Application calling method and apparatus, computer device and storage medium

Abstract

Provided are an application calling method and apparatus, a computer device and a storage medium. The method comprises: in response to an instruction input by a user, analyzing the instruction to obtain application information and a confidence level in the instruction, wherein the confidence level represents the degree of clarity of information covered in the instruction; determining whether the confidence level reaches a preset threshold; if the confidence level reaches the preset threshold, using a first mode to call an application program indicated by the application information; and if the confidence level does not reach the preset threshold, using a second mode to call the application program indicated by the application information, wherein the second mode is different from the first mode.

Description

Application calling method, device, computer equipment and storage medium Cross-references

[0001] This application refers to Chinese patent application No. 202311830720.6 filed on December 27, 2023, entitled “An application calling method, device, computer equipment and storage medium”, which is incorporated into this application in its entirety by reference. Technical Field

[0002] The present disclosure relates to the field of computer technology, and in particular to an application calling method, apparatus, computer equipment, and storage medium. Background Art

[0003] In recent years, major Internet companies, hardware manufacturers, and research institutions have invested heavily in the development of their own large-scale language model service platforms. These products have excellent natural language understanding and generation capabilities.

[0004] However, existing large-scale language model service platforms cannot directly invoke applications based on natural language commands entered by users. Instead, they query pre-defined application interface configurations and use them to invoke applications to execute natural language commands. This approach is not conducive to scalability and the large-scale integration of new applications. Summary of the Invention

[0005] In view of this, the present disclosure provides an application calling method to solve the problem that the existing method of calling applications requires calling applications through application interface configuration, which is not conducive to expansion and is not conducive to large-scale access of new applications.

[0006] In a first aspect, the present disclosure provides an application calling method, the method comprising:

[0007] In response to a command input by a user, parsing the command to obtain application information and a confidence level in the command, wherein the confidence level indicates the degree of clarity of the information covered by the command;

[0008] Determine whether the confidence level reaches a preset threshold;

[0009] When the confidence level reaches a preset threshold, calling the application pointed to by the application information using the first mode;

[0010] When the confidence level does not reach a preset threshold, the application program pointed to by the application information is called using a second mode, where the second mode is different from the first mode.

[0011] The application calling method provided in this embodiment obtains application information and confidence in the instruction, and calls the application program in different modes according to the confidence of the instruction. It does not require the agreed application interface configuration, has strong scalability, and can meet the needs of large-scale access of new applications.

[0012] In some implementations, invoking the application pointed to by the application information using the first mode includes:

[0013] In the first mode, the application is started so that the application obtains first parameter information in the instruction and executes the instruction based on the first parameter information.

[0014] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0015] In some implementations, invoking the application pointed to by the application information using the second mode includes:

[0016] In the second mode, the application is started so that the application obtains the second parameter information in the instruction, and executes the instruction based on the second parameter information when the second parameter information meets the execution requirement.

[0017] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0018] In some implementations, invoking the application pointed to by the application information using the second mode further includes:

[0019] In the second mode, the application is started to enable the application to obtain the second parameter information in the instruction. If the second parameter information cannot meet the execution requirements, the first window pops up, and the first window is used to prompt the user to supplement the parameter information, receive the third parameter information, and determine whether the third parameter information meets the execution requirements. If the third parameter information meets the execution requirements, the instruction is executed based on the third parameter information. If the third parameter information cannot meet the execution requirements, the first window pops up, wherein the third parameter information is the parameter information supplemented by the user.

[0020] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0021] In some embodiments, the method further comprises:

[0022] When the application completes the instruction, determine whether a new instruction is received;

[0023] If no new instruction is received, the application call is terminated.

[0024] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0025] In some embodiments, the method further comprises:

[0026] When a new instruction is received, the new instruction is parsed to obtain application information and confidence level in the new instruction, wherein the confidence level indicates the degree of clarity of the information covered by the new instruction;

[0027] Determine whether the confidence level reaches a preset threshold;

[0028] When the confidence level reaches a preset threshold, calling the application pointed to by the application information using the first mode;

[0029] When the confidence level does not reach a preset threshold, the application program pointed to by the application information is called using a second mode, where the second mode is different from the first mode.

[0030] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0031] In some embodiments, the method further comprises:

[0032] In response to a confirmation operation by the user, the execution result of the instruction is confirmed.

[0033] In some embodiments, the instructions are voice instructions.

[0034] In a second aspect, the present disclosure provides an application calling device, the device comprising:

[0035] An instruction parsing module, configured to parse an instruction input by a user and obtain application information and a confidence level in the instruction, wherein the confidence level indicates the degree of clarity of the information covered by the instruction;

[0036] A confidence judgment module is used to judge whether the confidence reaches a preset threshold;

[0037] A first mode calling module is configured to call the application pointed to by the application information using the first mode when the confidence level reaches a preset threshold;

[0038] The second mode calling module is used to call the application pointed to by the application information using a second mode when the confidence level does not reach a preset threshold, wherein the second mode is different from the first mode.

[0039] In a third aspect, the present disclosure provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the application calling method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0040] In a fourth aspect, the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the application calling method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the specific embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. 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 any creative work.

[0042] FIG1 is a schematic diagram of a flow chart of an application calling method according to an embodiment of the present disclosure;

[0043] FIG2 is a flow chart of another application calling method according to an embodiment of the present disclosure;

[0044] FIG3 is a flow chart of another application calling method according to an embodiment of the present disclosure;

[0045] FIG4 is a structural block diagram of an application calling device according to an embodiment of the present disclosure;

[0046] FIG5 is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions 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 of the present disclosure, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present disclosure.

[0048] Large-scale language model service platforms can serve as AI (Artificial Intelligence) assistants. In related technologies, when large-scale language model service platforms invoke corresponding applications based on natural language commands input by users, they cannot directly invoke the applications. Instead, they query pre-agreed application interface configurations and use the application interface configurations to invoke the applications to execute the natural language commands. This approach is not conducive to scalability and is not conducive to the large-scale integration of new applications.

[0049] The embodiment of the present disclosure provides an application calling method, which obtains application information and confidence in an instruction and calls the application program in different modes according to the confidence information. There is no need to agree on the application interface configuration, and the method has strong scalability and can meet the needs of large-scale access of new applications.

[0050] According to an embodiment of the present disclosure, an application calling method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, an application calling method is provided, which can be used in the above-mentioned mobile terminal, such as a central processing unit, a server, etc. FIG1 is a flow chart of the application calling method according to an embodiment of the present disclosure. As shown in FIG1 , the flow chart includes the following steps:

[0052] Step S101 : In response to an instruction input by a user, the instruction is parsed to obtain application information and confidence level in the instruction.

[0053] The confidence level indicates the clarity of the information contained in the instruction. The instruction is a natural language instruction, which can be input by voice or manually. The instruction instructs the AI ​​assistant to call an application to perform the operation specified in the instruction.

[0054] AI assistants have excellent natural language understanding and generation capabilities. Through a large amount of corpus training, they can perform logical reasoning, judge the truth or falsehood of things, analyze the necessary information needed to execute instructions, etc.

[0055] In other words, the AI ​​assistant can parse the user's input commands based on the context and obtain the confidence level of the commands.

[0056] Step S102: determine whether the confidence level reaches a preset threshold.

[0057] After analyzing the confidence level of the command, the confidence level is determined to see if it reaches a preset threshold, which is obtained by the AI ​​assistant based on a large amount of corpus training.

[0058] Step S103: When the confidence level reaches a preset threshold, the application pointed to by the application information is called using the first mode.

[0059] Among them, when the confidence reaches the preset threshold, it means that the confidence of the instruction is high and the information covered by the instruction is clear.

[0060] Among them, the first mode is the background running mode, which means that there is no need to interact with the user.

[0061] When the confidence reaches a preset threshold, the application pointed to by the application information is called in background running mode.

[0062] Step S104: When the confidence level does not reach the preset threshold, the application pointed to by the application information is called in the second mode.

[0063] The second mode is different from the first mode.

[0064] If the confidence level does not reach the preset threshold, it means that the confidence level of the instruction is low and the information covered by the instruction is not clear enough.

[0065] Among them, the second mode is the foreground running mode, which means that it may interact with the user.

[0066] When the confidence level does not reach a preset threshold, the application pointed to by the application information is called in a foreground running mode.

[0067] The application calling method provided in this embodiment obtains application information and confidence in the instruction, and calls the application program in different modes according to the confidence of the instruction. It does not require the agreed application interface configuration, has strong scalability, and can meet the needs of large-scale access of new applications.

[0068] It should be noted that the application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0069] In this embodiment, an application calling method is provided, which can be used in the above-mentioned mobile terminal, such as a central processing unit, a server, etc. FIG2 is a flow chart of the application calling method according to an embodiment of the present disclosure. As shown in FIG2 , the flow chart includes the following steps:

[0070] Step S201: In response to a command input by a user, the command is parsed to obtain application information and confidence in the command. For details, please refer to step S101 of the embodiment shown in FIG1 , which will not be described in detail here.

[0071] Step S202: determine whether the confidence level reaches a preset threshold.

[0072] Please refer to step S102 of the embodiment shown in FIG1 for details, which will not be described again here.

[0073] Step S203: When the confidence level reaches a preset threshold, the application pointed to by the application information is called using the first mode.

[0074] Specifically, the above step S203 includes:

[0075] Step S2031: In the first mode, start the application program so that the application program obtains first parameter information in the instruction and executes the instruction based on the first parameter information.

[0076] Among them, in the first mode, the information covered by the instruction is more clear, and the application program can execute the instruction according to the first parameter information in the instruction.

[0077] After obtaining the first parameter information in the instruction, the application executes the instruction based on the first parameter information.

[0078] In order to more clearly illustrate the above-mentioned use of the first mode to call the application pointed to by the application information, an exemplary description is given in conjunction with the following example.

[0079] For example, the user's instruction is "set an alarm for me at 10 o'clock tomorrow morning";

[0080] The AI ​​assistant parses the command and determines its confidence level. Since the command contains clear information, the AI ​​assistant determines that the confidence level has reached a preset threshold and calls the alarm clock app in background mode.

[0081] The application obtains the first parameter information as tomorrow morning at ten o'clock;

[0082] After the AI ​​assistant starts and initializes the alarm clock application, the alarm clock application sets the alarm for 10 o'clock tomorrow morning according to the first parameter information;

[0083] After the alarm is set, the AI ​​assistant determines that the command execution is completed, ends the call of the alarm application, and reclaims system resources.

[0084] Step S204: When the confidence level does not reach the preset threshold, the application pointed to by the application information is called in the second mode.

[0085] Specifically, the above step S204 includes:

[0086] Step S2041 , in the second mode, starting the application program so that the application program obtains second parameter information in the instruction, and executes the instruction based on the second parameter information when the second parameter information meets the execution requirement.

[0087] In the second mode, the information covered by the instruction is less clear, and the application may not be able to execute the instruction according to the second parameter information in the instruction.

[0088] Since the information covered by the instruction is less clear, the application needs to determine whether the second parameter information can meet the requirements for executing the instruction. When the second parameter information can meet the requirements for executing the instruction, the application executes the instruction based on the second parameter information.

[0089] Step S2042, in the second mode, start the application so that the application obtains the second parameter information in the instruction. If the second parameter information cannot meet the execution requirements, a first window pops up, and the first window is used to prompt the user to supplement the parameter information, receive the third parameter information, and determine whether the third parameter information meets the execution requirements. If the third parameter information meets the execution requirements, the instruction is executed based on the third parameter information. If the third parameter information cannot meet the execution requirements, the first window pops up.

[0090] The third parameter information is the parameter information supplemented by the user.

[0091] When the second parameter information cannot meet the requirements for executing the instruction, the user is required to supplement the parameter information.

[0092] It should be noted that the first window may prompt the user of parameter information that needs to be supplemented, so that the user can supplement the parameter information according to the prompt.

[0093] Among them, after the user supplements the parameter information, the application obtains the complete supplemented parameter information and again determines whether the supplemented parameter information meets the execution requirements until the application can execute the instruction based on the supplemented parameter information.

[0094] The application calling method of this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0095] In some embodiments, the method further comprises:

[0096] Step a1: When the application completes the instruction, it is determined whether a new instruction is received.

[0097] FIG3 is a flow chart of an application calling method according to an embodiment of the present disclosure. As shown in FIG3,

[0098] When the application completes executing the instructions, the AI ​​assistant determines whether it has received new instructions, that is, whether the task is completed.

[0099] It should be noted that when a user requires an application to perform a task, multiple instructions may be required to complete it. Therefore, when the application completes an instruction, it is necessary to determine whether a new instruction has been received.

[0100] Step a2: If no new instruction is received, terminate the calling of the application program.

[0101] As shown in FIG3 , if no new instruction is received, it means that there is no need to call the application program temporarily, the calling of the application program is terminated, and the system resources are recovered.

[0102] Step a3, when a new instruction is received, the new instruction is parsed to obtain the application information and confidence level in the new instruction, where the confidence level indicates the clarity of the information covered by the new instruction, and whether the confidence level reaches a preset threshold is determined; if the confidence level reaches the preset threshold, the application pointed to by the application information is called using the first mode; if the confidence level does not reach the preset threshold, the application pointed to by the application information is called using the second mode.

[0103] If a new instruction is received, the step of re-executing the new instruction for parsing is performed.

[0104] In some embodiments, the method further comprises:

[0105] Step b1: confirming the execution result of the instruction in response to the user's confirmation operation.

[0106] When an application executes a command, it completes the execution and obtains the execution result. As shown in Figure 3, the execution result needs to be fed back to the user for confirmation. If the user approves the execution result of the command, the execution of the command is completed. If the user disapproves the execution result of the command, the execution of the command is canceled. It is then determined whether a new command has been received and the new command is parsed.

[0107] For example: the user enters the command "help me book the cheapest flight to Shanghai tomorrow";

[0108] The AI ​​assistant interprets the command and determines the confidence level. Due to a lack of information such as the passenger, specific flight time, airline information, and acceptable price range, the AI ​​determines that the confidence level does not meet the preset threshold and therefore launches the flight booking application in the second mode.

[0109] After the application is started and initialized, it begins to judge the existing parameter information. If it finds that the existing information is insufficient to complete the air ticket order, a UI window will pop up to allow the user to fill in more information, such as passenger information, flight time period, airline screening, price range, etc. After collecting enough information, a flight that meets the requirements is selected and displayed to the user for confirmation. If the user agrees, the next order process will be automatically completed. If the user disagrees, the order will be canceled.

[0110] The AI ​​assistant determines whether the task is completed. If not, it continues to wait for the user to enter new instructions; if it is completed, it ends the call, recycles system resources, and the AI ​​assistant enters sleep mode.

[0111] The application calling method provided in this embodiment calls the application program in different modes according to the confidence level of the instruction, thereby improving the execution efficiency of the instruction and saving power consumption.

[0112] This embodiment also provides an application calling device for implementing the above-mentioned embodiments and implementation methods. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0113] This embodiment provides an application calling device, as shown in FIG4 , including:

[0114] The instruction parsing module 401 is configured to parse the instruction in response to the instruction input by the user, and obtain application information and confidence level in the instruction, wherein the confidence level indicates the degree of clarity of the information covered by the instruction.

[0115] The confidence determination module 402 is configured to determine whether the confidence reaches a preset threshold.

[0116] The first mode calling module 403 is configured to call the application pointed to by the application information using the first mode when the confidence level reaches a preset threshold.

[0117] The second mode calling module 404 is configured to call the application pointed to by the application information using a second mode when the confidence level does not reach a preset threshold, wherein the second mode is different from the first mode.

[0118] In some implementations, the first mode calling module 403 includes:

[0119] The first mode calling subunit is used to start the application in the first mode, so that the application obtains the first parameter information in the instruction and executes the instruction based on the first parameter information.

[0120] In some implementations, the second mode calling module 404 includes:

[0121] The second mode calling subunit is used to start the application in the second mode so that the application obtains the second parameter information in the instruction, and executes the instruction based on the second parameter information when the second parameter information meets the execution requirements.

[0122] In some embodiments, the second mode calling sub-unit is also used to start the application in the second mode so that the application obtains the second parameter information in the instruction. If the second parameter information cannot meet the execution requirements, a first window pops up, and the first window is used to prompt the user to supplement the parameter information, receive the third parameter information, and determine whether the third parameter information meets the execution requirements. If the third parameter information meets the execution requirements, the instruction is executed based on the third parameter information. If the third parameter information cannot meet the execution requirements, the first window pops up, wherein the third parameter information is the parameter information supplemented by the user.

[0123] In some embodiments, the apparatus further comprises:

[0124] The instruction reception judgment module is used to judge whether a new instruction is received when the application completes the instruction.

[0125] The calling end module is used to end the calling of the application program if no new instruction is received.

[0126] In some embodiments, the apparatus further comprises:

[0127] A step execution module is used to parse the new instruction when it receives it, obtain application information and confidence in the new instruction, wherein the confidence indicates the clarity of the information covered by the new instruction, and determine whether the confidence reaches a preset threshold. If the confidence reaches the preset threshold, the application pointed to by the application information is called using a first mode; if the confidence does not reach the preset threshold, the application pointed to by the application information is called using a second mode, wherein the second mode is different from the first mode.

[0128] In some embodiments, the apparatus further comprises:

[0129] The execution result determination module is used to confirm the execution result of the instruction in response to the user's confirmation operation.

[0130] The functional descriptions of the above modules and units are the same as those in the above corresponding embodiments and will not be repeated here.

[0131] The application calling device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0132] The embodiment of the present disclosure further provides a computer device having the application calling device shown in FIG. 4 above.

[0133] Please refer to Figure 5, which is a structural diagram of a computer device provided by an embodiment of the present disclosure. As shown in Figure 5, the computer device includes: one or more processors 501, a memory 502, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 takes a processor 501 as an example.

[0134] Processor 501 may be a central processing unit, a network processor, or a combination thereof. Processor 501 may also include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0135] The memory 502 stores instructions that can be executed by at least one processor 501, so as to enable the at least one processor 501 to execute the method shown in the above embodiment.

[0136] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 502 may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 502 includes a memory remotely located relative to the processor 501, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0137] The memory 502 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid state drive; the memory 502 may also include a combination of the above types of memory.

[0138] The computer device further includes a communication interface 503 for the computer device to communicate with other devices or a communication network.

[0139] The embodiments of the present disclosure also provide a computer-readable storage medium. The above-mentioned method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; in some embodiments, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

Claims

1. An application calling method, the method comprising: Parsing the instruction in response to an instruction input by a user to obtain application information and a confidence level in the instruction, wherein the confidence level represents the clarity of the information covered by the instruction; Determining whether the confidence level reaches a preset threshold; When the confidence level reaches the preset threshold, invoking an application program pointed to by the application information using a first mode; and When the confidence level does not reach the preset threshold, invoking an application program pointed to by the application information using a second mode, wherein the second mode is different from the first mode.

2. The method according to claim 1, wherein The invoking of the application program pointed to by the application information using the first mode includes: In the first mode, starting the application program so that the application program obtains first parameter information in the instruction and executes the instruction based on the first parameter information.

3. The method according to claim 1, wherein The invoking of the application program pointed to by the application information using the second mode includes: In the second mode, starting the application program so that the application program obtains second parameter information in the instruction, and when the second parameter information meets the execution requirement, executing the instruction based on the second parameter information.

4. The method according to claim 3, wherein The invoking of the application program pointed to by the application information using the second mode further includes: In the second mode, starting the application program so that the application program obtains second parameter information in the instruction, and when the second parameter information cannot meet the execution requirement, popping up a first window for prompting the user to supplement parameter information, receiving third parameter information, determining whether the third parameter information meets the execution requirement, when the third parameter information meets the execution requirement, executing the instruction based on the third parameter information, and when the third parameter information cannot meet the execution requirement, popping up the first window, wherein the third parameter information is the parameter information supplemented by the user.

5. The method according to claim 2, wherein, The method further includes: When the application program completes the instruction, determining whether a new instruction is received; When no new instruction is received, ending the invocation of the application program.

6. The method according to claim 5, wherein The method further includes: When a new instruction is received, parsing the new instruction to obtain application information and a confidence level in the new instruction, wherein the confidence level represents the clarity of the information covered by the new instruction; Determining whether the confidence level reaches a preset threshold; When the confidence level reaches the preset threshold, invoking an application program pointed to by the application information using the first mode; When the confidence level does not reach the preset threshold, invoking an application program pointed to by the application information using the second mode, wherein the second mode is different from the first mode.

7. The method according to claim 3, wherein, The method further includes: Confirming the execution result of the instruction in response to a confirmation operation by the user.

8. The method according to any one of claims 1-7, wherein, The instruction is a voice instruction.

9. An application calling device, the device comprising: An instruction parsing module, configured to parse the instruction in response to an instruction input by a user, and obtain application information and a confidence level in the instruction, where the confidence level represents the clarity of the information covered by the instruction; A confidence level judgment module, configured to judge whether the confidence level reaches a preset threshold; A first mode calling module, configured to call the application program pointed to by the application information in a first mode when the confidence level reaches the preset threshold; A second mode calling module, configured to call the application program pointed to by the application information in a second mode when the confidence level does not reach the preset threshold, where the second mode is different from the first mode.

10. A computer device, comprising: A memory and a processor, which are communicatively connected to each other, wherein the memory stores computer instructions, and the processor executes the computer instructions to execute the application calling method according to any one of claims 1 to 8.

11. A computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause a computer to execute the application calling method according to any one of claims 1 to 8.

Images