 2-Figure 10 The relevant descriptions and effects corresponding to the steps in the corresponding embodiments can be understood, and no further elaboration is made here.

[0116] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, which are used to implement the present invention when executed by a processor. Figure 2-Figure 10 The object control method provided in any one of the corresponding embodiments.

[0117] In order to implement the above embodiment, the embodiment of the present disclosure also provides an electronic device.

[0118] refer to Fig.13 , which shows a schematic diagram of the structure of an electronic device 900 suitable for implementing the embodiment of the present disclosure, and the electronic device 900 may be a terminal device or a server. The terminal device may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.13 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0119] like Fig.13 As shown, the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 to a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0120] Typically, the following devices may be connected to the I / O interface 905: input devices 906 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 908 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.13 The electronic device 900 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0121] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0122] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0123] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0124] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0125] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0128] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0129] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] In a first aspect, according to one or more embodiments of the present disclosure, there is provided an object control method, comprising:

[0131] Acquire environmental parameters of a target control object, wherein the environmental parameters represent a state of the target control object relative to a reference object in the operating environment of the target control object; process the environmental parameters and corresponding prompt word texts through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used to describe the generation logic of the target control instruction based on natural language; and execute the target control instruction to control the activity of the target control object.

[0132] According to one or more embodiments of the present disclosure, the prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate the target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameters and the candidate functions; processing the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object includes: the language processing model obtains at least one candidate function according to the first prompt information; the language processing model determines the target function corresponding to the environmental parameters from the at least one candidate function according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function.

[0133] According to one or more embodiments of the present disclosure, the language processing model determines the target function corresponding to the environmental parameters from the at least one candidate function according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function, including: the language processing model obtains the corresponding parameter-free target function from the at least one candidate function according to the second prompt information and the environmental parameters; and generates the target control instruction according to the parameter-free target function.

[0134] According to one or more embodiments of the present disclosure, the language processing model determines the target function corresponding to the environmental parameters from the at least one candidate function according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function, including: the language processing model determines at least one parameterized function and the target parameters corresponding to the parameterized function according to the second prompt information and the environmental parameters; configures the parameterized function based on the target parameters to obtain the target function, and generates the target control instruction according to the target function.

[0135] According to one or more embodiments of the present disclosure, the environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter characterizes the positional relationship of the target control object relative to a reference object; and the second environmental parameter characterizes the motion relationship of the target control object relative to a reference object.

[0136] According to one or more embodiments of the present disclosure, the prompt word text includes third prompt information, and the third prompt information is used to indicate the target development language corresponding to the operating environment; the environment parameters and the corresponding prompt word text are processed by a language processing model to generate target control instructions for the target control object, including: the language processing model generates a target control instruction based on the target development language according to the environment parameters and the corresponding prompt word text.

[0137] According to one or more embodiments of the present disclosure, obtaining the environmental parameters of the target control object includes: obtaining a target time interval, where the target time interval is determined based on scene information corresponding to the operating environment; and based on the target time interval, calling an environmental function at least once to obtain the environmental parameters of the target control object.

[0138] According to one or more embodiments of the present disclosure, after obtaining the environmental parameters of the target control object, the method further includes: updating the target time interval according to the environmental parameters.

[0139] According to one or more embodiments of the present disclosure, the method further includes: receiving a user configuration instruction during the operation of the operation environment; and generating the prompt word text according to the user configuration instruction.

[0140] In a second aspect, according to one or more embodiments of the present disclosure, there is provided an object control device, comprising:

[0141] An acquisition module, used for acquiring environmental parameters of a target control object, wherein the environmental parameters represent a state of the target control object relative to a reference object in an operating environment where the target control object is located;

[0142] A processing module, used for processing the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used for describing the generation logic of the target control instruction based on natural language;

[0143] The execution module is used to execute the target control instruction to control the activity of the target control object.

[0144] According to one or more embodiments of the present disclosure, the prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate the target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameters and the candidate functions; when the processing module processes the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, it is specifically used to: the language processing model obtains at least one candidate function according to the first prompt information; the language processing model determines the target function corresponding to the environmental parameters from the at least one candidate function according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function.

[0145] According to one or more embodiments of the present disclosure, when the processing module determines the target function corresponding to the environmental parameters from the at least one candidate function according to the second prompt information and the environmental parameters through the language processing model, and generates the target control instruction using the target function, it is specifically used for: the language processing model obtains the corresponding parameter-free target function from the at least one candidate function according to the second prompt information and the environmental parameters; and generates the target control instruction according to the parameter-free target function.

[0146] According to one or more embodiments of the present disclosure, when the processing module determines the target function corresponding to the environmental parameters from the at least one candidate function through the language processing model according to the second prompt information and the environmental parameters, and generates the target control instruction using the target function, it is specifically used for: the language processing model determines at least one parameterized function and the target parameters corresponding to the parameterized function according to the second prompt information and the environmental parameters; configures the parameterized function based on the target parameters to obtain the target function, and generates the target control instruction according to the target function.

[0147] According to one or more embodiments of the present disclosure, the environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter characterizes the positional relationship of the target control object relative to a reference object; and the second environmental parameter characterizes the motion relationship of the target control object relative to a reference object.

[0148] According to one or more embodiments of the present disclosure, the prompt word text includes third prompt information, and the third prompt information is used to indicate the target development language corresponding to the operating environment; when the processing module processes the environment parameters and the corresponding prompt word text through the language processing model to generate the target control instructions for the target control object, it is specifically used for: the language processing model generates the target control instructions based on the target development language according to the environment parameters and the corresponding prompt word text.

[0149] According to one or more embodiments of the present disclosure, the acquisition module is specifically used to: acquire a target time interval, where the target time interval is determined based on scene information corresponding to the operating environment; and based on the target time interval, call an environmental function at least once to obtain environmental parameters of the target control object.

[0150] According to one or more embodiments of the present disclosure, after obtaining the environmental parameters of the target control object, the acquisition module is further used to: update the target time interval according to the environmental parameters.

[0151] According to one or more embodiments of the present disclosure, the acquisition module is further used to: receive a user configuration instruction during the operation of the operation environment; and generate the prompt word text according to the user configuration instruction.

[0152] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0153] The memory stores computer-executable instructions;

[0154] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the object control method as described in the first aspect and various possible designs of the first aspect.

[0155] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the object control method described in the first aspect and various possible designs of the first aspect is implemented.

[0156] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the object control method as described in the first aspect and various possible designs of the first aspect.

[0157] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0158] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0159] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An object control method, characterized in that: include: Acquire an environmental parameter of a target control object, wherein the environmental parameter represents a state of the target control object relative to a reference object in an operating environment where the target control object is located; Processing the environmental parameters and the corresponding prompt word texts through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used to describe the generation logic of the target control instruction based on natural language; The target control instruction is executed to control the activity of the target control object.

2. The method according to claim 1, characterized in that The prompt word text includes first prompt information and second prompt information, wherein the first prompt information is used to indicate at least one candidate function that can be used to generate the target control instruction, and the second prompt information is used to characterize the mapping relationship between the environmental parameter and the candidate function; Processing the environmental parameters and the corresponding prompt word texts through a language processing model to generate a target control instruction for the target control object includes: The language processing model obtains at least one function to be selected according to the first prompt information; The language processing model determines a target function corresponding to the environmental parameter from the at least one candidate function according to the second prompt information and the environmental parameter, and generates the target control instruction using the target function.

3. The method according to claim 2, characterized in that The language processing model determines, according to the second prompt information and the environmental parameter, a target function corresponding to the environmental parameter from the at least one candidate function, and generates the target control instruction using the target function, including: The language processing model obtains a corresponding parameter-free objective function from the at least one candidate function according to the second prompt information and the environmental parameter; According to the parameter-free objective function, a target control instruction is generated.

4. The method according to claim 2, characterized in that: The language processing model determines, according to the second prompt information and the environmental parameter, a target function corresponding to the environmental parameter from the at least one candidate function, and generates the target control instruction using the target function, including: The language processing model determines at least one parameterized function and a target parameter corresponding to the parameterized function according to the second prompt information and the environment parameter; The parameterized function is configured based on the target parameters to obtain the target function, and a target control instruction is generated according to the target function.

5. The method according to claim 1, characterized in that The prompt word text includes third prompt information, and the third prompt information is used to indicate the target development language corresponding to the operating environment; Processing the environmental parameters and the corresponding prompt word texts through a language processing model to generate a target control instruction for the target control object includes: The language processing model generates a target control instruction based on the target development language according to the environmental parameters and the corresponding prompt word text.

6. The method according to claim 1, characterized in that The environmental parameters include at least a first environmental parameter and a second environmental parameter, wherein the first environmental parameter represents the positional relationship of the target control object relative to a reference object; and the second environmental parameter represents the motion relationship of the target control object relative to a reference object.

7. The method according to claim 1, characterized in that The step of obtaining the environmental parameters of the target control object includes: Obtaining a target time interval, where the target time interval is determined based on scenario information corresponding to the operating environment; Based on the target time interval, an environmental function is called at least once to obtain environmental parameters of the target control object.

8. The method according to claim 7, characterized in that After obtaining the environmental parameters of the target control object, the method further includes: The target time interval is updated according to the environmental parameter.

9. The method according to claim 1, characterized in that: Also includes: In the process of running the operating environment, receiving a user configuration instruction; The prompt word text is generated according to the user configuration instruction.

10. An object control device, characterized in that: include: An acquisition module, used for acquiring environmental parameters of a target control object, wherein the environmental parameters represent a state of the target control object relative to a reference object in an operating environment where the target control object is located; A processing module, used for processing the environmental parameters and the corresponding prompt word text through a language processing model to generate a target control instruction for the target control object, wherein the prompt word text is used for describing the generation logic of the target control instruction based on natural language; The execution module is used to execute the target control instruction to control the activity of the target control object.

11. An electronic device, characterized in that: include: Processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the object control method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the object control method according to any one of claims 1 to 9 is implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the object control method according to any one of claims 1 to 9 is implemented.

Images