CN119376871A - Application program calling method, device, computer equipment and storage medium - Google Patents
Application program calling method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN119376871A CN119376871A CN202311797385.4A CN202311797385A CN119376871A CN 119376871 A CN119376871 A CN 119376871A CN 202311797385 A CN202311797385 A CN 202311797385A CN 119376871 A CN119376871 A CN 119376871A
- Authority
- CN
- China
- Prior art keywords
- target
- execution
- application program
- instructions
- instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Stored Programmes (AREA)
Abstract
本发明涉及人工智能技术领域，公开了应用程序的调用方法、装置、计算机设备及存储介质，应用程序的调用方法包括：获取应用程序集合；其中，应用程序集合为预设模型根据目标指令识别的与目标指令对应的目标应用程序的集合；预设模型用于接收目标指令，并用于根据目标指令确定以及启动应用程序集合中的多个目标应用程序；获取目标指令，根据目标指令确定多个目标应用程序的执行步骤；调用多个目标应用程序，按照执行步骤执行目标指令。本发明通过预设模型确定并同时启动多个目标应用程序，缩短运行时间，提高用户体验。
The present invention relates to the field of artificial intelligence technology, and discloses a method, device, computer equipment and storage medium for calling an application. The method for calling an application includes: obtaining an application set; wherein the application set is a set of target applications corresponding to a target instruction identified by a preset model according to a target instruction; the preset model is used to receive the target instruction, and is used to determine and start multiple target applications in the application set according to the target instruction; obtain the target instruction, determine the execution steps of multiple target applications according to the target instruction; call multiple target applications, and execute the target instruction according to the execution steps. The present invention determines and starts multiple target applications at the same time through a preset model, shortens the running time, and improves the user experience.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a calling method and device of an application program, computer equipment and a storage medium.
Background
Along with the development of artificial intelligence (ARTIFICIAL INTELLIGENCE, AI), the application scenes are increased, the application of the artificial intelligence to the AI is increased, the application process of the AI comprises the steps of acquiring tasks issued by users, carrying out semantic understanding, information synthesis, reasonable reasoning and planning on the tasks, and finally calling external tools to complete the tasks.
In invoking external tools, there are generally two approaches, one for directly invoking the associated application programming interface (Application Programming Interface, API) of the interactive application and the other for simulating human actions to operate the interactive application interface. The application programs mentioned in the present invention refer to such interactive application programs, unless otherwise specified. For example, when the social software is called to send a message by using the AI large model, the AI large model can only simulate the clicking behavior of a person to operate the social software so as to complete sending of the message because the social software does not provide an application program interface to the outside. However, the running speed of the method is greatly restricted, and the next step can be executed after the last step is executed, so that the running time is too long, poor experience is brought to the user, and the method can not be applied to actual business scenes at all.
Disclosure of Invention
In view of the above, the present invention provides a method, apparatus, computer device and storage medium for calling an application program, so as to solve the problem of excessively long running time.
The invention provides a calling method of an application program, which is applied to an AI large model and comprises the steps of obtaining an application program set, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions, obtaining the target instructions, determining execution steps of the plurality of target application programs according to the target instructions, calling the plurality of target application programs, and executing the target instructions according to the execution steps.
The method comprises the steps of acquiring an application program set, wherein the application program set is a set of target application programs corresponding to target instructions, which are identified by a preset model according to the target instructions, namely the preset model is used for identifying and starting the target application programs corresponding to the target instructions according to the target instructions, determining execution steps of a plurality of target application programs according to the target instructions, and executing the target instructions according to the execution steps. According to the method and the device, the target application program corresponding to the target instruction is started in advance, the target instruction is executed according to the execution steps, and compared with the prior art that one application program is opened to obtain the execution result and then the next application program is opened to execute, the method and the device do not need to wait for completion of each step, so that the time for starting and running the application program is shortened, the running speed is improved, and the experience of a user is improved.
In an alternative embodiment, the determining the execution steps of the plurality of target application programs according to the target instructions comprises the steps of identifying and decomposing the target instructions to obtain a plurality of sub-instructions, determining the execution sequence of the plurality of target application programs corresponding to the plurality of sub-instructions, and determining the execution steps of the plurality of target application programs according to the execution sequence.
The invention identifies and decomposes the target instruction to obtain different sub-instructions corresponding to different target application programs, and can realize parallel execution among different target application programs, thereby reducing the execution time of the target instruction, determining execution steps of a plurality of target application programs according to the execution sequence, determining relevance among the target application programs according to different sub-instructions, setting parallel sub-instructions in the execution sequence when the sub-instructions are not relevant, and setting the execution steps which are not relevant in the execution steps to be executed in parallel, so that the running time is shortened, and the execution efficiency of the target instructions is improved.
In an alternative embodiment, the pre-set model is a fine-tuning specialized small model and/or a rules engine.
In an alternative implementation, the application program set is a set of target application programs corresponding to the target instructions, which are identified by the rule engine according to the target instructions, and the rule engine is used for extracting keywords of the target instructions, searching a target user keyword database, a system dynamic keyword database and a system static keyword database according to the keywords, and determining and starting a plurality of target application programs in the application program set according to search results.
In the invention, besides the target instruction can be identified by the preset model, the rule engine can also identify the target instruction, and a plurality of target application programs are determined according to the extraction and multiple retrieval of the keywords, so that the determined target application programs are more accurate and are more attached to the target instruction.
In an alternative embodiment, the executing steps include a parallel executing step and a serial executing step, wherein the parallel executing step represents executing steps of parallel processing of the plurality of executing steps, the serial executing step represents that a sequence relationship exists between the executing steps, and the second executing step is executed after the execution of the first executing step is finished.
In the invention, the execution steps comprise a parallel execution step and a serial execution step, namely the execution steps comprise an execution step capable of being processed in parallel and an execution step which is executed independently, the parallel processing improves the execution efficiency of the target instruction, shortens the running time and improves the experience feeling of the user.
In an alternative embodiment, after the target instruction is executed according to the executing step, the method further includes obtaining a plurality of execution results sent by a plurality of target application programs, combining the plurality of execution results to obtain a target execution result, and displaying the target execution result.
In the invention, the target execution result is displayed, so that the user can clearly know the execution condition of the target instruction, and the target instruction is ensured to be executed according to the actual intention of the user.
The invention provides a calling system of an application program, which comprises a preset model, an AI big model and an AI big model, wherein the preset model is used for receiving target instructions, identifying application program sets corresponding to the target instructions according to the target instructions, and starting a plurality of target application programs in the application program sets according to the target instructions, the application program sets represent the sets of the target application programs corresponding to the target instructions, the preset model is used for sending the application program sets to the AI big model, the AI big model is used for acquiring the target instructions and determining execution steps of the target application programs according to the target instructions, and the AI big model is used for calling the target application programs and executing the target instructions according to the execution steps.
The method comprises the steps of receiving a target instruction, identifying an application program set corresponding to the target instruction according to the target instruction, starting a plurality of target application programs in the application program set according to the target instruction, sending the application program set to an AI large model, acquiring the target instruction, determining execution steps of the target application programs according to the target instruction, and calling the target application programs according to the execution steps by the AI large model. According to the method and the device, the target application program corresponding to the target instruction is started in advance, and the target instruction is executed according to the execution steps, and compared with the prior art that one application program is opened to obtain the execution result and then the next application program is opened to execute, the completion of each step is not required to be waited, so that the time for starting and running the application program is shortened, the running speed is improved, and the experience feeling of a user is improved.
In an alternative embodiment, the pre-set model is a fine-tuning specialized small model and/or a rules engine.
In an alternative embodiment, the rules engine receives target instructions entered by a target user and determines the target application based on interactions between the keyword management module, the target user keyword database, the system dynamic keyword database, and the system static keyword database.
In an alternative implementation mode, the system further comprises an AI large model, wherein the AI large model is further used for acquiring a plurality of execution results sent by a plurality of target application programs, combining the plurality of execution results to obtain a target execution result, and displaying the target execution result.
The invention provides an application program calling device which is applied to an AI large model and comprises an application program set acquisition module and a target instruction execution module, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions, the target instruction acquisition module is used for acquiring the target instructions and determining execution steps of the plurality of target application programs according to the target instructions, and the target instruction execution module is used for calling the plurality of target application programs and executing the target instructions according to the execution steps.
In a fourth aspect, the present invention provides a computer device, including a memory and a processor, where the memory and the processor are communicatively connected to each other, and the memory stores computer instructions, and the processor executes the computer instructions, thereby executing the calling method of the application program of the first aspect or any implementation manner corresponding to the first aspect.
In a fifth aspect, the present invention provides a computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the calling method of the application program of the first aspect or any of the embodiments corresponding thereto.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an application calling method in the related art according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a method of invoking an application according to an embodiment of the invention;
FIG. 3 is a schematic diagram of an example design of a rules engine in accordance with an embodiment of the invention;
FIG. 4 is a flow diagram of a rule engine execution method according to an embodiment of the invention;
FIG. 5 is a flow diagram of a calling method of another application according to an embodiment of the invention;
FIG. 6 is a flow chart of a method of invoking a further application according to an embodiment of the invention;
FIG. 7 is a flow diagram of a method of operation of a specialized small model or rule engine according to an embodiment of the present invention;
FIG. 8 is a flow diagram of the call system operation of an application according to an embodiment of the present invention;
FIG. 9 is a block diagram of a calling device of an application according to an embodiment of the present invention;
fig. 10 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a flow chart of an application calling method in the related art is shown, in the related art, a plurality of target application programs are called, target instructions are executed according to execution steps, as shown in fig. 1, after the instructions are received, an AI large model control application running control module starts an application program a according to the instructions and controls the application program a to execute the instructions to obtain an execution result a, starts an application program B according to the execution result a and controls the application program B to execute the instructions to obtain an execution result B, starts an application program C according to the execution result B, and controls the application program C to execute the instructions to obtain an execution result C.
Therefore, after the execution of each application program in the related art is finished, the next application program can be started, which results in longer running time and lower efficiency.
The embodiment of the invention provides a calling method of an application program, which determines and simultaneously starts a plurality of target application programs through a preset model so as to achieve the effects of shortening the running time and improving the user experience.
According to an embodiment of the present invention, there is provided an embodiment of a calling method of an application program, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order different from that herein.
In this embodiment, a calling method of an application program is provided, which may be used for an AI large model, and fig. 2 is a flowchart of the calling method of the application program according to an embodiment of the present invention, as shown in fig. 2, where the flowchart includes the following steps:
Step S201, an application program set is obtained, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, and the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions.
In some alternative embodiments, the pre-set model is a fine-tuning specialized small model and/or a rules engine.
The preset model may be a small model dedicated for Fine Tuning (Fine Tuning), a rule engine, or a small model dedicated for Fine Tuning and a rule engine.
The preset model is used for identifying the target command and determining a plurality of target application programs corresponding to the target command according to the target command.
The target instruction is an instruction to be executed, which is input by a target user, the input form can be voice input, text input, gesture input and the like, and the target application program is an application program corresponding to the target instruction, namely, the target application program is an application program to be operated for executing the target instruction.
In the embodiment of the invention, the target application programs are interactive application programs under the condition of not being described.
The method includes the steps of receiving a target instruction, sending a target application program to a mail client, and sending a target application program to the mail client, wherein the target instruction is ' the latest 10 news summarized today ' and the summarized content is sent to L ' through mail, identifying the target application program as a news application according to the target instruction by a preset model, generating an application program set, wherein the application program set comprises the news application and the mail client, and starting the target application program, namely starting the news application and the mail client.
In some alternative embodiments, the application program set is a set of target application programs corresponding to the target instructions, which are identified by the rule engine according to the target instructions, wherein the rule engine is used for extracting keywords of the target instructions, searching a target user keyword database, a system dynamic keyword database and a system static keyword database according to the keywords, and determining and starting a plurality of target application programs in the application program set according to search results.
The rule engine is a component embedded in the application program, rules of the rule engine can be customized according to actual requirements, in the embodiment of the invention, the rule engine has the same function as a preset model and different running processes, after receiving a target instruction, the rule engine extracts keywords of the target instruction, and searches a target user keyword database, a system dynamic keyword database and a system static keyword database according to the keywords, and determines the target application program according to search results.
In the rule engine, the target user keyword database represents a database for storing common keywords of target users frequently using an AI large model, the system dynamic keyword database represents a database for storing keywords changed in real time, and the system static keyword database represents a database for storing keywords which are not changed.
As shown in fig. 3, which is a schematic diagram of a design example of a rule engine, in fig. 3, a target instruction input by a target user is received, keywords of the target instruction are extracted in a keyword management module, a target user keyword database, a system dynamic keyword database and a system static keyword database are searched according to the keywords, a search result is obtained, and a target application program is determined according to the search result.
In the embodiment of the invention, as shown in fig. 4, a schematic diagram of a rule engine execution method is shown, which includes receiving a target instruction input by a target user according to the rule engine, and determining a target application program according to interactions among a keyword management module target user keyword database, a system dynamic keyword database and a system static keyword database. As shown in fig. 4, exemplary, for keywords such as "send message", "contact", "notification", "talk" and the like, corresponding target application is a social application, for keywords such as "buy me", "order", "price", "promotion", "shopping live broadcast", and the like, corresponding target application is a shopping application, for keywords such as "hot keyword", "economic keyword", "political keyword", "star keyword", and the like, corresponding target application is a news application, and for keywords such as "search for", "calculate one", "time keyword", "weather keyword", and the like, corresponding target application is a tool application.
Illustratively, in the target user keyword database, "sending a message", for the target user, the application program used is social software V, in the system dynamic keyword database, "news hot spot" refers to a hot spot on news software S, and in the system static keyword database, "setting an alarm clock" refers to setting an alarm clock on alarm clock software.
In the embodiment of the invention, besides the target instruction can be identified by the preset model, the rule engine can also identify the target instruction, and a plurality of target application programs are determined according to the extraction and multiple retrieval of the keywords, so that the determined target application programs are more accurate and are more attached to the target instruction.
Step S202, a target instruction is acquired, and execution steps of a plurality of target application programs are determined according to the target instruction.
The mode of acquiring the target instruction may be that the user sends the target instruction in a voice form to the AI large model, or the target instruction in a text form typed by the target user, or the like.
In some alternative embodiments, the target instruction is identified and decomposed to obtain a plurality of sub-instructions, an execution order of a plurality of target applications corresponding to the plurality of sub-instructions is determined, and execution steps of the plurality of target applications are determined according to the execution order.
For an exemplary embodiment, for a target instruction, summarizing the 10 hottest news items today, sending the summarized content to an L' through mail, decomposing the target instruction to obtain a first sub-instruction, and running a news application; the method comprises the steps of receiving a first sub-instruction, summarizing the first 10 news contents, receiving a second sub-instruction, summarizing the first 10 news contents, receiving a third sub-instruction, opening a mail client, receiving a fourth sub-instruction, inputting an L mail address in an address field of the mail client, receiving a fifth sub-instruction, pasting the summarized contents in the second sub-instruction into a content field of the mail client and sending the content field, enabling an execution sequence of a target application program to be the news application and the mail client at the same time, enabling the execution sequence of the target application program to be the first sub-instruction and the third sub-instruction to be executed in parallel, enabling the second sub-instruction and the fourth sub-instruction to be executed in parallel, and finally executing the fifth sub-instruction.
In some alternative embodiments, the executing steps include a parallel executing step and a serial executing step, wherein the parallel executing step represents executing steps of parallel processing of the plurality of executing steps, the serial executing step represents that a sequence relationship exists between the executing steps, and the second executing step is executed after the execution of the first executing step is finished.
The sequence relationship between the first execution step and the second execution step is that the first execution step precedes the second execution step.
In some optional embodiments, there is no dependency between the parallel execution steps, there is a dependency between the serial execution steps, and the dependency represents a precedence relationship between the execution steps.
For example, running the news application and opening the mail client may be performed in parallel, so that running the news application and opening the mail client are parallel performing steps, while pasting the content summarized in the second sub-instruction into the content column of the mail client and transmitting the content can only be performed separately, so that pasting the content summarized in the second sub-instruction into the content column of the mail client and transmitting the content as serial performing steps.
In the embodiment of the invention, the execution steps comprise a parallel execution step and a serial execution step, namely the execution steps comprise an execution step capable of being processed in parallel and an execution step independently executed, the parallel processing improves the execution efficiency of the target instruction, shortens the running time and improves the experience feeling of a user.
Step S203, a plurality of target application programs are called, and target instructions are executed according to the executing steps.
In the embodiment of the invention, the target execution result is displayed, so that a user can clearly know the execution condition of the target instruction, and the target instruction is ensured to be executed according to the intention of the user.
According to the calling method of the application program, an application program set is obtained, wherein the application program set is a set of target application programs corresponding to target instructions, which are obtained by a preset model according to target instruction identification, namely the preset model is used for identifying and starting the target application programs corresponding to the target instructions according to the target instructions, determining execution steps of a plurality of target application programs according to the target instructions, and executing the target instructions according to the execution steps. According to the embodiment of the invention, the target application program corresponding to the target instruction is started in advance, the target instruction is executed according to the execution steps, and compared with the prior art that one application program is opened to obtain the execution result and then the next application program is opened to execute, the method and the device have the advantages that the completion of each step is not required to be waited, the starting and running time of the application program is shortened, the running speed is improved, and the experience feeling of a user is improved.
In this embodiment, a calling method of an application program is provided, which may be used in the above-mentioned AI big model, and fig. 5 is a flowchart of a calling method of another application program according to an embodiment of the present invention, as shown in fig. 5, where the flowchart includes the following steps:
Step S501, an application program set is obtained, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, and the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions. Please refer to step S201 in the embodiment shown in fig. 2 in detail, which is not described herein.
Step S502, a target instruction is acquired, and execution steps of a plurality of target application programs are determined according to the target instruction. Please refer to step S202 in the embodiment shown in fig. 2, which is not described herein.
In some alternative embodiments, the step S502 includes:
In step S5021, the target instruction is identified and decomposed to obtain a plurality of sub-instructions, and the execution order of the plurality of target application programs corresponding to the plurality of sub-instructions is determined.
Step S5022, determining execution steps of the plurality of target application programs according to the execution sequence.
Step S503, calling a plurality of target application programs, and executing the target instruction according to the executing step. Please refer to step S203 in the embodiment shown in fig. 2 in detail, which is not described herein.
Step S504, a plurality of execution results sent by a plurality of target application programs are obtained, the execution results are combined to obtain a target execution result, and the target execution result is displayed.
The calling method of another application program provided in this embodiment identifies and decomposes the target instruction to obtain different sub-instructions corresponding to different target application programs, and can implement parallel execution between different target application programs, thereby reducing execution time of the target instruction, determining execution sequences of a plurality of target application programs corresponding to a plurality of sub-instructions, determining execution steps of a plurality of target application programs according to the execution sequence, determining relevance among the target application programs according to different sub-instructions, setting parallel sub-instructions in the execution sequence when the sub-instructions are not relevant, and setting the execution steps which are not relevant in the execution steps to be executed in parallel, so that the running time is shortened, and the execution efficiency of the target instructions is improved.
In this embodiment, a method for calling an application program is provided, which may be used for the above-mentioned AI large model, and fig. 6 is a flowchart of a method for calling another application program according to an embodiment of the present invention, as shown in fig. 6, including:
The method comprises the steps of obtaining a target instruction, determining and starting an application program A and an application program B corresponding to the target instruction according to a special small model or a rule engine, controlling an application running control module to decompose the target instruction into a first sub-instruction, a second sub-instruction, a third sub-instruction and a fourth sub-instruction according to an AI large model, controlling the application program A to execute the third sub-instruction and the fourth sub-instruction, controlling the application program B to execute the first sub-instruction and the second sub-instruction, and accordingly obtaining a third execution result of the application program A, a fourth execution result and a second execution result and a first execution result of the application program B.
In fig. 6, a second sub-instruction and a fourth sub-instruction indicated by a bold line are executed in parallel, a first sub-instruction and a third sub-instruction indicated by a thin line are executed in parallel, the execution sequence of the embodiment of the present invention is that the first sub-instruction and the third sub-instruction of the thin line are executed first, then the second sub-instruction and the fourth sub-instruction of the bold line are executed, a bold dashed line indicates a second execution result and a fourth execution result corresponding to the second sub-instruction and the fourth sub-instruction, and a thin dashed line indicates a first execution result and a third execution result corresponding to the first sub-instruction and the third sub-instruction.
In the embodiment of the invention, the first sub-instruction and the third sub-instruction are executed first, wherein the first sub-instruction and the third sub-instruction are executed in parallel, the application program A corresponding to the first sub-instruction and the application program B corresponding to the third sub-instruction are executed in parallel, and the second sub-instruction and the fourth sub-instruction are executed later, wherein the second sub-instruction and the fourth sub-instruction are executed in parallel, and the application program A corresponding to the fourth sub-instruction and the application program B corresponding to the second sub-instruction are executed in parallel. In the embodiment of the invention, the application program A and the application program B are executed simultaneously according to the sub-instruction, and the execution of one application program is not required to be stopped and the other application program is executed, so that the parallelism is improved, the running time is reduced, and the execution efficiency of the target instruction is improved.
In the embodiment of the present invention, the application program is determined and started by using the special small model or the rule engine, for example, as shown in fig. 7, which is a schematic diagram of an operation method of the special small model or the rule engine, the special small model or the rule engine determines a plurality of application programs corresponding to the target instruction according to the target instruction, so that the application program a can be started to the leading application program N by preparing the operation environments of the plurality of application programs, and starting the plurality of application programs, and the special trained small model of the application operation control module controls the plurality of application programs in parallel and executes the target instruction.
Wherein the specifically trained small model is a machine learning model for a particular task. Typically, when training a small model, given enough samples of a particular domain, these samples are typically question-and-answer samples, i.e., given questions and answers, by learning these samples, the reasoning skills of that domain are mastered.
In the embodiment of the invention, the reasoning calculation force is greatly reduced due to the fact that the special training small model is only applied to a specific scene, the reasoning cost is greatly reduced, the response time of the special training small model is fast, and the response speed is faster due to the fact that the parameters are small and the special training process is provided.
In this embodiment, a call system of an application program is provided, and fig. 8 is a flowchart of the operation of the call system of the application program according to an embodiment of the present invention, as shown in fig. 8, the flowchart includes the following steps:
Step S801, a preset model is used for receiving a target instruction, identifying an application program set corresponding to the target instruction according to the target instruction, and starting a plurality of target application programs in the application program set according to the target instruction, wherein the application program set represents a set of target application programs corresponding to the target instruction.
Step S802, presetting a model, which is used for sending an application program set to the AI large model.
Step 803, an AI large model is used for acquiring a target instruction and determining execution steps of a plurality of target application programs according to the target instruction.
Step S804, AI big model, used for calling a plurality of target application programs, according to the execution steps to execute the target instruction.
In some alternative embodiments, the pre-set model is a fine-tuning specialized small model and/or a rules engine.
In some alternative embodiments, the rules engine receives target instructions entered by a target user and determines the target application based on interactions between the keyword management module, the target user keyword database, the system dynamic keyword database, and the system static keyword database.
In some optional embodiments, the system further comprises an AI large model, wherein the AI large model is further used for acquiring a plurality of execution results sent by a plurality of target application programs, combining the plurality of execution results to obtain a target execution result, and displaying the target execution result.
The method comprises the steps of receiving a target instruction, identifying an application program set corresponding to the target instruction according to the target instruction, starting a plurality of target application programs in the application program set according to the target instruction, sending the application program set to an AI large model, acquiring the target instruction, determining execution steps of the plurality of target application programs according to the target instruction, and calling the plurality of target application programs to execute the target instruction according to the execution steps. According to the method and the device, the target application program corresponding to the target instruction is started in advance, and the target instruction is executed according to the execution steps, and compared with the prior art that one application program is opened to obtain the execution result and then the next application program is opened to execute, the completion of each step is not required to be waited, so that the time for starting and running the application program is shortened, the running speed is improved, and the experience feeling of a user is improved.
The embodiment also provides a calling device of an application program, which is used for implementing the above embodiment and the preferred implementation manner, and the description is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides an application calling device, as shown in fig. 9, including:
The application program set acquisition module 901 is used for acquiring an application program set, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, and the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions.
The target instruction acquiring module 902 is configured to acquire a target instruction, and determine execution steps of a plurality of target application programs according to the target instruction.
The target instruction execution module 903 is configured to call a plurality of target applications and execute target instructions according to execution steps.
In some alternative embodiments, the target instruction fetch module 902 includes:
and the execution sequence determining unit is used for identifying and decomposing the target instruction to obtain a plurality of sub-instructions and determining the execution sequence of a plurality of target application programs corresponding to the plurality of sub-instructions.
And the execution step determining unit is used for determining execution steps of the plurality of target application programs according to the execution sequence.
In some alternative embodiments, the apparatus further comprises:
The execution result display module is used for acquiring a plurality of execution results sent by a plurality of target application programs, combining the execution results to obtain a target execution result, and displaying the target execution result.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The calling device of the Application program in this embodiment is presented as a functional unit, where the unit refers to an ASIC (Application SPECIFIC INTEGRATED Circuit) Circuit, a processor and a memory that execute one or more software or firmware programs, and/or other devices that can provide the above functions.
The embodiment of the invention also provides computer equipment, which is provided with the calling device of the application program shown in the figure 9.
Referring to fig. 10, fig. 10 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, and as shown in fig. 10, the computer device includes one or more processors 1010, a memory 1020, and interfaces for connecting components, including a high-speed interface and a low-speed interface. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 1010 is illustrated in fig. 10.
The processor 1010 may be a central processor, a network processor, or a combination thereof. Wherein the processor 1010 may further comprise 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.
Wherein the memory 1020 stores instructions executable by the at least one processor 1010 to cause the at least one processor 1010 to perform methods shown in implementing the above embodiments.
The memory 1020 may include a storage program area that may store an operating system, application programs required for at least one function, and a storage data area that may store data created according to the use of the computer device, etc. In addition, memory 1020 may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some alternative embodiments, memory 1020 may optionally include memory located remotely from processor 1010, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 1020 may include volatile memory, such as random access memory, nonvolatile memory, such as flash memory, hard disk, or solid state disk, and memory 1020 may include a combination of the above types of memory.
The computer device also includes a communication interface 1030 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium may be a magnetic disk, an optical disk, a read-only memory, a random-access memory, a flash memory, a hard disk, a solid state disk, or the like, and further, the storage medium may further include a combination of the above types of memories. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (13)
1. A method for invoking an application program, applied to an AI large model, the method comprising:
The method comprises the steps of acquiring an application program set, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions, and the preset model is used for receiving the target instructions and determining and starting a plurality of target application programs in the application program set according to the target instructions;
acquiring the target instruction, and determining execution steps of the plurality of target application programs according to the target instruction;
And calling the target application programs, and executing the target instructions according to the executing steps.
2. The method of claim 1, wherein the step of determining the plurality of target applications based on the target instructions comprises:
Identifying and decomposing the target instruction to obtain a plurality of sub-instructions, and determining the execution sequence of the plurality of target application programs corresponding to the plurality of sub-instructions;
and determining the execution steps of the target application programs according to the execution sequence.
3. The method according to claim 1 or 2, wherein the pre-set model is a fine-tuning specific small model and/or a rules engine.
4. The method of claim 3, wherein the step of,
The rule engine is used for extracting keywords of the target instructions, searching a target user keyword database, a system dynamic keyword database and a system static keyword database according to the keywords, and determining and starting a plurality of target application programs in the application program set according to search results.
5. A method according to claim 1 or 2, characterized in that,
The execution steps comprise parallel execution steps and serial execution steps, wherein the parallel execution steps represent execution steps of parallel processing of a plurality of execution steps, the serial execution steps represent that a sequence relationship exists among the execution steps, and when the execution of the first execution step is finished, the second execution step is executed.
6. The method according to claim 1 or 2, wherein after said executing said target instruction according to said executing step, said method further comprises:
And acquiring a plurality of execution results sent by the plurality of target application programs, combining the plurality of execution results to obtain a target execution result, and displaying the target execution result.
7. A call system for an application program, the system comprising:
The system comprises a preset model, a target instruction, an application program set, a target application program set and a control module, wherein the preset model is used for receiving the target instruction, identifying an application program set corresponding to the target instruction according to the target instruction, and starting a plurality of target application programs in the application program set according to the target instruction;
the preset model is used for sending the application program set to an AI large model;
the AI large model is used for acquiring the target instruction and determining execution steps of the plurality of target application programs according to the target instruction;
And the AI large model is used for calling the plurality of target application programs and executing the target instructions according to the executing steps.
8. The system of claim 7, wherein the pre-set model is a fine-tuning specialized small model and/or a rules engine.
9. The system of claim 8, wherein the rules engine receives target instructions entered by a target user and determines the target application based on interactions between the keyword management module, the target user keyword database, the system dynamic keyword database, and the system static keyword database.
10. The system of claim 7, wherein the system further comprises:
the AI large model is further used for acquiring a plurality of execution results sent by the plurality of target application programs;
the AI large model is also used for combining the execution results to obtain a target execution result and displaying the target execution result.
11. An apparatus for invoking an application program, applied to an AI large model, comprising:
The system comprises an application program set acquisition module, an application program set acquisition module and a control module, wherein the application program set is a set of target application programs which are identified by a preset model according to target instructions and correspond to the target instructions;
the target instruction acquisition module is used for acquiring the target instructions and determining execution steps of the target application programs according to the target instructions;
And the target instruction execution module is used for calling the target application programs and executing the target instructions according to the execution steps.
12. A computer device, comprising:
A memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the method of invoking the application of any of claims 1 to 6.
13. A computer-readable storage medium having stored thereon computer instructions for causing a computer to execute the calling method of the application program of any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311797385.4A CN119376871A (en) | 2023-12-25 | 2023-12-25 | Application program calling method, device, computer equipment and storage medium |
| PCT/CN2024/130479 WO2025139391A1 (en) | 2023-12-25 | 2024-11-07 | Application invocation method and apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311797385.4A CN119376871A (en) | 2023-12-25 | 2023-12-25 | Application program calling method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119376871A true CN119376871A (en) | 2025-01-28 |
Family
ID=94333356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311797385.4A Pending CN119376871A (en) | 2023-12-25 | 2023-12-25 | Application program calling method, device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN119376871A (en) |
| WO (1) | WO2025139391A1 (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108762844B (en) * | 2018-05-29 | 2021-09-07 | Oppo广东移动通信有限公司 | Application preloading method, device, storage medium and terminal |
| US11573823B2 (en) * | 2019-11-18 | 2023-02-07 | International Business Machines Corporation | Parallel execution of applications |
| CN114237444A (en) * | 2021-11-30 | 2022-03-25 | 阿波罗智联(北京)科技有限公司 | Application program starting method and device, electronic equipment and storage medium |
| CN115562748A (en) * | 2022-09-26 | 2023-01-03 | 展讯通信（深圳）有限公司 | Application starting method and device, chip and module equipment |
| CN116450014A (en) * | 2023-04-03 | 2023-07-18 | 武汉星纪魅族科技有限公司 | Application running method, device, equipment and storage medium |
-
2023
- 2023-12-25 CN CN202311797385.4A patent/CN119376871A/en active Pending
-
2024
- 2024-11-07 WO PCT/CN2024/130479 patent/WO2025139391A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2025139391A1 (en) | 2025-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9582757B1 (en) | Scalable curation system | |
| US20200301954A1 (en) | Reply information obtaining method and apparatus | |
| CN111753075B (en) | Method and device for creating customer service robot question-answer data and computer equipment | |
| CN116501960B (en) | Content retrieval method, device, equipment and medium | |
| US20130239006A1 (en) | Aggregator, filter and delivery system for online context dependent interaction, systems and methods | |
| CN116521841A (en) | Method, device, equipment and medium for generating reply information | |
| CN117853600A (en) | Image generation method, device, electronic equipment and storage medium | |
| US11762937B2 (en) | Information processing apparatus, information processing system, and method of processing information | |
| CN109165286A (en) | Automatic question-answering method, device and computer readable storage medium | |
| CN108831444A (en) | Semantic resources training method and system for voice dialogue platform | |
| CN119807345A (en) | A joint debugging service method and system based on the integration of AI big model and automated testing technology | |
| WO2025130246A1 (en) | Prompt word expansion method and apparatus, and computer device and storage medium | |
| WO2025026189A1 (en) | Method and apparatus for prompt word management, device, and storage medium | |
| CN117765117B (en) | Image editing method, device, electronic device and storage medium | |
| CN118152617A (en) | Method, device, electronic equipment and storage medium for configuring image for text | |
| CN117610539A (en) | Intention execution method, device, electronic equipment and storage medium | |
| CN119376871A (en) | Application program calling method, device, computer equipment and storage medium | |
| CN116821463A (en) | Searching method, searching device, electronic equipment and storage medium | |
| CN117008807A (en) | Keyboard theme switching method, device, equipment and readable storage medium | |
| CN106682221B (en) | Question-answer interaction response method and device and question-answer system | |
| CN113111643B (en) | Information processing method, device and apparatus | |
| WO2025086562A1 (en) | Method and apparatus for storing data, and device and medium | |
| CN119739875A (en) | Method, apparatus, device, medium and program product for article retrieval | |
| WO2025091733A1 (en) | Method for interaction with digital assistant, apparatus, device and storage medium | |
| AU2022441312A1 (en) | Intelligent assistant system for conversational job search |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |