Simulation software function calling method and device
Through voice recognition technology combined with the secondary development of simulation software, the problem of inability to achieve voice control in complex simulation software scenarios is solved, and higher operation efficiency and accuracy are achieved, lowering the user's operation threshold.
Patent Information
- Application Number
- CN202410982462.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-15
AI Technical Summary
Voice control cannot be implemented in complex simulation software scenarios, resulting in high user operation thresholds and increased time consumption.
Through voice recognition technology combined with the secondary development of simulation software, the functions and basic information of each simulation software are determined, the calling interface and instructions are created, and the user voice command is identified when the user is detected, and the target calling command is determined to realize the corresponding functions.
It lowers the threshold for using simulation software, reduces the time for multi-software operation, and provides higher control efficiency and accuracy. It is similar to the intelligent assistant, and uses multiple simulation software to simulate quickly and accurately.
Smart Images

Figure CN118963696A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method and device for calling a simulation software function. Background Art
[0002] Simulation software allows users to simulate and analyze processes, systems or phenomena in the real world in a virtual environment. This type of software is widely used in many fields such as scientific research, engineering design, product development, education and training. Through simulation, users can predict the behavior, performance and potential problems of the system without actually building a physical prototype, thereby saving cost, time and resources. However, more complex joint simulations require the control of multiple simulation software, which increases the user's usage threshold and time consumption. In order to improve the efficiency of the use of simulation software and facilitate users. This method can combine voice recognition with the secondary development of simulation software, so that users can directly control the simulation software through voice and complete the joint simulation of multiple simulation software. Summary of the invention
[0003] In view of this, the embodiments of the present application provide a simulation software function calling method, device, electronic device and computer-readable storage medium to solve the problem in the prior art that voice control cannot be achieved in complex simulation software scenarios.
[0004] The first aspect of an embodiment of the present application provides a method for calling a simulation software function, including: determining multiple functions provided by each simulation software, and obtaining basic information and related information of each function; creating a calling interface and a calling instruction for the function based on the basic information of each function; adding auxiliary information to the calling instruction of the function based on the related information of each function; when a voice instruction issued by a user is detected, performing voice recognition on the voice instruction to obtain a recognition result; based on each calling instruction and the auxiliary information of the calling instruction, determining a target calling instruction corresponding to the recognition result from multiple calling instructions; and implementing the corresponding function through the calling interface corresponding to the target calling instruction.
[0005] According to a second aspect of an embodiment of the present application, a simulation software function calling device is provided, comprising: an acquisition module, configured to determine multiple functions provided by each simulation software, and to obtain basic information and related information of each function; a creation module, configured to create a calling interface and a calling instruction for each function based on the basic information of the function; an addition module, configured to add supplementary information to the calling instruction of the function based on the related information of each function; an identification module, configured to perform voice recognition on the voice instruction to obtain a recognition result when a voice instruction issued by a user is detected; a determination module, configured to determine a target calling instruction corresponding to the recognition result from multiple calling instructions based on each calling instruction and the supplementary information of the calling instruction; and a calling module, configured to implement the corresponding function through the calling interface corresponding to the target calling instruction.
[0006] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0007] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0008] Compared with the prior art, the embodiments of the present application have the following beneficial effects: determining multiple functions provided by each simulation software, and obtaining basic information and related information of each function; creating a call interface and a call instruction for the function based on the basic information of each function; adding auxiliary information to the call instruction of the function based on the related information of each function; performing voice recognition on the voice instruction to obtain a recognition result when a voice instruction issued by the user is detected; determining the target call instruction corresponding to the recognition result from multiple call instructions based on each call instruction and the auxiliary information of the call instruction; and implementing the corresponding function through the call interface corresponding to the target call instruction. The above-mentioned technical means can solve the problem in the prior art that voice control cannot be achieved in complex simulation software scenarios, thereby providing control efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0010] Figure 1It is a flowchart of a simulation software function calling method provided in an embodiment of the present application;
[0011] Figure 2 It is a flowchart of another simulation software function calling method provided in an embodiment of the present application;
[0012] Figure 3 It is a structural diagram of a simulation software function calling device provided in an embodiment of the present application;
[0013] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0014] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0015] A simulation software function calling method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.
[0016] Figure 1 It is a flowchart of a simulation software function calling method provided in an embodiment of the present application. Figure 1 The simulation software function calling method can be executed by a computer or a server, or by software on a computer or a server. Figure 1 As shown, the simulation software function calling method includes:
[0017] S101, determining multiple functions provided by each simulation software, and obtaining basic information and related information of each function;
[0018] S102, creating a calling interface and a calling instruction for each function based on basic information of the function;
[0019] S103, adding supplementary information to the calling instruction of each function based on the relevant information of the function;
[0020] S104, when a voice command issued by a user is detected, voice recognition is performed on the voice command to obtain a recognition result;
[0021] S105, determining a target calling instruction corresponding to the recognition result from the plurality of calling instructions based on each calling instruction and the auxiliary information of the calling instruction;
[0022] S106, implementing corresponding functions through the calling interface corresponding to the target calling instruction.
[0023] The basic information of each function includes the function name, function description and calling path, etc. The relevant information of each function includes the explanation of the technical terms involved in the function. Based on the basic information of each function, a calling interface is created for the function. The name of the calling interface is the function name of the function and carries the function description of the function. Based on the basic information of each function, a calling instruction is created for the function. The calling instruction calls the function according to the calling path of the function. The relevant information of each function is used as the auxiliary information of the calling instruction of the function. The voice command issued by the user is subjected to voice recognition to obtain a recognition result. The recognition result is compared with each calling instruction and its auxiliary information to determine the target calling instruction from multiple calling instructions, and the corresponding function is implemented through the calling interface of the function corresponding to the target calling instruction.
[0024] By using voice recognition to develop simulation software, users can switch between different simulation software through voice commands. This not only lowers the threshold for using simulation software, but also greatly reduces the time spent on operating multiple software. It is equivalent to an intelligent assistant that can understand your simulation requirements and can quickly and accurately use multiple simulation software for simulation. Artificial neural networks can also be added to repeatedly learn and upgrade voice recognition.
[0025] Due to the complexity of simulation tasks, users may need to control one simulation software at one time and another simulation software at another time. At this time, a voice recognition service is needed to be responsible for the simulation of all simulation software. Because each simulation software provides different functions, how to accurately recognize the user's voice and accurately control the functions of the corresponding simulation software is a technical difficulty. Take the simulation software ANSYS, ADS and Cadence in the field of electronic engineering and multi-physics field simulation as an example.
[0026] ANSYS (Analysis System) is a multi-physics simulation software package, mainly used for engineering simulation and analysis, providing the following functions: Structural mechanics analysis (function name): static, dynamic and nonlinear analysis to predict the response of materials and structures under various load conditions (function description); Fluid dynamics analysis: used to simulate the flow characteristics of gases and liquids, including turbulence, heat transfer, chemical reactions, etc.; Electromagnetic field analysis: used for high-frequency and low-frequency electromagnetic field simulation, covering antenna design, wireless communication, power equipment and other fields; Thermal analysis: used for heat dissipation and thermal management simulation, suitable for electronic equipment, mechanical systems, etc.; System-level simulation: system-level simulation of electrical, hydraulic, pneumatic, thermal and other systems; Multi-physics coupling: interdisciplinary coupling analysis, such as fluid-solid coupling, electrothermal coupling, etc.
[0027] ADS (Advanced Design System) is mainly used for the design and simulation of RF and microwave circuits, and provides the following functions: Circuit simulation (function name): provides time domain and frequency domain simulation for verification of RF and microwave circuit design (function description); Electromagnetic field simulation: through the integrated electromagnetic simulator, the performance of components such as antennas, transmission lines, and filters can be analyzed; System design: supports system-level RF and microwave circuit design, including signal chains, communication systems, etc.; Signal integrity analysis: used to evaluate signal quality in high-speed digital circuits, etc.
[0028] Cadence (Cadence Design Systems) provides a series of electronic design automation tools, mainly for the design of integrated circuits and printed circuit boards, providing the following functions: Integrated circuit design (function name): design and verification of analog and mixed-signal integrated circuits (function description); Printed circuit board design: a full set of tools from schematic capture, layout design to signal integrity and power integrity analysis; Package design: used for the design and analysis of system-level packages; Verification and testing for integrated circuit functional verification and debugging.
[0029] For example, the information related to the circuit simulation function provided by ADS includes: Insertion loss: Insertion loss refers to the degree of power reduction when a component (such as a filter, connector, coupler, etc.) is added to a transmission line or network. Insertion loss is usually measured in decibels (dB), which reflects the energy loss caused by the intervention of the device during the transmission process; Loss coefficient: The loss coefficient refers to the degree to which the signal energy in a material or system attenuates as the distance increases. It is usually used to describe the signal loss in cables, optical fibers or other transmission media. The loss coefficient is also called the attenuation coefficient, and its unit is usually decibels per kilometer (dB / km) or neper per meter (Np / m); Attenuation: Attenuation refers to the phenomenon that the intensity of a signal gradually decreases during propagation, which can be caused by a variety of factors, including absorption, scattering and reflection. In the transmission of electrical and optical signals, attenuation is inevitable, and it will increase with the increase of transmission distance. Attenuation affects the transmission quality of the signal, resulting in a decrease in the signal-to-noise ratio, thereby affecting the performance of the communication system.
[0030] According to the technical solution provided in the embodiment of the present application, multiple functions provided by each simulation software are determined, and basic information and related information of each function are obtained; based on the basic information of each function, a calling interface and a calling instruction are created for the function; based on the related information of each function, additional information is added to the calling instruction of the function; when a voice instruction issued by the user is detected, voice recognition is performed on the voice instruction to obtain a recognition result; based on each calling instruction and the additional information of the calling instruction, a target calling instruction corresponding to the recognition result is determined from multiple calling instructions; and the corresponding function is implemented through the calling interface corresponding to the target calling instruction. The above-mentioned technical means can solve the problem in the prior art that voice control cannot be implemented in complex simulation software scenarios, thereby improving control efficiency and accuracy.
[0031] Furthermore, based on each call instruction and the auxiliary information of the call instruction, a target call instruction corresponding to the recognition result is determined from multiple call instructions, including: calculating a first similarity between the recognition result and each call instruction; calculating a second similarity between the recognition result and the auxiliary information of each call instruction; weightedly summing the first similarity and the second similarity corresponding to each call instruction according to a preset weight to obtain a third similarity corresponding to each call instruction; and taking the call instruction with the highest third similarity as the target call instruction.
[0032] The voice commands issued by the user may contain technical terms related to the functions that need to be called. Therefore, in addition to calculating the first similarity between the recognition result and each calling instruction, the second similarity between the recognition result and the auxiliary information of the calling instruction is also calculated. The target calling instruction is obtained by comprehensively considering the first similarity and the second similarity.
[0033] Furthermore, after adding auxiliary information to the calling instruction of each function based on the relevant information of the function, the method also includes: generating a calling instruction library using the calling instructions of each function and the auxiliary information of the calling instruction; using the recognition result to compare with each calling instruction in the calling instruction library and the auxiliary information of the calling instruction to determine the target calling instruction corresponding to the recognition result.
[0034] The speech recognition service determines the target calling instruction corresponding to the recognition result by calling the instruction library.
[0035] Furthermore, voice recognition is performed on the voice command to obtain a recognition result, including: constructing a feature extraction network, and constructing a voice recognition model using the feature extraction network, a statistical network, and a probability network; inputting the voice command into the voice recognition model: extracting audio features of the voice command using the feature extraction network; matching corresponding phonemes for the audio features using the statistical network; and determining the recognition result based on the phonemes using the probability network.
[0036] The audio feature can be any commonly used audio feature, such as Mel frequency cepstral coefficients. The feature extraction network is an algorithm for extracting Mel frequency cepstral coefficients (the algorithm is already available). The statistical network can use a hidden Markov model to match sound features with phonemes. Phoneme is the smallest functional unit used to describe speech in linguistics, and multiple phonemes can determine a word. The language model can use the N-gram model, which is based on phonemes to predict the probability of the next word in the recognition result. It is based on the Markov assumption that the current item in the sequence only depends on the previous N-1 items, without considering earlier historical information.
[0037] Furthermore, after implementing the corresponding function through the calling interface corresponding to the target calling instruction, the method also includes: receiving user feedback information; determining the loss based on the feedback information; and optimizing the speech recognition model according to the loss.
[0038] If the feedback information indicates that the called function is wrong, it means that the recognition result is wrong. You can refer to reinforcement learning, determine the reward based on the feedback information, determine the loss based on the reward, and optimize the model parameters of the speech recognition model based on the loss. If the recognition result is wrong, the reward is negative and the loss is large. If the recognition result is correct, the reward is positive and the loss is small or no.
[0039] In some embodiments, multiple complex simulation tasks are established, wherein each complex simulation task is jointly simulated using multiple simulation software; a complex call instruction is generated according to each complex simulation task, wherein each complex call instruction contains multiple call instructions in a sequential order; the ancillary information of all call instructions contained in each complex call instruction is used as the ancillary information of the complex call instruction; based on each complex call instruction and the ancillary information of the complex call instruction, a target complex call instruction corresponding to the recognition result is determined from multiple complex call instructions; and a corresponding function is called through a call interface corresponding to the call instruction contained in the target complex call instruction to implement the complex simulation task corresponding to the target complex call instruction.
[0040] The following are some examples of common complex simulation tasks:
[0041] The first complex simulation task is used in the scenario of designing RF systems or microwave components: using the circuit simulation function of ADS to build RF circuits, including amplifiers, filters, mixers and other devices; after the circuit design is completed, the RF circuit is imported into ANSYS, and the electromagnetic field analysis function of ANSYS is used to evaluate the performance of the RF circuit under different electromagnetic fields.
[0042] The second complex simulation task is applied to integrated circuit design: using the integrated circuit design function provided by Cadence to design an integrated circuit. After completion, the integrated circuit can be exported to ANSYS, and the thermal analysis function provided by ANSYS can be used to evaluate the thermal distribution and cooling requirements of the integrated circuit; at the same time, the signal integrity function provided by ANSYS can be used to check the possible signal quality problems in the integrated circuit.
[0043] The third complex simulation task is applied to printed circuit board design: design a printed circuit board using the printed circuit board design function provided by Cadence. After completion, the printed circuit board can be imported into ANSYS, and the signal integrity analysis function provided by ANSYS can be used to check the signal quality problems that may exist in the printed circuit board.
[0044] Figure 2 It is a flowchart of another simulation software function calling method provided in an embodiment of the present application.
[0045] like Figure 2 As shown, the method includes:
[0046] Execute the following loop:
[0047] S201, determining whether i is greater than N, wherein i is the sequence number of the call instruction in the target complex call instruction, and N is the number of the call instructions in the target complex call instruction;
[0048] S202, when i is greater than N, it is determined that the complex simulation task corresponding to the target complex call instruction is completed, and the loop ends;
[0049] S203, when i is not greater than N, calling a corresponding function through a calling interface corresponding to the i-th calling instruction in the target complex calling instruction;
[0050] S204, update i with the value of i+1.
[0051] Executing the target complex call instruction is to execute each call instruction in the target complex call instruction in order until all the call instructions in the target complex call instruction are executed.
[0052] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.
[0053] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.
[0054] Figure 3 Schematic diagram of a simulation software function calling device provided in an embodiment of the present application. Figure 3As shown, the simulation software function calling device includes:
[0055] The acquisition module 301 is configured to determine multiple functions provided by each simulation software and acquire basic information and related information of each function;
[0056] A creation module 302 is configured to create a calling interface and a calling instruction for each function based on basic information of the function;
[0057] An adding module 303 is configured to add auxiliary information to the calling instruction of each function based on the relevant information of the function;
[0058] The recognition module 304 is configured to perform voice recognition on the voice command when a voice command issued by the user is detected to obtain a recognition result;
[0059] The determination module 305 is configured to determine the target call instruction corresponding to the recognition result from the plurality of call instructions based on each call instruction and the auxiliary information of the call instruction;
[0060] The calling module 306 is configured to implement corresponding functions through the calling interface corresponding to the target calling instruction.
[0061] According to the technical solution provided in the embodiment of the present application, multiple functions provided by each simulation software are determined, and basic information and related information of each function are obtained; based on the basic information of each function, a calling interface and a calling instruction are created for the function; based on the related information of each function, additional information is added to the calling instruction of the function; when a voice instruction issued by the user is detected, voice recognition is performed on the voice instruction to obtain a recognition result; based on each calling instruction and the additional information of the calling instruction, a target calling instruction corresponding to the recognition result is determined from multiple calling instructions; and the corresponding function is implemented through the calling interface corresponding to the target calling instruction. The above-mentioned technical means can solve the problem in the prior art that voice control cannot be implemented in complex simulation software scenarios, thereby improving control efficiency and accuracy.
[0062] In some embodiments, the determination module 305 is also configured to calculate a first similarity between the recognition result and each call instruction; calculate a second similarity between the recognition result and the auxiliary information of each call instruction; weightedly sum the first similarity and the second similarity corresponding to each call instruction according to a preset weight to obtain a third similarity corresponding to each call instruction; and use the call instruction with the highest third similarity as the target call instruction.
[0063] The voice commands issued by the user may contain technical terms related to the functions that need to be called. Therefore, in addition to calculating the first similarity between the recognition result and each calling instruction, the second similarity between the recognition result and the auxiliary information of the calling instruction is also calculated. The target calling instruction is obtained by comprehensively considering the first similarity and the second similarity.
[0064] In some embodiments, the determination module 305 is also configured to generate a call instruction library using the call instructions of each function and the auxiliary information of the call instruction; and compare the recognition result with each call instruction in the call instruction library and the auxiliary information of the call instruction to determine the target call instruction corresponding to the recognition result.
[0065] The speech recognition service determines the target calling instruction corresponding to the recognition result by calling the instruction library.
[0066] In some embodiments, the recognition module 304 is also configured to construct a feature extraction network, and construct a speech recognition model using the feature extraction network, the statistical network and the probabilistic network; input the voice command into the speech recognition model: extract the audio features of the voice command using the feature extraction network; match the corresponding phonemes for the audio features using the statistical network; and determine the recognition result based on the phonemes using the probabilistic network.
[0067] The audio feature can be any commonly used audio feature, such as Mel frequency cepstral coefficients. The feature extraction network is an algorithm for extracting Mel frequency cepstral coefficients (the algorithm is already available). The statistical network can use a hidden Markov model to match sound features with phonemes. Phoneme is the smallest functional unit used to describe speech in linguistics, and multiple phonemes can determine a word. The language model can use the N-gram model, which is based on phonemes to predict the probability of the next word in the recognition result. It is based on the Markov assumption that the current item in the sequence only depends on the previous N-1 items, without considering earlier historical information.
[0068] In some embodiments, the recognition module 304 is further configured to receive feedback information from the user; determine the loss based on the feedback information; and optimize the speech recognition model according to the loss.
[0069] If the feedback information indicates that the called function is wrong, it means that the recognition result is wrong. You can refer to reinforcement learning, determine the reward based on the feedback information, determine the loss based on the reward, and optimize the model parameters of the speech recognition model based on the loss. If the recognition result is wrong, the reward is negative and the loss is large. If the recognition result is correct, the reward is positive and the loss is small or no.
[0070] In some embodiments, the calling module 306 is also configured to establish multiple complex simulation tasks, wherein each complex simulation task is jointly simulated using multiple simulation software; generate a complex calling instruction according to each complex simulation task, wherein each complex calling instruction contains multiple calling instructions in a sequence; use the auxiliary information of all calling instructions contained in each complex calling instruction as the auxiliary information of the complex calling instruction; based on each complex calling instruction and the auxiliary information of the complex calling instruction, determine the target complex calling instruction corresponding to the identification result from multiple complex calling instructions; call the corresponding function through the calling interface corresponding to the calling instruction contained in the target complex calling instruction to implement the complex simulation task corresponding to the target complex calling instruction.
[0071] The following are some examples of common complex simulation tasks:
[0072] The first complex simulation task is used in the scenario of designing RF systems or microwave components: using the circuit simulation function of ADS to build RF circuits, including amplifiers, filters, mixers and other devices; after the circuit design is completed, the RF circuit is imported into ANSYS, and the electromagnetic field analysis function of ANSYS is used to evaluate the performance of the RF circuit under different electromagnetic fields.
[0073] The second complex simulation task is applied to integrated circuit design: using the integrated circuit design function provided by Cadence to design an integrated circuit. After completion, the integrated circuit can be exported to ANSYS, and the thermal analysis function provided by ANSYS can be used to evaluate the thermal distribution and cooling requirements of the integrated circuit; at the same time, the signal integrity function provided by ANSYS can be used to check the possible signal quality problems in the integrated circuit.
[0074] The third complex simulation task is applied to printed circuit board design: design a printed circuit board using the printed circuit board design function provided by Cadence. After completion, the printed circuit board can be imported into ANSYS, and the signal integrity analysis function provided by ANSYS can be used to check the signal quality problems that may exist in the printed circuit board.
[0075] In some embodiments, the calling module 306 is also configured to execute the following loop: determine whether i is greater than N, where i is the sequence number of the calling instruction in the target complex calling instruction, and N is the number of calling instructions in the target complex calling instruction; when i is greater than N, determine that the complex simulation task corresponding to the target complex calling instruction is completed and end the loop; when i is not greater than N, call the corresponding function through the calling interface corresponding to the i-th calling instruction in the target complex calling instruction; update i with the value of i+1.
[0076] Executing the target complex call instruction is to execute each call instruction in the target complex call instruction in order until all the call instructions in the target complex call instruction are executed.
[0077] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0078] Figure 4 Schematic diagram of an electronic device 4 provided in an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.
[0079] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 The electronic device 4 is merely an example and does not limit the electronic device 4 , and may include more or less components than those shown in the figure, or different components.
[0080] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0081] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.
[0082] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
[0083] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0084] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical feature diagrams therein. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for calling a simulation software function, characterized in that: include: Identify the multiple functions provided by each simulation software and obtain basic and related information of each function; Create a calling interface and a calling instruction for each function based on the basic information of the function; Add additional information to the calling instruction of each function based on the relevant information of the function; When a voice command issued by a user is detected, voice recognition is performed on the voice command to obtain a recognition result; Based on each calling instruction and the auxiliary information of the calling instruction, determining a target calling instruction corresponding to the recognition result from the plurality of calling instructions; The corresponding function is realized through the calling interface corresponding to the target calling instruction.
2. The method according to claim 1, characterized in that Based on each calling instruction and the auxiliary information of the calling instruction, determining a target calling instruction corresponding to the recognition result from the multiple calling instructions includes: Calculating a first similarity between the recognition result and each calling instruction; Calculating a second similarity between the recognition result and the attached information of each calling instruction; The first similarity and the second similarity corresponding to each calling instruction are weighted and summed according to a preset weight to obtain a third similarity corresponding to each calling instruction; The call instruction with the third highest similarity is used as the target call instruction.
3. The method according to claim 1, characterized in that: After adding auxiliary information to the calling instruction of each function based on the relevant information of the function, the method further includes: Generate a call instruction library using the call instructions of each function and the auxiliary information of the call instructions; The recognition result is compared with each calling instruction in the calling instruction library and the auxiliary information of the calling instruction to determine the target calling instruction corresponding to the recognition result.
4. The method according to claim 1, characterized in that Performing voice recognition on the voice command to obtain a recognition result includes: Constructing a feature extraction network, and constructing a speech recognition model using the feature extraction network, the statistical network and the probability network; Input the voice command into the voice recognition model: Extracting audio features of the voice command using the feature extraction network; Matching corresponding phonemes for the audio features using the statistical network; Based on the phonemes, the recognition result is determined using the probabilistic network.
5. The method according to claim 4, characterized in that After implementing the corresponding function through the calling interface corresponding to the target calling instruction, the method further includes: Receive feedback from users; determining a loss based on the feedback information; The speech recognition model is optimized according to the loss.
6. The method according to claim 1, characterized in that The method further comprises: Establish multiple complex simulation tasks, wherein each complex simulation task is jointly simulated using multiple simulation software; Generate a complex call instruction according to each complex simulation task, wherein each complex call instruction includes multiple call instructions in a sequential order; Using the subsidiary information of all the call instructions contained in each complex call instruction as the subsidiary information of the complex call instruction; Based on each complex call instruction and the auxiliary information of the complex call instruction, determining a target complex call instruction corresponding to the recognition result from a plurality of complex call instructions; The corresponding function is called through the calling interface corresponding to the calling instruction contained in the target complex calling instruction to realize the complex simulation task corresponding to the target complex calling instruction.
7. The method according to claim 6, characterized in that Calling a corresponding function through a calling interface corresponding to the target complex calling instruction includes: Execute the following loop: Determine whether i is greater than N, where i is the sequence number of the call instruction in the target complex call instruction, and N is the number of the call instructions in the target complex call instruction; When i is greater than N, it is determined that the complex simulation task corresponding to the target complex call instruction is completed, and the loop ends; When i is not greater than N, calling the corresponding function through the calling interface corresponding to the i-th calling instruction in the target complex calling instruction; Update i with the value of i+1.
8. A simulation software function calling device, characterized in that: include: an acquisition module, configured to determine a plurality of functions provided by each simulation software, and to acquire basic information and related information of each function; A creation module is configured to create a calling interface and a calling instruction for each function based on basic information of the function; An adding module is configured to add auxiliary information to a calling instruction of each function based on relevant information of the function; The recognition module is configured to perform voice recognition on the voice command issued by the user when the voice command issued by the user is detected to obtain a recognition result; A determination module is configured to determine a target calling instruction corresponding to the recognition result from a plurality of calling instructions based on each calling instruction and the auxiliary information of the calling instruction; The calling module is configured to implement corresponding functions through the calling interface corresponding to the target calling instruction.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Voice control method and apparatus for application program
CN105183422A
Configurable voice control operational software and voice feedback method and system
CN107015780A
Voice control method and device for application program, storage medium and program product
CN118351850A
Customizable embedded vocal command sets for a lighting and / or other environmental controller
US20200104094A1
Speech control method and apparatus, electronic device, and storage medium
WO2023093280A1
