Development method and device of intelligent software with body and medium

Abstract

The invention provides a development method of intelligent software, which is applied to an intelligent project software development platform, the software development platform is provided with an intelligent project template based on a dora-rs framework, and the method comprises the following steps: obtaining a configuration script file of a to-be-developed project; based on a dora-rs framework, establishing a function module corresponding to the configuration script file in the software development platform; according to the business logic configuration information item in the configuration script file, setting the business logic module to be loaded and called by the corresponding function module; and according to the configuration information of the data operation module and the external resource configuration information in the configuration script file, setting the data operation module and the external resource item corresponding to the function module. The invention further discloses a development device of the intelligent software with the body and a computer readable storage medium.

Description

Technical Field

[0001] The present invention relates to the field of software technology, and in particular to a method and device for developing embodied intelligent software and a computer-readable storage medium. Background Art

[0002] With the continuous progress of large model technology and the significant enhancement of the capabilities of small language models (SLMs), the field of embodied intelligence is gradually becoming a very attractive track in the current field of artificial intelligence. Globally, many technology giants are actively deploying in this field to promote the development and application of embodied intelligence technology, and have launched embodied intelligence application products based on SLMs. A number of embodied intelligence startups have also emerged in China. In the field of embodied intelligence, the initial landing value has been obtained through the capabilities of large models, and with the continuous development of robot hardware and systems, embodied intelligence will have unlimited application potential and development prospects.

[0003] Defects and deficiencies of existing technologies: Currently, most embodied intelligence projects are closed source, and there is no embodied intelligence platform to provide support for open source in this field. Since embodied intelligence involves a large number of underlying operations of robot hardware, it is very difficult and complicated to directly implement and implement the project, and there is a high learning cost. In addition, the mainstream companies in the industry that develop embodied intelligent robots mainly focus on general robots. Facing the market demand for robots with private specific scene applications, they seem to be out of reach, which is also the main disadvantage of closed source. As a result, the development of embodied intelligence landing projects is very slow, and they are far behind the large model technology. It is difficult to make full use of the rapidly developing large model technology, which limits the development and dissemination of embodied intelligence technology. It can be seen from the development experience of large models that although closed source has brought certain profits to this field, the rapid development of large models still relies on the open source model. Therefore, for the field of embodied intelligence, there is an urgent need for an open source platform to do the corresponding promotion work. Summary of the invention

[0004] The present invention provides a method, device and computer-readable storage medium for developing embodied intelligent software, which are used to solve the problem in the prior art that the embodied intelligent software development process can be integrated with an open source platform, improve development efficiency and lower the development threshold.

[0005] In a first aspect, the present invention provides a method for developing embodied intelligent software, which is applied to an embodied intelligent project software development platform, wherein the software development platform is provided with an embodied intelligent project template based on a dora-rs framework, and the method comprises: obtaining a configuration script file of a project to be developed, wherein the configuration script file at least comprises: basic data configuration information, business logic configuration information, and a set of selectable software systems {S1, S2, S3...S n} and the target software system S0 of the project to be developed to be generated, n represents the number of software systems in the selectable software system set; based on the dora-rs framework, a functional module corresponding to the configuration script file is established in the software development platform; wherein the functional module includes an underlying operating environment module, a large model data interaction sample module, a business logic module and a data operation module; according to the business logic configuration information item in the configuration script file, the business logic module to be loaded and called by the corresponding functional module is set; according to the configuration information of the data operation module and the external resource configuration information in the configuration script file, the data operation module and the external resource item corresponding to the functional module are set.

[0006] In some embodiments, obtaining the configuration script file of the project to be developed includes: obtaining the configuration script file from the code library resources of the control system in the open source community; or, collecting the configuration script file from the open source community webpage by using a web crawler or an open API tool.

[0007] In some embodiments, a functional module corresponding to the configuration script file is established in the software development platform, including: determining corresponding functional module parameters according to the configuration script file; reading the functional module object of the project to be developed according to the functional module parameters, and associating the functional module object with the corresponding business logic module.

[0008] In some embodiments, according to the configuration information of the data operation module and the external resource configuration information in the configuration script file, the data operation module and the external resource item corresponding to the functional module are set, including: according to the configuration script file, generating a directory file that is compatible with the business scenario of the project to be developed, wherein the directory file includes: a natural language recognition folder and a sample code folder.

[0009] In some embodiments, it also includes: collecting configuration data from the configuration script file and the optional software system of the open source community, and organizing them into a configuration data set; adapting the configuration data according to the similarity between the configuration data in the configuration data set and the configuration data of the target software system S0 of the project to be developed, to obtain a fine-tuning data set, and using the fine-tuning data set to fine-tune the large model.

[0010] In some embodiments, the sample code folder includes: a configuration text example, wherein the configuration text example is used to generate a large model data interaction sample.

[0011] In some embodiments, using the fine-tuning dataset to fine-tune the large model includes: calculating the similarity between the configuration data in the fine-tuning dataset and the configuration data of the target software system S0 of the project to be developed, and determining to add the configuration data to the fine-tuning dataset when the similarity meets a predetermined threshold.

[0012] In some embodiments, the external resource items include a model compression tool and a model fusion tool.

[0013] In a second aspect, the present invention provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the above-mentioned method for developing embodied intelligent software is implemented.

[0014] In a third aspect, the present invention further provides a computer-readable storage medium, characterized in that program code is stored in the computer-readable storage medium, and the program code can be called by a processor to execute the above-mentioned method for developing embodied intelligent software.

[0015] Compared with the prior art, the present invention can achieve at least one of the following beneficial effects:

[0016] First, the present invention can promote the open source sharing of embodied intelligence technology, allowing more technology enthusiasts to access it and use their imagination to develop their own embodied intelligence projects, thereby promoting the rapid development of embodied intelligence implementation projects.

[0017] Second, it provides maintenance and updates of templates, tools, models, technical documents, etc. for embodied intelligence projects, lowering the threshold for the development of embodied intelligence projects.

[0018] Third, it provides analysis of different application scenarios and automatically recommends the most suitable large model and its configuration plan based on the user-specified embodied intelligent project requirements and scenario characteristics, which is convenient and fast.

[0019] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the disclosure, nor is it intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present disclosure will become more apparent through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present disclosure.

[0021] Figure 1 A flow chart of a method for developing embodied intelligent software provided by an embodiment of the present invention is shown;

[0022] Figure 2 is a schematic block diagram of a device for developing embodied intelligent software provided by an embodiment of the present invention;

[0023] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0025] As used herein, the term "including" and its variations mean open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0026] This application provides a method for developing embodied intelligent software. Figure 1 , which is a schematic diagram of the first embodiment of the present application. Figure 1 A method for developing embodied intelligent software is described in detail in the first embodiment of the present application.

[0027] The present invention provides a method 100 for developing embodied intelligent software, which is applied to an embodied intelligent project software development platform, wherein the software development platform is provided with an embodied intelligent project template based on a dora-rs framework. The processing flow of the method 100 may include the following steps:

[0028] Step S102: Obtain the configuration script file of the project to be developed, that is, obtain the configuration script file of the project to be developed, wherein the configuration script file at least includes: basic data configuration information, business logic configuration information, and a set of selectable software systems {S1, S2, S3...Sn} of the open source community that are compatible with the business scenario of the project to be developed and the target software system S0 of the project to be developed to be generated, n represents the number of software systems in the set of selectable software systems. In this embodiment, the scheme can promote the open source sharing of embodied intelligence technology, so that more technology enthusiasts can access it, and give full play to their imagination to develop their own embodied intelligence projects, and promote the rapid development of embodied intelligence landing projects; moreover, it provides analysis of different application scenarios, and automatically recommends the most suitable large model and its configuration scheme according to the embodied intelligence project requirements and scenario characteristics specified by the user, which is convenient and fast.

[0029] In some embodiments, obtaining the configuration script file of the project to be developed includes: obtaining the configuration script file from the code library resources of the control system in the open source community; or, collecting the configuration script file from the open source community webpage by using a web crawler or an open API tool.

[0030] Step S104: Establish a functional module corresponding to the configuration script file, that is, based on the dora-rs framework, establish a functional module corresponding to the configuration script file in the software development platform; wherein the functional module includes an underlying operating environment module, a large model data interaction sample module, a business logic module, and a data operation module. This method provides maintenance and updates of templates, tools, models, technical documents, etc. for embodied intelligence projects, and reduces the threshold for the development of embodied intelligence landing projects.

[0031] In some embodiments, a functional module corresponding to the configuration script file is established in the software development platform, including: determining corresponding functional module parameters according to the configuration script file; reading the functional module object of the project to be developed according to the functional module parameters, and associating the functional module object with the corresponding business logic module.

[0032] Step S106: Setting the business logic module, that is, setting the business logic module to be loaded and called by the corresponding functional module according to the business logic configuration information item in the configuration script file.

[0033] Step S108: Setting the data operation module and the external resource item, that is, setting the data operation module and the external resource item corresponding to the functional module according to the configuration information of the data operation module and the external resource configuration information in the configuration script file.

[0034] In some embodiments, according to the configuration information of the data operation module and the external resource configuration information in the configuration script file, the data operation module and the external resource item corresponding to the functional module are set, including: according to the configuration script file, generating a directory file that is compatible with the business scenario of the project to be developed, wherein the directory file includes: a natural language recognition folder and a sample code folder.

[0035] In some embodiments, it also includes: collecting configuration data from the configuration script file and the optional software system of the open source community, and organizing them into a configuration data set; adapting the configuration data according to the similarity between the configuration data in the configuration data set and the configuration data of the target software system S0 of the project to be developed, to obtain a fine-tuning data set, and using the fine-tuning data set to fine-tune the large model.

[0036] In some embodiments, the sample code folder includes: a configuration text example, wherein the configuration text example is used to generate a large model data interaction sample.

[0037] In some embodiments, using the fine-tuning dataset to fine-tune the large model includes: calculating the similarity between the configuration data in the fine-tuning dataset and the configuration data of the target software system S0 of the project to be developed, and determining to add the configuration data to the fine-tuning dataset when the similarity meets a predetermined threshold.

[0038] In some embodiments, the external resource items include a model compression tool and a model fusion tool.

[0039] Figure 2 2 is a schematic block diagram of an embodied intelligent software development device 200 according to an exemplary embodiment. The embodied intelligent software development device 200 includes: an acquisition module 202, a construction function module 204, a first configuration module 206 and a second configuration module 208, wherein:

[0040] The acquisition module 202 acquires a configuration script file of the project to be developed, wherein the configuration script file at least includes: basic data configuration information, business logic configuration information, and a set of selectable software systems {S1, S2, S3...Sn} of the open source community that are compatible with the business scenario of the project to be developed and a target software system S0 of the project to be developed to be generated, where n represents the number of software systems in the set of selectable software systems;

[0041] Constructing a functional module 204, based on the dora-rs framework, establishing a functional module corresponding to the configuration script file in the software development platform; wherein the functional module includes an underlying operating environment module, a large model data interaction sample module, a business logic module and a data operation module;

[0042] A first configuration module 206, which sets the business logic module to be loaded and called by the corresponding function module according to the business logic configuration information item in the configuration script file;

[0043] The second configuration module 208 sets the data operation module and the external resource item corresponding to the functional module according to the configuration information of the data operation module and the external resource configuration information in the configuration script file.

[0044] In some embodiments, the acquisition module 202 can acquire the configuration script file of the project to be developed, including: acquiring the configuration script file from the code library resources of the control system in the open source community; or collecting from the open source community webpage by using a web crawler or an open API tool.

[0045] In some embodiments, the construction function module 204 can establish a function module corresponding to the configuration script file in the software development platform, including: determining the corresponding function module parameters according to the configuration script file; reading the function module object of the project to be developed according to the function module parameters, and associating the function module object with the corresponding business logic module.

[0046] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device 300 may include a processor 3001 and a memory 3002. Optionally, the electronic device 300 may further include a transceiver 3003. The processor 3001, the memory 3002 and the transceiver 3003 may be connected, for example, via a communication bus. The memory 3002 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 3001, the steps of the method for developing embodied intelligent software as described above are implemented.

[0047] In a specific implementation, as an embodiment, the processor 3001 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 are shown in FIG.

[0048] In a specific implementation, as an embodiment, the electronic device 300 may also include multiple processors, such as Figure 3 3001 and processor 3004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0049] The memory 3002 is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor 3001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0050] The transceiver 3003 is used to communicate with a network device or a terminal device.

[0051] Optionally, the transceiver 3003 may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0052] Optionally, the transceiver 3003 may be integrated with the processor 3001 , or may exist independently and be coupled to the processor 3001 via an interface circuit of the electronic device 300 , which is not specifically limited in the embodiment of the present invention.

[0053] It should be noted that Figure 3 The structure of the electronic device 300 shown in the figure does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In addition, the technical effects of the electronic device 300 can refer to the technical effects of the above-mentioned method embodiment, which will not be repeated here.

[0054] In an exemplary embodiment, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the steps of the above-mentioned simulation method for simulating the combined injury of a human body by a shock wave and fragments. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0055] An embodiment of the present invention further provides an electronic device, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the above-mentioned method for developing embodied intelligent software is implemented.

[0056] An embodiment of the present invention provides a computer-readable storage medium, characterized in that program code is stored in the computer-readable storage medium, and the program code can be called by a processor to execute the above-mentioned method for developing embodied intelligent software.

[0057] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0058] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0059] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0060] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0061] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes 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 invention.

[0062] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0063] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0064] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0065] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0067] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0068] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for developing embodied intelligent software, characterized in that: Applied to an embodied intelligence project software development platform, the software development platform is provided with an embodied intelligence project template based on the dora-rs framework, the method comprises: Obtain a configuration script file for the project to be developed, wherein the configuration script file at least includes: basic data configuration information, business logic configuration information, and a selectable software system set {S1, S2, S3...S n } and the target software system S0 of the project to be developed to be generated, n represents the number of software systems in the selectable software system set; Based on the dora-rs framework, a functional module corresponding to the configuration script file is established in the software development platform; wherein the functional module includes an underlying operating environment module, a large model data interaction sample module, a business logic module and a data operation module; According to the business logic configuration information item in the configuration script file, the business logic module to be loaded and called by the corresponding functional module is set; According to the configuration information of the data operation module and the external resource configuration information in the configuration script file, the data operation module and the external resource item corresponding to the functional module are set.

2. The method for developing embodied intelligent software according to claim 1, characterized in that: Get the configuration script file of the project to be developed, including: Get the configuration script file from the code library of this control system in the open source community; or, The data is collected from open source community web pages by using web crawlers and open API tools.

3. The method for developing embodied intelligent software according to claim 1, characterized in that: Establishing a functional module corresponding to the configuration script file in the software development platform includes: Determine corresponding function module parameters according to the configuration script file; According to the function module parameters, the function module object of the project to be developed is read, and the function module object is associated with the corresponding business logic module.

4. The method for developing embodied intelligent software according to claim 1, characterized in that: According to the configuration information of the data operation module and the external resource configuration information in the configuration script file, the data operation module and the external resource item corresponding to the functional module are set, including: According to the configuration script file, a directory file adapted to the business scenario of the project to be developed is generated, wherein the directory file includes: a natural language recognition folder and a sample code folder.

5. The method for developing embodied intelligent software according to claim 1, characterized in that: Also includes: Collecting configuration data from the configuration script file and the selectable software system of the open source community, and arranging them into a configuration data set; The configuration data is adapted according to the similarity between the configuration data in the configuration data set and the configuration data of the target software system S0 of the project to be developed, so as to obtain a fine-tuning data set, and the large model is fine-tuned using the fine-tuning data set.

6. The method for developing embodied intelligent software according to claim 4, characterized in that: The sample code folder includes: a configuration text example, and the configuration text example is used to generate a large model data interaction sample.

7. The method for developing embodied intelligent software according to claim 5, characterized in that: Use this fine-tuning dataset to fine-tune the large model, including: The similarity between the configuration data in the fine-tuning data set and the configuration data of the target software system S0 of the project to be developed is calculated, and when the similarity meets a predetermined threshold, it is determined to add the configuration data to the fine-tuning data set.

8. The method for developing embodied intelligent software according to any one of claims 1 to 7, characterized in that: External resource items include model compression tools and model fusion tools.

9. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for developing embodied intelligent software as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, and the program code can be called by a processor to execute the method for developing embodied intelligent software as described in any one of claims 1 to 7.

Images