Voice control methods, devices, electronic devices and readable storage media

Abstract

This disclosure provides a voice control method, device, electronic device, and readable storage medium, relating to artificial intelligence technologies such as deep learning, natural language processing, and autonomous driving. The voice control method includes: acquiring a voice control command; obtaining text information based on the voice control command; inputting the text information and an information extraction command into a large language model; obtaining the output of the large language model as target function description information; the information extraction command being used by the large language model to extract function description information from the input text information; determining a target information set based on the target function description information; selecting the execution function corresponding to the target information set as the target execution function; and controlling a target object according to the target execution function. This disclosure enhances the scalability of voice control and improves the response success rate and accuracy of voice control.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the fields of artificial intelligence technology such as deep learning, natural language processing, and autonomous driving. It provides a voice control method, apparatus, electronic device, and readable storage medium. Background Technology

[0002] Existing technologies typically employ Natural Language Understanding (NLU) for voice control. This method requires pre-setting NLU information corresponding to different voice commands, as well as execution functions corresponding to different NLU information. If there is no execution function corresponding to the NLU information of the currently acquired voice command, voice control cannot be achieved. Summary of the Invention

[0003] According to a first aspect of this disclosure, a voice control method is provided, comprising: acquiring a voice control command; obtaining text information based on the voice control command; inputting the text information and an information extraction command into a large language model; acquiring the output of the large language model as target function description information, wherein the information extraction command is used by the large language model to extract function description information from the input text information; determining a target information set based on the target function description information; selecting an execution function corresponding to the target information set as a target execution function; and controlling a target object based on the target execution function.

[0004] According to a second aspect of this disclosure, a voice control device is provided, comprising: an acquisition unit for acquiring voice control instructions and obtaining text information based on the voice control instructions; a processing unit for inputting the text information and an information extraction instruction into a large language model, acquiring the output result of the large language model as target function description information, wherein the information extraction instruction is used by the large language model to extract function description information from the input text information; a determination unit for determining a target information set based on the target function description information, and selecting an execution function corresponding to the target information set as a target execution function; and a control unit for controlling a target object according to the target execution function.

[0005] According to a third aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0006] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described above.

[0007] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described above.

[0008] As can be seen from the above technical solutions, this disclosure imposes fewer restrictions on the input voice control commands, thereby enhancing the scalability of voice control, improving the success rate of voice control response, and leveraging the powerful understanding capabilities of large language models to improve the accuracy of the acquired objective function description information, thus enhancing the accuracy of voice control.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0012] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0013] Figure 3 This is a block diagram of an electronic device used to implement the voice control method of the embodiments of this disclosure. Detailed Implementation

[0014] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and mechanisms are omitted in the following description.

[0015] Figure 1 This is a schematic diagram based on the first embodiment of this disclosure. (See diagram below.) Figure 1 As shown, the voice control method in this embodiment specifically includes the following steps:

[0016] S101. Obtain voice control commands and obtain text information based on the voice control commands;

[0017] S102. Input the text information and information extraction instructions into the large language model, and obtain the output result of the large language model as the target function description information. The information extraction instructions are used by the large language model to extract function description information from the input text information.

[0018] S103. Determine the target information set based on the target function description information, and take the execution function corresponding to the target information set as the target execution function;

[0019] S104. Control the target object according to the target execution function.

[0020] The voice control method in this embodiment uses a large language model to extract target function description information from the text information corresponding to the voice control command. On the other hand, it determines the target execution function based on the target information set determined by the target function description information, thereby achieving the purpose of controlling the target object through the determined target execution function. This embodiment has fewer restrictions on the input voice control commands, thereby enhancing the scalability of voice control, improving the response success rate of voice control, and leveraging the powerful understanding ability of the large language model, it can also improve the accuracy of the obtained target function description information, thereby improving the accuracy of voice control.

[0021] The voice control method of this embodiment is applicable to any voice control scenario, such as voice control of smart home appliances and voice control of autonomous vehicles.

[0022] In this embodiment, after executing S101 to obtain the voice control command, the obtained voice control command can be converted into text information through a voice recognition system.

[0023] In this embodiment, after obtaining text information by executing S101, S102 is executed to input the text information and information extraction instructions into the large language model, and obtain the output result of the large language model as the target function description information; the information extraction instructions in this embodiment are used by the large language model to extract function description information from the text information.

[0024] In this embodiment, the Large Language Model (LLM) used can be any type of large language model.

[0025] In this embodiment, the information extraction instruction input to the large language model in S102 can be pre-set text information, which enables the large language model to determine that the content of this output is "function description information in the text information".

[0026] In this embodiment, when executing S102 to input text information and information extraction instructions into the large language model and obtain the output result of the large language model as the target function description information, the following may also be included: obtaining parameter extraction instructions; inputting text information, information extraction instructions and parameter extraction instructions into the large language model and obtaining the output result of the large language model as the target function description information and function parameters; in this embodiment, the parameter extraction instructions can be pre-set text information, which enables the large language model to determine that the content of this output is "function parameters in text information".

[0027] In other words, this embodiment can simultaneously input information extraction instructions and parameter extraction instructions into the large language model, enabling the large language model to extract function description information and function parameters from text information, thereby achieving the purpose of more accurately controlling the target object based on the extracted function parameters.

[0028] For example, if the text information obtained by executing S101 in this embodiment is "adjust the car fragrance to level 4", and if this embodiment executes S102 to input "adjust the car fragrance to level 4" and an information extraction instruction (e.g., extract function description information from the input text) into the large language model, the target function description information that can be obtained through the large language model is "car fragrance adjustment", or "fragrance adjustment", or "adjust car fragrance", etc.; if this embodiment inputs a parameter extraction instruction (e.g., extract function parameters from the input text) into the large language model when executing S102, then the function parameter that can also be obtained through the large language model is "level 4".

[0029] It is understood that, before executing S102 to use the large language model, this embodiment can also train the large language model so that it has the ability to output function description information and function parameters based on the input text information and instructions; wherein, this embodiment can use training data containing text information, extracted instructions, and function description information and function parameters to train the large language model.

[0030] When existing technologies implement voice control using Natural Language Understanding (NLU), they need to pre-set the NLU information (including domain information, intent information, etc.) corresponding to each voice control command, as well as the execution function corresponding to each NLU information. Then, in practical applications, the corresponding execution function is determined based on the NLU information corresponding to the voice control command input.

[0031] However, if the voice control command input does not have a pre-set execution function corresponding to its NLU information, the voice control cannot be implemented. For example, if only the execution function corresponding to the NLU information of "pause music" is pre-set, then when the input is "I want to pause music", the corresponding execution function cannot be obtained to complete the voice control.

[0032] This embodiment does not require pre-setting execution functions corresponding to NLU information for different voice control commands. It achieves the purpose of determining the execution function based on the function description information by extracting function description information from text information through a large language model. The restrictions on the input voice control commands are very small, thereby greatly improving the scalability of voice control. This allows the voice control commands "pause music" and "I want to pause music" in the above example to be completed.

[0033] In this embodiment, after executing S102 to obtain the output result of the large language model as the target function description information, S103 is executed to determine the target information set based on the target function description information, and the execution function corresponding to the target information set is taken as the target execution function.

[0034] In this embodiment, multiple information sets are pre-set, each containing multiple function descriptions. Different information sets correspond to different execution functions. It can be understood that the function descriptions contained in the information sets can be obtained through a large language model.

[0035] For example, information set 1 contains function description information 1 and function description information 2, and the execution function corresponding to information set 1 is execution function 1; information set 2 contains function description information 3, function description information 4 and function description information 5, and the execution function corresponding to information set 2 is execution function 3.

[0036] In this embodiment, when executing S103 to determine the target information set based on the objective function description information, an optional implementation method can be adopted: the information set containing the objective function description information is used as the target information set.

[0037] In other words, this embodiment simplifies the process of determining the target information set by querying the function description information contained in each information set and using the information set containing the target function description information as the target information set.

[0038] In this embodiment, when executing S103 to determine the target information set based on the objective function description information, the following method can also be used: obtain the target feature vector of the objective function description information; calculate the similarity between the target feature vector and the set feature vectors of multiple information sets respectively. In this embodiment, the average value of the feature vectors of multiple function description information contained in the information set can be used as the set feature vector of the information set; and the information set corresponding to the set feature vector with the highest similarity calculation result can be used as the target information set.

[0039] In practical use, it may not be possible to include all function description information in a certain information set. In order to ensure successful response to voice control, this embodiment selects the target information set from multiple information sets by calculating the similarity between the target function description information and different information sets, and then determines the execution function corresponding to the target information set to realize voice control.

[0040] After determining the target information set in S103 in this embodiment, the execution function corresponding to the target information set can be used as the target execution function according to the pre-set correspondence between the information set and the execution function; wherein, one information set corresponds to one execution function.

[0041] For example, the execution function corresponding to information set 1 is "pause1()", which is used to pause music; the execution function corresponding to information set 2 is "adjust1()", which is used to adjust the air conditioner; and the execution function corresponding to information set 3 is "adjust2()", which is used to adjust the fragrance.

[0042] It is understood that this embodiment can also add other function description information to the information set to update the information set; after executing S103 in this embodiment, if it is determined that the information set does not contain the current target function description information, the target function description information can be added to the target information set; this embodiment can also add function description information to the information set according to actual needs.

[0043] In this embodiment, after executing S103 to use the execution function corresponding to the target information set as the target execution function, S104 is executed to control the target object according to the target execution function.

[0044] In this embodiment, when executing S104 to control the target object according to the target execution function, the target object can first be determined according to the target execution function or the target function description information (determined according to the correspondence between the pre-set execution function or function description information and the object). In this embodiment, the target object can be a hardware object (such as a car window, air conditioner, etc.) or a software object (such as a music playback software, navigation software, etc.). Then, the target object is controlled accordingly according to the target execution function, such as adjusting, turning on or off the air conditioner, or opening or closing the car window, etc.

[0045] In this embodiment, when executing S104 to control the target object according to the target execution function, the following may also be included: obtaining function parameters; controlling the target object according to the target execution function and function parameters.

[0046] In other words, this embodiment can also combine the acquired function parameters to control the target object, which can improve the accuracy of controlling the target object.

[0047] For example, if the function parameter obtained in the above example is "4 levels", and the determined target execution function is "adjust2()", this embodiment can write "4 levels" into the "adjust2()" function when executing S104, so that the car fragrance can be adjusted to level 4.

[0048] Figure 2 This is a schematic diagram according to the second embodiment of this disclosure. (See diagram below.) Figure 2 As shown, the voice control device 200 of this embodiment includes:

[0049] Acquisition unit 201 is used to acquire voice control commands and obtain text information based on the voice control commands;

[0050] Processing unit 202 is used to input the text information and information extraction instructions into a large language model, and obtain the output result of the large language model as the target function description information. The information extraction instructions are used by the large language model to extract function description information from the input text information.

[0051] Determining unit 203 is used to determine a target information set based on the target function description information, and to take the execution function corresponding to the target information set as the target execution function;

[0052] Control unit 204 is used to control the target object according to the target execution function.

[0053] After acquiring the voice control command, the acquisition unit 201 can convert the acquired voice control command into text information through the voice recognition system.

[0054] In this embodiment, after the text information is obtained by the acquisition unit 201, the processing unit 202 inputs the text information and the information extraction instruction into the large language model and obtains the output result of the large language model as the target function description information; the information extraction instruction in this embodiment is used by the large language model to extract function description information from the text information.

[0055] In this embodiment, the Large Language Model (LLM) used can be any type of large language model.

[0056] The information extraction instruction input by the processing unit 202 to the large language model can be pre-set text information, which enables the large language model to determine that the content of this output is "function description information in the text information".

[0057] When the processing unit 202 inputs text information and information extraction instructions into the large language model and obtains the output result of the large language model as the target function description information, it may also include the following: obtaining parameter extraction instructions; inputting text information, information extraction instructions and parameter extraction instructions into the large language model and obtaining the output result of the large language model as the target function description information and function parameters; in this embodiment, the parameter extraction instructions can be pre-set text information, which enables the large language model to determine that the content of this output is "function parameters in text information".

[0058] In other words, the processing unit 202 can also simultaneously input information extraction instructions and parameter extraction instructions into the large language model, enabling the large language model to extract function description information and function parameters from the text information, thereby achieving the purpose of more accurately controlling the target object based on the extracted function parameters.

[0059] It is understandable that before using the large language model, the processing unit 202 can also train the large language model so that it has the ability to output function description information and function parameters based on the input text information and instructions; wherein, in this embodiment, training data containing text information, extraction instructions, function description information and function parameters can be used to train the large language model.

[0060] In this embodiment, after the processing unit 202 obtains the output result of the large language model as the target function description information, the determination unit 203 determines the target information set based on the target function description information and uses the execution function corresponding to the target information set as the target execution function.

[0061] In this embodiment, multiple information sets are pre-set, each containing multiple function descriptions, and different information sets correspond to different execution functions.

[0062] When determining the target information set based on the objective function description information, the determining unit 203 may adopt the following optional implementation method: taking the information set containing the objective function description information as the target information set.

[0063] In other words, the determining unit 203 can simplify the determination steps of the target information set by querying the function description information contained in each information set and taking the information set containing the target function description information as the target information set.

[0064] When determining the target information set based on the objective function description information, the determining unit 203 may also use the following methods: obtain the target feature vector of the objective function description information; calculate the similarity between the target feature vector and the set feature vectors of multiple information sets respectively; and take the information set corresponding to the set feature vector with the highest similarity calculation result as the target information set.

[0065] In actual use, it may not be possible to contain all the function description information in a certain information set. In order to ensure successful response to voice control, the determining unit 203 selects the target information set from multiple information sets by calculating the similarity between the target function description information and different information sets, and then determines the execution function corresponding to the target information set to realize voice control.

[0066] After determining the target information set, the determining unit 203 can use the execution function corresponding to the target information set as the target execution function according to the pre-set correspondence between the information set and the execution function; wherein, one information set corresponds to one execution function.

[0067] It is understood that this embodiment can also add other function description information to the information set to update the information set; the determining unit 203 can add the target function description information to the target information set if the current target function description information is not included in the information set; this embodiment can also add function description information to the information set through the determining unit 203 according to actual needs.

[0068] In this embodiment, after the determining unit 203 selects the execution function corresponding to the target information set as the target execution function, the control unit 204 controls the target object according to the target execution function.

[0069] When the control unit 204 controls the target object according to the target execution function, it can first determine the target object according to the target execution function or the target function description information. In this embodiment, the target object can be a hardware object (such as a car window, air conditioner, etc.) or a software object (such as a music playback software, navigation software, etc.). Then, it can perform corresponding control on the target object according to the target execution function, such as adjusting, turning on or off the air conditioner, or opening or closing the car window.

[0070] When controlling the target object according to the target execution function, the control unit 204 may also include the following: obtaining function parameters; controlling the target object according to the target execution function and function parameters.

[0071] In other words, the control unit 204 can also control the target object by combining the acquired function parameters, which can improve the accuracy of controlling the target object.

[0072] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0073] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0074] like Figure 3 The diagram shown is a block diagram of an electronic device for a voice control method according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0075] like Figure 3 As shown, device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 302 or a computer program loaded from storage unit 308 into random access memory (RAM) 303. RAM 303 may also store various programs and data required for the operation of device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0076] Multiple components in device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0077] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as voice control methods. For example, in some embodiments, the voice control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308.

[0078] In some embodiments, part or all of the computer program may be loaded and / or installed on the device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by computing unit 301, one or more steps of the voice control method described above may be performed. Alternatively, in other embodiments, computing unit 301 may be configured to perform the voice control method by any other suitable means (e.g., by means of firmware).

[0079] Various implementations of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0080] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable voice control device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0082] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for showing information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0083] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0084] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0085] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A voice control method, comprising: Obtain voice control commands and retrieve text information based on the voice control commands; The text information and information extraction instructions are input into the large language model, and the output of the large language model is obtained as the target function description information. The information extraction instructions are used by the large language model to extract function description information from the input text information. A target information set is determined based on the target function description information, and the execution function corresponding to the target information set is taken as the target execution function; The target object is controlled according to the target execution function.

2. The method according to claim 1, wherein, The step of inputting the text information and information extraction instructions into a large language model and obtaining the output of the large language model as the objective function description information includes: Get parameter extraction instructions; The text information, the information extraction instruction, and the parameter extraction instruction are input into the large language model, and the output of the large language model is obtained as the objective function description information and function parameters.

3. The method according to claim 1, wherein, The step of determining the target information set based on the objective function description information includes: The information set containing the objective function description information is taken as the objective information set.

4. The method according to claim 1, wherein, The step of determining the target information set based on the objective function description information includes: Obtain the target feature vector of the objective function description information; Calculate the similarity between the target feature vector and the set feature vectors of multiple information sets respectively; The information set corresponding to the feature vector of the set with the highest similarity calculation result is taken as the target information set.

5. The method according to claim 2, wherein, The control of the target object according to the target execution function includes: Obtain the function parameters; The target object is controlled according to the target execution function and the function parameters.

6. The method according to claim 4, further comprising: If it is determined that the objective function description information is not contained in the plurality of information sets, the objective function description information is added to the objective information set.

7. A voice control device, comprising: The acquisition unit is used to acquire voice control commands and obtain text information based on the voice control commands. The processing unit is used to input the text information and information extraction instructions into the large language model, obtain the output result of the large language model as the target function description information, and the information extraction instructions are used by the large language model to extract function description information from the input text information; The determining unit is configured to determine a target information set based on the target function description information, and to use the execution function corresponding to the target information set as the target execution function. The control unit is used to control the target object according to the target execution function.

8. The apparatus according to claim 7, wherein, When the processing unit inputs the text information and information extraction instructions into the large language model and obtains the output of the large language model as the objective function description information, it specifically performs the following: Get parameter extraction instructions; The text information, the information extraction instruction, and the parameter extraction instruction are input into the large language model, and the output of the large language model is obtained as the objective function description information and function parameters.

9. The apparatus according to claim 7, wherein, When determining the target information set based on the target function description information, the determining unit specifically performs the following: The information set containing the objective function description information is taken as the objective information set.

10. The apparatus according to claim 7, wherein, When determining the target information set based on the target function description information, the determining unit specifically performs the following: Obtain the target feature vector of the objective function description information; Calculate the similarity between the target feature vector and the set feature vectors of multiple information sets respectively; The information set corresponding to the feature vector of the set with the highest similarity calculation result is taken as the target information set.

11. The apparatus according to claim 8, wherein, When the control unit controls the target object according to the target execution function, it specifically performs the following: Obtain the function parameters; The target object is controlled according to the target execution function and the function parameters.

12. The apparatus of claim 10, wherein the determining unit is further configured to perform: If it is determined that the objective function description information is not contained in the plurality of information sets, the objective function description information is added to the objective information set.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images