Method and apparatus for recommending application suite, and electronic device and storage medium

Abstract

Disclosed in the embodiments of the present invention are a method and apparatus for recommending an application suite, and an electronic device and a storage medium. The method comprises: receiving demand information of a digital system; inputting the demand information into a recommendation unit that is adapted to recommending an application suite, wherein the recommendation unit is determined on the basis of historical demand information and label information of each application in a historical application suite, and the historical application suite is associated with the historical demand information; and providing the application suite recommended by the recommendation unit. By using a recommendation unit determined on the basis of historical demand information and a historical application suite, an application suite is automatically recommended, thereby reducing dependence on human experts, cutting down costs, and improving the recommendation efficiency.

Description

Method, device, electronic device and storage medium for recommending application suite Technical Field

[0001] The present invention relates to the field of digital technology, and in particular to a method, device, electronic device and storage medium for recommending an application suite. Background Art

[0002] In a modular digital system based on microservices, users can freely select various applications (apps) and customize the workflows between them to create their own customized digital systems. An application suite integrates the functionality of multiple applications and other components. Application platforms offer a large number of applications, and their dependencies, interface compatibility, and functional complementarity are complex. Selecting the right applications to build an application suite is often time-consuming.

[0003] Gathering user requirements through face-to-face interviews and on-site surveys, combined with production experts' understanding of business processes and system architects' assessment of interface and system integration feasibility, can help users select the appropriate application suite. However, this approach has many limitations. For example, human experience is limited to the number of applications that can be processed, making it impossible to fully utilize the entire ecosystem.

[0004] Summary of the Invention

[0005] The embodiments of the present invention provide a method, device, electronic device, and storage medium for recommending an application suite.

[0006] A method for recommending an application suite, comprising:

[0007] Receive demand information from digital systems;

[0008] inputting the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in a historical application suite, wherein the historical application suite is associated with the historical demand information;

[0009] An application suite recommended by the recommendation unit is provided.

[0010] Therefore, by utilizing the recommendation units determined based on historical demand information and historical application suites, the application suites can be automatically recommended, thereby reducing dependence on human experts, lowering costs, and improving recommendation efficiency.

[0011] In one embodiment, it includes:

[0012] Establishing a mapping table based on a mapping relationship between keywords in the historical demand information and tag information of each application in the historical application suite;

[0013] The mapping table is stored in the recommendation unit, wherein the recommendation unit is adapted to determine tag information matching the keywords in the requirement information based on querying the mapping table, and determine the recommended application suite based on the matching tag information.

[0014] Therefore, the application suite can be quickly determined based on the query mapping table, thereby improving the recommendation speed.

[0015] In one embodiment, it includes:

[0016] Determining a training sample, where the training sample includes the historical demand information, wherein a training label of the training sample is label information of each application in the historical application suite;

[0017] Inputting the training sample into a neural network model to receive label information of a prediction application from the neural network model;

[0018] Determining a loss function value based on a difference between the label information of the prediction application and the training label;

[0019] The model parameters of the neural network model are configured so that the loss function value is lower than a preset threshold.

[0020] It can be seen that the application suite can be determined based on artificial intelligence, which improves the accuracy of recommendations.

[0021] In one embodiment, the requirement information includes at least one of the following:

[0022] System functional requirements that conform to the standard vocabulary for the functional division of digital systems;

[0023] The digital state of digital systems;

[0024] Hardware configuration information of the digital system;

[0025] Engineering scope of digital systems.

[0026] Therefore, demand information is diverse and standardized, which can achieve standardized recommendations and improve recommendation efficiency.

[0027] In one embodiment, the tag information includes at least one of the following:

[0028] The unique identifier of the application;

[0029] Description of the application's capabilities.

[0030] Therefore, the tag information can not only represent the unique identifier of the application, but also represent the capabilities of the application.

[0031] In one embodiment, before providing the application suite recommended by the recommendation unit, the method further includes:

[0032] parsing application dependencies of the recommended application suite;

[0033] Based on the application dependency, obtaining the applications that the recommended application suite depends on;

[0034] The dependent applications are included in the recommended application suite.

[0035] It can be seen that based on the analysis of application dependencies, the dependent applications can be automatically included in the application suite, and users no longer need to find the dependent applications themselves, which is convenient for users to use.

[0036] A device for recommending an application kit, comprising:

[0037] A receiving module, used for receiving demand information of a digital system;

[0038] an input module configured to input the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in a historical application suite associated with the historical demand information;

[0039] A module is provided, configured to provide the application suite recommended by the recommendation unit.

[0040] Therefore, by utilizing the recommendation units determined based on historical demand information and historical application suites, the application suites can be automatically recommended, thereby reducing dependence on human experts, lowering costs, and improving recommendation efficiency.

[0041] In one embodiment, it includes:

[0042] A mapping module is used to establish a mapping table based on the mapping relationship between the keywords in the historical demand information and the tag information of each application in the historical application suite; store the mapping table in the recommendation unit, wherein the recommendation unit is adapted to determine the tag information that matches the keywords in the demand information based on querying the mapping table, and determine the recommended application suite based on the matching tag information.

[0043] Therefore, the application suite can be quickly determined based on the query mapping table, thereby improving the recommendation speed.

[0044] In one embodiment, it includes:

[0045] A training module is used to determine a training sample, wherein the training sample includes the historical demand information, wherein the training label of the training sample is the label information of each application in the historical application suite; input the training sample into a neural network model to receive label information of the predicted application from the neural network model; determine a loss function value based on the difference between the label information of the predicted application and the training label; and configure model parameters of the neural network model so that the loss function value is lower than a preset threshold.

[0046] It can be seen that the application suite can be determined based on artificial intelligence, which improves the accuracy of recommendations.

[0047] In one embodiment, the providing module is used to, before providing the application suite recommended by the recommendation unit: parse the application dependencies of the recommended application suite; based on the application dependencies, obtain the applications on which the recommended application suite depends; and include the dependent applications in the recommended application suite.

[0048] Therefore, demand information is diverse and standardized, which can achieve standardized recommendations and improve recommendation efficiency.

[0049] An electronic device, comprising:

[0050] processor;

[0051] a memory for storing executable instructions of the processor;

[0052] The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method for recommending an application suite as described in any one of the above items.

[0053] A computer-readable storage medium stores computer instructions thereon, wherein when the computer instructions are executed by a processor, the method for recommending an application suite as described in any one of the above items is implemented.

[0054] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the method for recommending an application suite as described in any one of the above items is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, so that those skilled in the art will understand the above and other features and advantages of the present invention more clearly. In the accompanying drawings:

[0056] FIG1 is an exemplary flow chart of a method for recommending an application suite according to an embodiment of the present invention.

[0057] FIG2 is an exemplary schematic diagram of an expert manual recommendation application suite.

[0058] FIG3 is a first exemplary schematic diagram of automatically recommending an application suite based on expert knowledge according to an embodiment of the present invention.

[0059] FIG4 is a second exemplary schematic diagram of automatically recommending an application suite based on expert knowledge according to an embodiment of the present invention.

[0060] FIG. 5 is an exemplary diagram of a standardized functional division of a digital system.

[0061] FIG6 is an exemplary structural diagram of a device for recommending an application suite according to an embodiment of the present invention.

[0062] FIG. 7 is an exemplary structural diagram of an electronic device according to an embodiment of the present invention.

[0063] The accompanying drawings are numerals as follows: DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail with reference to the following examples.

[0065] For the sake of brevity and intuitiveness in description, the solution of the present invention is explained below by describing several representative implementation methods. A large number of details in the implementation methods are only used to help understand the solution of the present invention. However, it is obvious that the technical solution of the present invention may not be limited to these details when it is implemented. In order to avoid unnecessarily obscuring the solution of the present invention, some implementation methods are not described in detail, but only a framework is given. In the following, "including" means "including but not limited to", and "according to..." means "at least according to..., but not limited to only according to...". Due to the language habits of Chinese, when the number of a component is not specifically specified below, it means that the component can be one or more, or can be understood as at least one.

[0066] In the embodiment of the present invention, a recommendation unit is pre-established based on expert knowledge, and then the application suite can be automatically recommended using the recommendation unit without relying on experts.

[0067] FIG1 is an exemplary flow chart of a method for recommending an application suite according to an embodiment of the present invention. As shown in FIG1 , the method includes:

[0068] Step 101: Receive demand information of a digital system.

[0069] A digital system converts traditional manual operations into digital, automated ones, improving efficiency and accuracy. It also records and processes data in real time. Digital systems utilize computers and related software to digitize data. Through data storage, transmission, analysis, and processing, they automate business processes, improving efficiency and reducing costs.

[0070] Digital systems include various systems and software based on digital technology. For example:

[0071] (1) Digital office systems: such as email, collaborative office software, online document management systems, etc., can help enterprises realize information-based office and improve work efficiency and communication efficiency.

[0072] (2) Digital marketing systems: such as e-commerce platforms, digital advertising platforms, social media marketing tools, etc., can help companies achieve online sales and promotions, and increase market coverage and sales.

[0073] (3) Digital production systems: such as digital production lines, intelligent logistics management systems, quality control systems, etc., can help enterprises realize production automation and management optimization, and improve production efficiency and quality levels.

[0074] (4) Digital customer service systems: such as online customer service systems, intelligent customer service robots, customer relationship management systems, etc., can help companies realize the digitalization and intelligence of customer service and improve customer satisfaction and loyalty.

[0075] Typical examples of digital systems are listed above. Those skilled in the art will appreciate that such descriptions are merely exemplary and are not intended to limit the scope of protection of the embodiments of the present invention.

[0076] Here, you can receive the demand information of the digital system through the user interface. The demand information of the digital system includes:

[0077] (1) Requirement information of the constructed digital system. For example, if the constructed digital system needs to add new functions or personalized customization functions, the corresponding requirement information can be generated for these functions.

[0078] (2) Requirement information during the construction of a digital system, such as the requirement information of the specific functional modules included in the digital system.

[0079] In one embodiment, the requirement information includes at least one of the following:

[0080] (1) System functional requirements that conform to the standard vocabulary for the functional division of digital systems.

[0081] For example, a custom function list based on industry standards such as ISA 95, ISA 88, and VDI 5600 can be presented in the user interface, and users can select the functions they need to implement from the list as system function requirements.

[0082] Figure 5 is an exemplary diagram of the standardized functional division of a digital system. In Figure 5, the standardized functional architecture of the digital system includes, from top to bottom: an enterprise control level 60 (e.g., Enterprise Resource Planning (ERP)), a manufacturing control level 71 (e.g., Manufacturing Execution System (MES)), and a manufacturing level 72 (e.g., work centers, machines, and installation configurations). The manufacturing control level 71 includes detailed modeling and process control 61, information management 62, quality management 63, personnel management 64, equipment management 65, performance analysis 66, data acquisition 67, materials management 68, order management 69, and energy management 70.

[0083] (2) The digital state of the digital system.

[0084] Based on the standard model of manufacturing enterprises, users can describe the current state of data by selecting and configuring data sources. For example, the digital state lists the specific format and / or data source required for the data. For example, in the requirements information, specify (1) the data source type: MongoDB; (2) the IP address of the data source; (3) the data type (e.g., order table); (4) the data field (e.g., ID), etc.

[0085] (3) Hardware configuration information of the digital system.

[0086] For example, hardware configuration information refers to the hardware configuration requirements of a digital system. Specifically, it may include hardware device information (such as device type and quantity), interface (such as Ethernet or Profibus), protocol (such as Step7, Modbus, OPC UA, etc.), and data points. Specifically, hardware device information may include S7-300 controllers, WinCC controllers, LOGO-smart controllers, and so on.

[0087] (4) Engineering scope of the digital system.

[0088] For example, the project scope may include the workgroup scope or production line scope of the digital system, etc.

[0089] Step 102: Input the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in the historical application suite, wherein the historical application suite is associated with the historical demand information.

[0090] The historical demand information can be demand information historically provided to human experts. The historical application suite is a recommended application suite determined by human experts based on the historical demand information. In other words, the human experts determined the historical application suite based on the historical demand information and their own professional knowledge. Therefore, there is a correlation between the historical application suite and the historical demand information, and this correlation represents the expert's knowledge. The expert knowledge represented by this correlation can be used to generate a recommendation unit adapted for the recommended application suite. Specifically, the recommendation unit can be implemented as a software algorithm, a hardware module, a firmware module, or an integrated system comprising a software algorithm and / or a hardware module and / or a firmware module.

[0091] In one embodiment, the tag information of the application includes at least one of the following: a unique identifier of the application; and capability description information of the application. Similarly, in the capability description information, the application's capabilities are described using standard vocabulary that complies with the functional division of digital systems.

[0092] Here, after receiving the input information, the recommendation unit determines a recommended application suite (e.g., determines the unique identifier of each application included in the application suite). Thus, by utilizing the recommendation unit determined based on historical demand information and historical application suites, automated application suite recommendations are achieved, reducing reliance on human experts, lowering costs, and improving recommendation efficiency.

[0093] Step 103: Provide the application suite recommended by the recommendation unit.

[0094] Here, the application suite recommended by the recommendation unit can be obtained in various ways (for example, from the APP platform in the cloud), and the application suite recommended by the recommendation unit can be provided (for example, the application suite is sent to the initiator of the demand information of the digital system).

[0095] In one embodiment, the method includes: establishing a mapping table based on the mapping relationship between keywords in historical demand information and the tag information of each application in the historical application suite; storing the mapping table in a recommendation unit, wherein the recommendation unit is adapted to query the mapping table to determine the tag information that matches the keywords in the demand information, and then determine a recommended application suite based on the matching tag information. Therefore, the application suite can be quickly determined by querying the mapping table, improving the speed of recommendation.

[0096] For example: Assume that the keywords in the historical demand information include: "material loading", "product quality control" and "assembly". The historical application suite includes APP1, APP2, APP3 and APP4. Among them, the label information of APP1 includes the description information of "material loading" and the ID of APP1, the label information of APP2 includes the description information of "raw material quality control" and the ID of APP2, the label information of APP3 includes the description information of "manufacturing process quality control" and the ID of APP3, and the label information of APP4 includes the description information of "assembly" and the ID of APP4. Therefore, in the mapping table: "material loading" has a mapping relationship with the ID of APP1, "product quality control" has a mapping relationship with the ID of APP2 and the ID of APP3, and "assembly" has a mapping relationship with the ID of APP4. Preferably, considering that the keywords in the historical demand information and the keywords in the APP description information may not necessarily match completely, the mapping relationship between the keywords in the historical demand information and the keywords in the APP description information can be further saved in the mapping table, and the keywords in the APP description information can be further displayed after the APP ID is determined, so as to facilitate the confirmation of the accuracy of the recommendation.

[0097] After establishing the mapping table, when a request message containing "material loading" is received, the mapping table is queried and the matching information is APP1's ID, so APP1 is recommended. When a request message containing "product quality control" is received, the mapping table is queried and the matching information is APP2's ID and APP3's ID, so APP2 and APP3 are recommended.

[0098] In one embodiment, the method includes: determining a training sample, the training sample including historical demand information, wherein the training labels of the training sample are the label information of each application in the historical application suite; inputting the training sample into a neural network model to receive the label information of the predicted application from the neural network model; determining a loss function value based on the difference between the predicted application label information and the training label; and configuring the model parameters of the neural network model so that the loss function value is below a preset threshold. This indicates that the application suite can be determined using artificial intelligence, improving the accuracy of recommendations.

[0099] In one embodiment, before providing the application suite recommended by the recommendation unit, the method further includes: parsing application dependencies of the recommended application suite; obtaining applications that the recommended application suite depends on based on the application dependencies; and including the dependent applications in the recommended application suite.

[0100] For example, assume that the application suite recommended by the recommendation unit includes: APP1, APP1, APP3 and APP4. By analyzing the dependency relationships of APP1, APP1, APP3 and APP4, it is found that: APP1, APP1 and APP3 can all be executed independently without relying on other APPs, while the execution of APP4 depends on APP5. Therefore, APP5 is obtained (for example, APP5 is downloaded from the cloud platform), and APP6 is included in the recommended application suite, and then the application suite is provided to the initiator of the demand information of the digital system. It can be seen that based on the analysis of application dependencies, the dependent applications can be automatically included in the application suite, and users no longer need to find the dependent applications on their own, which is convenient for users to use.

[0101] The implementation process of the embodiment of the present invention includes two stages. In the first stage, a recommendation unit is generated based on the knowledge of human experts. In the second stage, an application suite is automatically recommended based on the recommendation unit.

[0102] Figure 2 is an exemplary schematic diagram of an expert-based manual recommendation application suite. Figure 2 exemplarily describes the execution process of the first phase.

[0103] In Figure 2, multiple application providers 16 publish their own applications (one or more) to the application database 14 in the application management process 13. Moreover, during the application publishing process, the application providers 16 upload the capability information of their respective applications respectively. In the application database 14, the capability information of each application is associated with the ID of the corresponding application to form the label information of each application. In the demand input process 11, the manufacturing enterprise user 10 inputs the demand information of the digital system (which may include system function requirements, digital status, hardware configuration information and project scope, etc.). Based on the demand information, the expert 17 uses his own knowledge in the recommendation process 12 to determine the corresponding application suite (including one or more applications). In the recommendation process 12, the application suite can also be automatically downloaded from the application database 14, and then provided to the manufacturing enterprise user 10.

[0104] Based on the learning of expert knowledge in the first stage, a recommendation unit that can automatically recommend application suites can be generated.

[0105] FIG3 is a first exemplary schematic diagram of automatically recommending an application suite based on expert knowledge according to an embodiment of the present invention.

[0106] In Figure 3, multiple application providers 16 publish their applications to the application database 14 in the application management process 13. During the application publishing process, application providers 16 upload their respective application capability information. Application database 14 associates and stores each application's capability information with its corresponding application ID to form tag information for each application. Recommendation unit 30 includes database 15. Database 15 stores a mapping between keywords in the requirement information sent to experts 17 in the first phase and the tag information for each application in the application suite, determined by experts 17.

[0107] In the requirements input process 11, the manufacturing enterprise user 10 inputs the requirements information for the digital system (which may include system functional requirements, digital status, hardware configuration information, and project scope). The recommendation unit 30 extracts keywords from the requirements information and, based on these keywords, queries the database 15 in the recommendation process 12 to determine the corresponding application suite (including one or more applications). The recommendation unit 30 can also automatically download the application suite from the application database 14 and then provide the application suite to the manufacturing enterprise user 10.

[0108] FIG4 is a second exemplary schematic diagram of automatically recommending an application suite based on expert knowledge according to an embodiment of the present invention.

[0109] In Figure 4, multiple application providers 16 publish their applications to the application database 14 in the application management process 13. During the application publishing process, the application providers 16 upload the capability information of their respective applications. In the application database 14, the capability information of each application is associated with the corresponding application ID to form the label information of each application. The recommendation unit 30 includes a neural network model 31. Among them, the demand information sent to the expert 17 in the first stage is used as a training sample; the label information of each application in the application suite determined by the expert 17 in the first stage is used as the training label of the training sample, and the neural network model 31 is trained.

[0110] After the neural network model 31 is trained, the manufacturing enterprise user 10 enters the digital system's requirements (which may include system functional requirements, digital status, hardware configuration information, and project scope, etc.) in the requirements input process 11. The recommendation unit 30 generates label information for predicted applications based on the neural network model 31. The set of predicted applications constitutes the downloadable application suite. The recommendation unit 30 can also automatically download the application suite from the application database 14 and then provide the application suite to the manufacturing enterprise user 10.

[0111] FIG6 is an exemplary structural diagram of an apparatus for recommending an application suite according to an embodiment of the present invention. As shown in FIG6 , the apparatus 600 for recommending an application suite includes:

[0112] Receiving module 601, used to receive demand information of the digital system;

[0113] an input module 602 for inputting the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in the historical application suite, wherein the historical application suite is associated with the historical demand information;

[0114] A providing module 603 is configured to provide an application suite recommended by a recommendation unit.

[0115] In one embodiment, it includes: a mapping module 604, which is used to establish a mapping table based on the mapping relationship between keywords in historical demand information and tag information of each application in the historical application suite; store the mapping table in a recommendation unit, wherein the recommendation unit is adapted to determine tag information that matches the keywords in the demand information based on querying the mapping table, and determine a recommended application suite based on the matching tag information.

[0116] In one embodiment, it includes: a training module 605, which is used to determine a training sample, the training sample includes historical demand information, wherein the training label of the training sample is the label information of each application in the historical application suite; inputting the training sample into a neural network model to receive label information of the predicted application from the neural network model; determining a loss function value based on the difference between the label information of the predicted application and the training label; and configuring model parameters of the neural network model so that the loss function value is lower than a preset threshold.

[0117] In one embodiment, a module 603 is provided for: before providing the application suite recommended by the recommendation unit, parsing the application dependencies of the recommended application suite; obtaining the applications on which the recommended application suite depends based on the application dependencies; and including the dependent applications in the recommended application suite.

[0118] The embodiment of the present invention also proposes an electronic device with a processor-memory architecture. Figure 7 is a structural diagram of an electronic device according to an embodiment of the present invention. As shown in Figure 7, the electronic device 700 includes a processor 701, a memory 702, and a computer program stored on the memory 702 and executable on the processor 701. When the computer program is executed by the processor 701, the method of any of the above recommended application suites is implemented. Among them, the memory 702 can be specifically implemented as a variety of storage media such as an electrically erasable programmable read-only memory (EEPROM), a flash memory (Flash memory), and a programmable read-only memory (PROM). The processor 701 can be implemented to include one or more central processing units or one or more field programmable gate arrays, wherein the field programmable gate array integrates one or more central processing unit cores. Specifically, the central processing unit or the central processing unit core can be implemented as a CPU, an MCU, or a DSP, and so on.

[0119] It should be noted that not all steps and modules in the above processes and structure diagrams are required, and certain steps or modules can be omitted based on actual needs. The execution order of the steps is not fixed and can be adjusted as needed. The division of the modules is merely for the convenience of describing the functional division adopted. In actual implementation, a module can be implemented by multiple modules, and the functions of multiple modules can be implemented by the same module. These modules can be located in the same device or in different devices.

[0120] The hardware modules in each embodiment can be implemented mechanically or electronically. For example, a hardware module may include a specially designed permanent circuit or logic device (such as a dedicated processor, such as an FPGA or ASIC) for performing a specific operation. The hardware module may also include a programmable logic device or circuit (such as a general-purpose processor or other programmable processor) temporarily configured by software to perform a specific operation. As for whether to implement the hardware module mechanically, or using a dedicated permanent circuit, or using a temporarily configured circuit (such as configured by software), it can be decided based on cost and time considerations.

[0121] The above are only preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0122] Nouns and pronouns referring to persons in this patent application are not limited to a specific gender.

Claims

1. A method for recommending an application suite, characterized in that: include: receiving (101) demand information of a digital system; inputting (102) the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in a historical application suite, wherein the historical application suite is associated with the historical demand information; An application suite recommended by the recommendation unit is provided (103).

2. The method according to claim 1, characterized in that include: Establishing a mapping table based on a mapping relationship between keywords in the historical demand information and tag information of each application in the historical application suite; The mapping table is stored in the recommendation unit, wherein the recommendation unit is adapted to determine tag information matching the keywords in the requirement information based on querying the mapping table, and determine the recommended application suite based on the matching tag information.

3. The method according to claim 1, characterized in that include: Determine a training sample, wherein the training sample includes the historical demand information, wherein a training label of the training sample is label information of each application in the historical application suite; Inputting the training sample into a neural network model to receive label information of a prediction application from the neural network model; Determining a loss function value based on a difference between the label information of the prediction application and the training label; The model parameters of the neural network model are configured so that the loss function value is lower than a preset threshold.

4. The method according to claim 1, characterized in that The requirement information includes at least one of the following: System functional requirements that conform to standard vocabulary regarding the functional division of digital systems; The digital status of digital systems; Hardware configuration information of the digital system; Engineering scope of digital systems.

5. The method according to claim 1, characterized in that The tag information includes at least one of the following: The unique identifier of the application; Description of application capabilities.

6. The method according to any one of claims 1 to 5, characterized in that Before providing (103) the application suite recommended by the recommendation unit, the method further includes: parsing application dependencies of the recommended application suite; Based on the application dependency relationship, obtaining the application that the recommended application suite depends on; The dependent applications are included in the recommended application suite.

7. A device for recommending an application suite, characterized in that: include: A receiving module (601), used for receiving demand information of a digital system; An input module (602) for inputting the demand information into a recommendation unit adapted to recommend an application suite, wherein the recommendation unit is determined based on historical demand information and tag information of each application in a historical application suite, wherein the historical application suite is associated with the historical demand information; A providing module (603) is used to provide the application suite recommended by the recommendation unit.

8. The device according to claim 7, characterized in that include: A mapping module (604) is used to establish a mapping table based on the mapping relationship between the keywords in the historical demand information and the tag information of each application in the historical application suite; The mapping table is stored in the recommendation unit, wherein the recommendation unit is adapted to determine tag information matching the keywords in the requirement information based on querying the mapping table, and determine the recommended application suite based on the matching tag information.

9. The device according to claim 7, characterized in that include: A training module (605) is used to determine a training sample, wherein the training sample includes the historical demand information, wherein the training label of the training sample is the label information of each application in the historical application suite; input the training sample into a neural network model to receive label information of a predicted application from the neural network model; determine a loss function value based on a difference between the label information of the predicted application and the training label; and configure model parameters of the neural network model so that the loss function value is lower than a preset threshold.

10. The device according to any one of claims 7 to 9, characterized in that: The providing module (603) is used to: before providing the application suite recommended by the recommendation unit: parse the application dependency relationship of the recommended application suite; based on the application dependency relationship, obtain the application that the recommended application suite depends on; and include the dependent application in the recommended application suite.

11. An electronic device, characterized in that: include: Processor (701); A memory (702), configured to store executable instructions of the processor (701); The processor (701) is used to read the executable instructions from the memory (702) and execute the The executable instructions are used to implement the method of recommending an application suite according to any one of claims 1-6.

12. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the method for recommending an application suite according to any one of claims 1 to 6 is implemented.

13. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for recommending an application suite according to any one of claims 1 to 6.

Images