Method and device for generating control strategy in information system, equipment and medium

Abstract

The embodiment of the invention provides a method, device and equipment for generating a control strategy in an information system and a storage medium. The method comprises the following steps: receiving first information input by a user in a natural language, wherein the first information indicates a target rule for managing the information system; determining a first control strategy generation module matched with the first information from a plurality of control strategy generation modules by utilizing a first machine learning model; presenting target configuration information generated for a target control policy, which is generated using a first control policy generation module and indicates a control policy for implementing a target rule in the information system; and in response to a received positive indication for the target configuration information, adding a target control strategy corresponding to the target rule in the information system based on the target configuration information. Therefore, the strategy can be automatically improved and optimized, so that the operation and maintenance efficiency and the safety management efficiency of various information systems such as an enterprise office network system and a special business system are improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for generating a control strategy in an information system. Background Art

[0002] With the development of information technology (IT), the development of various industries is increasingly dependent on information systems. Correspondingly, the demand for management platforms for information systems is also increasing. For example, the information technology operation and maintenance and data security management of an enterprise can use various IT tools to transform the enterprise's management system into actual IT capabilities and business support, including management strategy formulation, operation and maintenance data analysis, etc. However, in an increasingly complex network environment, effective IT operation and maintenance also faces many challenges. Therefore, an effective policy generation method is expected to achieve management of information systems. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for generating a control policy in an information system is provided. The method includes: receiving first information input by a user in a natural language, the first information indicating a target rule for managing the information system; using a first machine learning model, determining a first control policy generation module that matches the first information from a plurality of control policy generation modules, the plurality of control policy generation modules being respectively configured to generate configuration information of different types of control policies; presenting target configuration information generated for the target control policy, the target configuration information being generated using the first control policy generation module, and the target control policy indicating a control policy for implementing the target rule in the information system; and in response to receiving a positive indication for the target configuration information, adding a target control policy corresponding to the target rule in the information system based on the target configuration information.

[0004] In the second aspect of the present disclosure, a device for generating a control policy in an information system is provided. The device includes: a first information receiving module, configured to receive first information input by a user in a natural language, the first information indicating a target rule for managing the information system; a control policy generation module determination module, configured to use a first machine learning model to determine a first control policy generation module that matches the first information from multiple control policy generation modules, and the multiple control policy generation modules are respectively configured to generate configuration information of different types of control policies; a configuration information presentation module, configured to present target configuration information generated for the target control policy, the target configuration information is generated using the first control policy generation module, and the target control policy indicates a control policy for implementing the target rule in the information system; and a control policy adding module, configured to add a target control policy corresponding to the target rule in the information system based on the target configuration information in response to receiving an affirmative indication for the target configuration information.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 A flowchart illustrating an example process for generating a control policy in an information system according to some embodiments of the present disclosure;

[0011] Figure 3A schematic diagram showing an example architecture for generating a control policy in an information system according to some embodiments of the present disclosure;

[0012] Figure 4 A flowchart showing a process of generating a control strategy in an information system according to some embodiments of the present disclosure;

[0013] Figure 5 A block diagram showing an apparatus for generating a control strategy in an information system according to some embodiments of the present disclosure; and

[0014] Figure 6 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0016] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0017] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0018] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0019] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0020] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain 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 construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0021] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0022] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0023] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0024] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", which are used interchangeably in this article. A model may also include different types of processing units or networks.

[0025] As briefly mentioned above, effective IT operation and maintenance also faces many challenges in an increasingly complex network environment. For example, it requires a deep understanding of the overall IT architecture of the enterprise, which includes not only technical aspects, but also knowledge of business processes, organizational structures, etc. Accordingly, high-quality IT operation and maintenance relies on high-quality talents, requiring compound talents who understand both technology and business. Furthermore, the IT environment is dynamically changing, and the operation and maintenance strategy needs to be continuously optimized and adjusted, which requires operation and maintenance personnel to have keen insight and rapid response capabilities.

[0026] Therefore, an embodiment of the present disclosure proposes a scheme for generating a control policy in an information system. According to various embodiments of the present disclosure, first information of a target rule for managing an information system input by a user in a natural language is received. Using a first machine learning model, a first control policy generation module matching the first information is determined from a plurality of control policy generation modules, and the plurality of control policy generation modules are respectively configured to generate configuration information of different types of control policies. Accordingly, target configuration information generated for the target control policy is presented, the target configuration information is generated using the first control policy generation module, and the target control policy indicates a control policy for implementing the target rule in the information system. Then, if a positive indication for the target configuration information is received, a target control policy corresponding to the target rule is added to the information system based on the target configuration information.

[0027] In the embodiments of the present disclosure, users are supported to express the control policies they want to add in natural language, and the control policies expressed in natural language are converted into executable policies in the information system using machine learning technology. Using the embodiments of the present disclosure, even if the user does not have a deep understanding of the information system, the control policy can be added. In addition, the user can add policies quickly and conveniently in natural language. Thus, the improvement and optimization of the policy can be completed automatically, thereby improving the operation and maintenance efficiency of the information system and reducing the operation and maintenance cost.

[0028] Example Environment

[0029] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, environment 100 may include system management platform 110. In this example environment 100, system management platform 110 may be used to manage the information system of an organization (enterprise, government unit, other group, etc.). Such an information system may include a collection of various hardware, software, networks, data resources, etc. For example, an information system may include various hardware devices within an organization. Interfaces between different components within an information system and interfaces of the information system to the outside world are also part of the information system.

[0030] In the case of receiving information for generating a control strategy inputted by the user 140 in natural language, the target model 155 may be called to determine a control strategy generation module, and then the control strategy is added to the information system. Figures 1 to 4 The described "module" is configured to perform one or more tasks, or to implement one or more functions. For example, such a module may be an encapsulated functional module that provides an external input interface and an output interface. Such a module may also be referred to as a plug-in in this article.

[0031] In some examples, the system management platform 110 can also determine the control policy by calling the control policy generation module. Then, the system management platform 110 adds the control policy to the information system by calling the control adding policy module. In some cases, the user 140 can be a user who manages the control policy by using a terminal device, such as an IT administrator of an enterprise.

[0032] In some embodiments, at least some of the functions of the system management platform 110 can be implemented based on the target model 155. In the process of adding control strategies in the information system, the system management platform 110 can call one or more target models 155, such as the capabilities of the target model 155. As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for the given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0033] The system management platform 110 may be deployed locally on the terminal device of the user 140, and / or may be supported by a server device. For example, the terminal device of the user 140 may run a client of the system management platform, and the client may support the interaction between the user and the system management platform provided by the server. In the case where the system management platform runs locally on the user's terminal device, the user 140 may directly interact with the local system management platform using the terminal device. In the case where the system management platform runs on the server device, the server device may provide services to the client running in the terminal device based on the communication connection with the terminal device. The system management platform 110 may present a corresponding interface 142 to the user 140 based on the operation of the user 140, so as to output information related to system management to the user 140 and / or receive information from the user 140.

[0034] The system management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the data management platform 110 can be implemented based on cloud services.

[0035] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and does not imply any limitation on the scope of the present disclosure.

[0036] Some example embodiments of the present disclosure will be described below with reference to the accompanying drawings. Hereinafter, the example embodiments will be described mainly with respect to the system management platform 110. It should be understood that the actions described with respect to the system management platform 110 can be performed by the control strategy generation module and the control strategy addition module on the system management platform 110, or can be performed by the control strategy generation module and the control strategy addition module in collaboration with their service end (e.g., server 130) and / or machine learning model.

[0037] The following will refer to Figure 2 and Figure 3 The present disclosure's approach to policy generation is described. Figure 2 A flow chart of an example process 200 for a control strategy generation module, a control strategy addition module according to some embodiments of the present disclosure is shown. Figure 3 A schematic diagram of an example architecture 300 for a control strategy generation module and a control strategy addition module according to some embodiments of the present disclosure is shown.

[0038] In block 211, the system management platform 110 receives first information input by a user in natural language. The first information indicates a target rule for managing an information system, for example, a rule for managing an information technology system (IT system) input by a user (also referred to as a manager). In some examples, the system management platform 110 receives the natural language input by the user, for example, a natural language corresponding to a security management system or IT management system of an enterprise that the user specifically needs to implement, or a problem scenario that an enterprise IT administrator expects to solve.

[0039] In some embodiments, the system management platform 110 uses a first machine learning model to determine a first control policy generation module that matches the first information from a plurality of control policy generation modules. In some embodiments, the plurality of control policy generation modules are respectively configured to generate configuration information for different types of control policies. It is understandable that the system management platform 110 uses a first machine learning model to determine the user's intent, and based on the user's intent, determines a first control policy generation module (also referred to as a policy generation plug-in) from a plurality of pre-configured control policy generation modules for generating different types of control policies. For example, if the system management platform 110 uses a first machine learning model to determine that the administrator's intent category is "solved through IT system platform policy items that can implement configuration information", the first machine learning model can call a policy generation plug-in that matches the current administrator's intent category.

[0040] In some examples, the administrator may pre-set each type of policy to correspond to a control policy generation module. For example, if a security policy needs to be generated, the system management platform 110 may call a security control policy generation module. If a network access policy needs to be generated, the system management platform 110 may call a network access control policy generation module. In some examples, the plug-in may constrain the model to convert the policy into what kind of configuration information.

[0041] In some embodiments, the system management platform 110 may also determine the first control strategy generation module that matches the first information from multiple control strategy generation modules in the following manner. Figure 2 As shown, in process 200, in block 212, the system management platform 110 retrieves at least one knowledge base related to the management of the information system according to the first information to obtain a search result matching the first information. In block 213, the system management platform 110 determines a first control strategy generation module from a plurality of control strategy generation modules based on the search result using a first machine learning model.

[0042] In some embodiments, at least one knowledge base may include a knowledge base on general technologies of the information system, such as an information technology knowledge base. Alternatively or additionally, at least one knowledge base may include a knowledge base on the management of the organization to which the information system belongs, such as an enterprise management system knowledge base. Alternatively or additionally, at least one knowledge base may include a knowledge base on historical management strategies adopted by the information system, such as a historical strategy database. Alternatively or additionally, at least one knowledge base may also include a knowledge base on reference methods for policy configuration, such as a knowledge base for policy configuration methods.

[0043] As shown in the example architecture 300, the system management platform 110 receives (311) specific requirements for the policy to be generated input by the user. Based on the first information input by the user, the system management platform 110 sends (312) a request for querying the target policy to the machine learning model. Based on the first information, the machine learning model searches for relevant knowledge background through a knowledge base including an IT technology knowledge base, an enterprise management system knowledge base, historical policy data, and a policy configuration method to determine the search results, thereby improving the understanding of IT background knowledge.

[0044] Subsequently, the machine learning model analyzes and summarizes the search results to determine the first control strategy generation module for generating the strategy. The machine learning model sends (313) a call request for calling the first control strategy generation module to the system management platform 110. After receiving the call request, the system management platform 110 calls (314) the first control strategy generation module. Accordingly, the system management platform 110 receives (315) the initial target configuration information for the target strategy generated by the first control strategy generation module.

[0045] Therefore, the embodiments of the present disclosure analyze the enterprise's IT management system, IT technology knowledge base, and historical system platform policy data knowledge base, and based on the conditional logic of time, event data, and processing measures, can decompose the enterprise's IT management methods for terminals, security, etc. into configuration parameters corresponding to the system platform. Accordingly, the configuration parameters can be provided to the administrator for reference to reduce the requirements for the enterprise administrator's IT technology background and historical enterprise solution implementation experience. This method improves the work efficiency of enterprise administrators in the daily IT operation and maintenance process.

[0046] The following reference Figure 2 and Figure 3 The process of determining target configuration information by the system management platform 110 is described. It can be understood that the actions described with respect to the system management platform 110 can be performed by the control strategy generation module.

[0047] Continuing with process 200, in box 214, the system management platform 110 converts the first information into descriptive information with preset logic by calling the second machine learning model through the first control strategy generation module. The system management platform 110 determines the target configuration information based on the descriptive information and the corresponding parameters of the information system. In some examples, the second machine learning model and the first machine learning model can be the same machine learning model, for example, a language model, which is not limited in this disclosure. In some examples, the first control strategy generation module can use the second machine learning model to convert the first information input by the user into descriptive information with preset logic, such as "when in X, facing X data situation, take X action". Then, the system management platform 110 converts the descriptive information into configuration information based on the system parameters supported by the information system.

[0048] In some embodiments, the preset logic may include conditional logic, and the description information includes a first part corresponding to the condition of the conditional logic and a second part corresponding to the action of the conditional logic. For example, the first part corresponding to the condition of the conditional logic may be expressed as "if...", and the second part corresponding to the action of the conditional logic may be expressed as "then...".

[0049] In some embodiments, the system management platform 110 uses the first control policy generation module to determine prompt information for the second machine learning model, where the prompt information includes trigger condition information, and the trigger condition information indicates multiple trigger conditions of the target type policy corresponding to the first control policy generation module. Then, the system management platform 110 generates description information using the second machine learning model based on the prompt information and the first information. The first part indicates the target trigger condition among the multiple trigger conditions. For example, for a rule about office safety, the second machine learning model can rewrite and optimize this rule to make the information it expresses clearer. The following will refer to Table 1 to illustrate the generation of prompt information, which is an example of prompt information.

[0050] Table 1

[0051]

[0052]

[0053]

[0054] It can be understood that the system management platform 110 converts the first information into descriptive information with a logical relationship using the second machine learning model via the first control strategy generation module. In some embodiments, the second machine learning model can convert the first information into descriptive information with a logical relationship based on the prompt information. In some embodiments, the prompt information includes trigger condition information, and the trigger condition information is used to indicate multiple trigger conditions of the target type control strategy corresponding to the first control strategy generation module. As shown in Table 1, the third row in the prompt information shows an example of multiple trigger conditions. In some embodiments, the multiple trigger conditions can be pre-configured by the user.

[0055] In some examples, the second machine learning model can select a target trigger condition from multiple trigger conditions based on the description information. For example, if the second machine learning model determines that a piece of information input by a user corresponds to a rule about office safety, it can determine a trigger condition that matches the rule from multiple trigger conditions. In some embodiments, the second machine learning model can select at least one trigger condition that matches the description information from multiple trigger conditions based on the description information. Then, the second machine learning model analyzes and compares the at least one trigger condition to determine the target trigger condition.

[0056] In some embodiments, the system management platform 110 retrieves at least one knowledge base related to the management of the information system based on the first information to obtain a search result matching the first information. Then, the system management platform 110 can determine multiple trigger conditions from the search results. In some examples, the first control strategy generation module can use the second machine learning model combined with the knowledge base of the strategy configuration method to convert the information input by the user into a logical relationship based on "when in X, facing X data situation, make X disposal".

[0057] In some embodiments, the prompt information may also include a description and example of a conversion task of converting natural language input into description information. For example, as shown in Table 1, rows 5 to 9 in the prompt information show skill 1 used by the machine learning model. That is, the machine learning model can understand the information input by the user and rewrite the expression of the sentence into the form of "if..., then...".

[0058] In some embodiments, the prompt information may further include a selection rule for selecting a trigger condition from a plurality of trigger conditions. For example, as shown in Table 1, lines 11 to 13 in the prompt information show skill 2 used by the machine learning model. That is, the machine learning model selects at least one trigger condition that best matches the first information based on the rewritten rule description. Then, in combination with the rule description, the at least one selected trigger condition is compared and analyzed, and the most appropriate trigger condition is selected as the target trigger condition.

[0059] In some embodiments, the prompt information may also include constraints for the conversion task. For example, as shown in Table 1, lines 15 to 17 in the prompt information show constraint information used to constrain the machine learning model. That is, the machine learning model is constrained to only select the recommended trigger configuration from multiple trigger conditions provided by the user. Please do not generate non-existent trigger conditions based on the text.

[0060] In some embodiments, the prompt information includes action information, the action information indicates multiple control actions of the target type control policy, and the second part indicates a target management action among multiple management actions. In some examples, the prompt information can be to understand the first information input by the user and rewrite the expression of the sentence into the form of "if..., then..." For example, for the example "When a device that does not belong to the company's equipment accesses the network, the network permissions will be downgraded", the rewriting result can be "If the device does not belong to the company's equipment, the network permissions will be downgraded". It can be understood that the generation process of the target management action can refer to the generation process of the target trigger condition, and the present disclosure will not be repeated here.

[0061] In some embodiments, the system management platform 110 presents target configuration information generated for the target control policy. The target configuration information is generated using the first control policy generation module, and the target control policy indicates a control policy for implementing the target rule in the information system. In some examples, the system management platform 110 may present configuration information for the target control policy generated via the first control policy generation module. It is understandable that the system management platform 110 can implement the control policy of the target rule in the information system.

[0062] In some embodiments, if the system management platform 110 receives a positive indication for the target configuration information, it adds a target control policy corresponding to the target rule based on the target configuration information. Continuing with process 200, in box 215, after receiving the target configuration information output by the machine learning model, the system management platform 110 presents the target configuration information and determines whether the target configuration information meets the user's expectations. In box 216, if the system management platform 110 receives the user's determination of the target management information, it calls the policy adding plug-in. In box 217, the system management platform 110 calls the policy adding plug-in to add the control policy corresponding to the target rule.

[0063] In some embodiments, the system management platform 110 may add a target control policy corresponding to a target rule in the information system in the following manner. If the system management platform 110 receives a positive indication from the user, it extracts configuration parameters from the target configuration information. The system management platform 110 converts the configuration parameters into interface parameters of the target interface in the information system through the control policy adding module. Then, the system management platform 110 adds the interface parameters to the target interface as the target control policy through the control policy adding module.

[0064] In some examples, if the system management platform 110 receives a positive indication, it calls the control policy adding module to add the target control policy. The control policy adding module (also referred to as the control policy adding plug-in) can convert the configuration parameters in the target configuration information into the interface parameters of the target interface included in the information system (for example, a post request), and then call the target interface in the information system. Then, the control policy adding module can add the target control policy to the information system based on the interface parameters of the target interface, and return the added result to the system management platform 110.

[0065] like Figure 3 In the example architecture 300 shown, the system management platform 110 sends (316) the initial target configuration information for the target rule generated by the target rule generation block to the machine learning model. It can be understood that the first control strategy generation module converts the initial target configuration information into description information with logical relationships by using the machine learning model. Subsequently, the machine learning model sends (317) the description information with logical relationships (i.e., policy content) to the system management platform 110.

[0066] The system management platform 110 presents (318) the target configuration information corresponding to the description information with a logical relationship on the client device corresponding to the user. If the system management platform 110 receives (319) a confirmation addition instruction from the user's client device, the confirmation instruction is sent (320) to the machine learning model. Subsequently, the system management platform 110 receives (321) a request for calling the control strategy addition module sent from the machine learning model and extracts parameters. In some examples, the control strategy addition module can be used to add a control strategy to an information system.

[0067] The system management platform 110 calls (322) the policy adding block based on the request and parameters for calling the control policy adding module. Accordingly, the system management platform 110 receives (323) the result returned from the control policy adding module. The system management platform 110 sends (324) the result returned by the control policy adding module to the machine learning model. The system management platform 110 receives (325) the text returned by the machine learning model and sends (326) the text to the client device corresponding to the user. The text indication is used to inform the user of the result of the control policy addition, such as the control policy addition was successful, or the control policy failed to be added.

[0068] In summary, the present disclosure can improve the response efficiency to business through the combination of strategy analysis conversion and control strategy generation module. Furthermore, with the construction of more control strategy creation modules for different information systems and the accumulation of more historical control strategy data knowledge bases, the system can complete the management plan of the information system more intelligently and accurately.

[0069] Example Process

[0070] Figure 4 FIG. 4 is a flowchart of a process 400 for generating a control strategy in an information system according to some embodiments of the present disclosure. The process 400 may be implemented at the system management platform 110. Figure 1 Process 400 is described.

[0071] In block 410 , the system management platform 110 receives first information input by a user in a natural language, the first information indicating a target rule for managing an information system.

[0072] In box 420, the system management platform 110 uses the first machine learning model to determine a first control strategy generation module that matches the first information from multiple control strategy generation modules, and the multiple control strategy generation modules are respectively configured to generate configuration information of different types of control strategies.

[0073] In block 430 , the system management platform 110 presents target configuration information generated for a target control policy, the target configuration information being generated using the first control policy generation module, and the target control policy indicating a control policy for implementing a target rule in the information system.

[0074] At block 440 , in response to receiving a positive indication for the target configuration information, the system management platform 110 adds a target control policy corresponding to the target rule in the information system based on the target configuration information.

[0075] In some embodiments, determining the first control strategy generation module that matches the first information from multiple control strategy generation modules includes: based on the first information, obtaining a retrieval result that matches the first information by retrieving at least one knowledge base related to the management of the information system; and determining the first control strategy generation module from multiple control strategy generation modules based on the retrieval result using a first machine learning model.

[0076] In some embodiments, at least one knowledge base includes at least one of the following: a knowledge base about general technologies of information systems, a knowledge base about the management of the organization to which the information system belongs, a knowledge base about historical management strategies adopted by the information system, or a knowledge base about reference methods for policy configuration.

[0077] In some embodiments, the target configuration information is generated in the following manner: by calling the second machine learning model through the first control strategy generation module, the first information is converted into descriptive information with preset logic; and based on the descriptive information and corresponding parameters of the information system, the target configuration information is determined.

[0078] In some embodiments, the preset logic includes conditional logic, the descriptive information includes a first part corresponding to the condition of the conditional logic and a second part corresponding to the action of the conditional logic, and converting the first information into descriptive information with preset logic includes: using a first control strategy generation module to determine prompt information for a second machine learning model, the prompt information includes trigger condition information, the trigger condition information indicates multiple trigger conditions of a target type control strategy corresponding to the first control strategy generation module; and based on the prompt information and the first information, using the second machine learning model to generate descriptive information, the first part indicating a target trigger condition among multiple trigger conditions.

[0079] In some embodiments, the prompt information further includes one of the following: a description and example of a conversion task of converting a natural language input into descriptive information, a selection rule for selecting a trigger condition from multiple trigger conditions, or a constraint of the conversion task.

[0080] In some embodiments, the multiple trigger conditions are determined by: based on the first information, retrieving at least one knowledge base related to the management of the information system to obtain search results matching the first information; and determining the multiple trigger conditions from the search results.

[0081] In some embodiments, the prompt information includes action information, the action information indicates a plurality of control actions of the target type policy, and the second part indicates a target management action among the plurality of control actions.

[0082] In some embodiments, adding a target control policy corresponding to a target rule in an information system based on target configuration information includes: extracting configuration parameters from the target configuration information in response to an affirmative indication; converting the configuration parameters into interface parameters of a target interface in the information system through a control policy adding module; and adding the interface parameters to the target interface as a target control policy through the control policy adding module.

[0083] Example devices and equipment

[0084] Figure 5 A schematic structural block diagram of an apparatus 500 for generating a control strategy in an information system according to some embodiments of the present disclosure is shown. The apparatus 500 may be implemented as or included in a system management platform 110. Each module / component in the apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0085] As shown in the figure, the device 500 includes an information receiving module 510, which is configured to receive first information input by a user in natural language, and the first information indicates a target rule for managing an information system. The device 500 also includes a control strategy generation module determination module 520, which is configured to use a first machine learning model to determine a first control strategy generation module that matches the first information from multiple control strategy generation modules, and the multiple control strategy generation modules are respectively configured to generate configuration information of different types of control strategies. The device 500 also includes a configuration information presentation module 530, which is configured to present target configuration information generated for the target control strategy, the target configuration information is generated using the first control strategy generation module, and the target control strategy indicates a control strategy for implementing the target rule in the information system. The device 500 also includes a control strategy adding module 540, which is configured to add a target control strategy corresponding to the target rule in the information system based on the target configuration information in response to receiving an affirmative indication for the target configuration information.

[0086] In some embodiments, the control strategy generation module determination module 520 is also configured to obtain, based on the first information, a retrieval result matching the first information by retrieving at least one knowledge base related to the management of the information system; and to determine the first control strategy generation module from multiple control strategy generation modules based on the retrieval result using the first machine learning model.

[0087] In some embodiments, at least one knowledge base includes at least one of the following: a knowledge base about general technologies of information systems, a knowledge base about the management of the organization to which the information system belongs, a knowledge base about historical management strategies adopted by the information system, or a knowledge base about reference methods for policy configuration.

[0088] In some embodiments, the target configuration information is generated in the following manner: by calling the second machine learning model through the first control strategy generation module, the first information is converted into descriptive information with preset logic; and based on the descriptive information and corresponding parameters of the information system, the target configuration information is determined.

[0089] In some embodiments, the preset logic includes conditional logic, the description information includes a first part corresponding to the condition of the conditional logic and a second part corresponding to the action of the conditional logic, and the device 500 also includes a description information determination module, which is configured to use the first control strategy generation module to determine prompt information for the second machine learning model, the prompt information includes trigger condition information, and the trigger condition information indicates multiple trigger conditions of the target type control strategy corresponding to the first control strategy generation module; and based on the prompt information and the first information, generate description information using the second machine learning model, the first part indicating the target trigger condition among the multiple trigger conditions.

[0090] In some embodiments, the prompt information further includes one of the following: a description and example of a conversion task of converting a natural language input into descriptive information, a selection rule for selecting a trigger condition from multiple trigger conditions, or a constraint of the conversion task.

[0091] In some embodiments, the multiple trigger conditions are determined by: based on the first information, retrieving at least one knowledge base related to the management of the information system to obtain search results matching the first information; and determining the multiple trigger conditions from the search results.

[0092] In some embodiments, the prompt information includes action information, the action information indicates a plurality of control actions of the target type policy, and the second part indicates a target management action among the plurality of control actions.

[0093] In some embodiments, the control policy adding module 540 is also configured to extract configuration parameters from the target configuration information in response to a positive indication; convert the configuration parameters into interface parameters of the target interface in the information system through the control policy adding module; and add the interface parameters to the target interface as a target control policy through the control policy adding module.

[0094] Figure 6 6 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 6 The electronic device 600 shown can be used to implement Figure 1 The system management platform 110 is configured to:

[0095] like Figure 6 As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0096] The electronic device 600 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 600.

[0097] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 620 may include a computer program product 625 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0098] The communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0099] The input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0100] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0101] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0103] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0104] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0105] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. 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 implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating a control strategy in an information system, comprising: receiving first information input by a user in a natural language, the first information indicating a target rule for managing an information system; Determine, using a first machine learning model, a first control strategy generation module that matches the first information from a plurality of control strategy generation modules, wherein the plurality of control strategy generation modules are respectively configured to generate configuration information of different types of control strategies; presenting target configuration information generated for a target control policy, the target configuration information being generated using the first control policy generation module, and the target control policy indicating a control policy for implementing the target rule in the information system; as well as In response to receiving a positive indication for the target configuration information, the target control policy corresponding to the target rule is added in the information system based on the target configuration information.

2. The method according to claim 1, wherein determining a first control strategy generation module matching the first information from a plurality of control strategy generation modules comprises: Based on the first information, obtaining a search result matching the first information by searching at least one knowledge base related to the management of the information system; as well as The first control strategy generation module is determined from the multiple control strategy generation modules using the first machine learning model based on the retrieval results.

3. The method according to claim 2, wherein the at least one knowledge base comprises at least one of the following: A knowledge base on common technologies of said information systems, A knowledge base about the management of the organization to which the said information system belongs, a knowledge base about the historical management strategies employed by the information system in question, or A knowledge base of reference methods for policy configuration.

4. The method according to claim 1, wherein the target configuration information is generated by: By calling the second machine learning model by the first control strategy generation module, the first information is converted into description information with preset logic; and Based on the description information and corresponding parameters of the information system, the target configuration information is determined.

5. The method according to claim 4, wherein the preset logic includes conditional logic, the description information includes a first part corresponding to a condition of the conditional logic and a second part corresponding to an action of the conditional logic, and converting the first information into description information having the preset logic includes: Determine, using the first control strategy generation module, prompt information for the second machine learning model, the prompt information including trigger condition information, the trigger condition information indicating a plurality of trigger conditions of a target type control strategy corresponding to the first control strategy generation module; as well as Based on the prompt information and the first information, the description information is generated using the second machine learning model, and the first part indicates a target trigger condition among the multiple trigger conditions.

6. The method according to claim 5, wherein the prompt information further comprises one of the following: Description and examples of the task of converting natural language input into the described information, a selection rule for selecting a trigger condition from the plurality of trigger conditions, or The constraints of the transformation task.

7. The method according to claim 5, wherein the plurality of trigger conditions are determined by: Based on the first information, obtaining a search result matching the first information by searching at least one knowledge base related to management of the information system; and The plurality of trigger conditions are determined from the search results. 8 . The method according to claim 5 , wherein the prompt information includes action information, the action information indicates a plurality of control actions of the target type control strategy, and the second part indicates a target management action among the plurality of management actions.

9. The method according to claim 1, wherein adding the target control policy corresponding to the target rule in the information system based on the target configuration information comprises: In response to the positive indication, extracting configuration parameters from the target configuration information; By controlling the strategy adding module, the configuration parameters are converted into interface parameters of the target interface in the information system; as well as The interface parameters are added to the target interface through the control strategy adding module as the target control strategy.

10. An apparatus for strategy generation, comprising: A first information receiving module is configured to receive first information input by a user in a natural language, wherein the first information indicates a target rule for managing an information system; a control strategy generation module determination module, configured to use a first machine learning model to determine a first control strategy generation module that matches the first information from a plurality of control strategy generation modules, wherein the plurality of control strategy generation modules are respectively configured to generate configuration information of different types of control strategies; a configuration information presenting module, configured to present target configuration information generated for the target control strategy, wherein the target configuration information is generated by using the first control strategy generating module, and the target control strategy is a control strategy capable of implementing the target rule in the information system; as well as The control policy adding module is configured to, in response to receiving a positive indication for the target configuration information, add the target control policy corresponding to the target rule in the information system based on the target configuration information.

11. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 9 when executed by the at least one processing unit.

12. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 9.

Images