A multi-granularity cache automatic clearing method and system for a fan AI assistant
By labeling the cached data of the wind turbine AI assistant with multi-dimensional tags and setting retention strategies, the shortcomings of cache management in existing technologies are solved, enabling refined management and long-term retention of high-value data, thereby improving system stability and user experience.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- FUJIAN HAIDIAN OPERATION & MAINTENANCE TECH CO LTD
- Filing Date
- 2026-03-13
- Publication Date
- 2026-07-21
AI Technical Summary
The existing cache management strategy of the wind turbine AI assistant cannot distinguish the value of data services, resulting in the accidental deletion of high-value historical fault records. It lacks the ability to clean up data in a targeted manner according to business dimensions, and the crude cleaning process can easily cause the loss of critical data, affecting the user experience.
A multi-granularity cache automatic clearing method is adopted. By labeling cached data with multi-dimensional tags, including type, source, creation timestamp, and last access time, different retention policies and clearing priorities are set. Combined with the project ID and equipment model of the wind turbine, faults are monitored in real time and the clearing policy is adjusted accordingly.
It enables fine-grained cache management by project, device, and data type, ensuring the long-term retention of high-value fault knowledge, preventing accidental deletion of critical data, effectively freeing up storage resources, and improving system stability and user experience.
Smart Images
Figure CN122432072A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cache data management technology, specifically to a multi-granularity cache automatic clearing method and system for wind turbine AI assistants. Background Technology
[0002] Current wind turbine AI assistant clients generally use a global LRU (Least Recently Used) or fixed-period timed clearing strategy to manage local cache. All cached data is treated as homogeneous objects and processed uniformly according to access time or storage duration.
[0003] The aforementioned prior art has the following significant drawbacks: (1) It is impossible to distinguish the value of data services, and high-value historical fault records (such as rare fault cases) may be deleted by mistake, while low-value temporary logs are retained; (2) Lack of the ability to perform targeted cleanup based on business dimensions such as wind farm projects and equipment models, resulting in irrelevant project data occupying limited storage space for a long time; (3) The difference in data timeliness was not considered, and the same strategy was used for benchmark knowledge that needs to be retained for a long time and temporary sessions that are effective for a short time; (4) The cleaning process is rough and may cause users to lose key data unexpectedly, affecting the user experience. Summary of the Invention
[0004] To address these issues, this invention proposes a multi-granularity cache automatic clearing method and system for wind turbine AI assistants.
[0005] According to one aspect of the present invention, a multi-granularity cache automatic clearing method for wind turbine AI assistants is proposed, comprising the following steps: S1, store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priority are specified according to the different sources and types of cache data. S2, when the local storage usage exceeds a certain threshold or triggers the daily scheduled clearing task, the wind turbine cache data clearing process is carried out; S3, traverse the wind turbine cache data according to the clearing priority, and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data; S4. If the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, physical deletion is performed. After deletion, the storage utilization rate is updated. If it drops below a certain threshold, the wind turbine cache data clearing process is terminated in advance.
[0006] Specifically, the types of wind turbine cache data include knowledge bases, session records, temporary files, and logs; the sources of the wind turbine cache data include expert review and automatic extraction.
[0007] Specifically, when the type of the wind turbine cache data is a knowledge base and the source is expert review, the wind turbine cache data is subject to a permanent retention strategy; When the type of the wind turbine cache data is a knowledge base and the source is automatic extraction, the wind turbine cache data is subject to a 365-day retention policy. When the type of the wind turbine cache data is session record, the wind turbine cache data is subject to a 30-day retention policy; When the type of the wind turbine cache data is a temporary file, the wind turbine cache data is subject to a session-end deletion retention policy; When the type of the wind turbine cache data is log, the wind turbine cache data is subject to a 90-day retention policy.
[0008] Specifically, the priority order for clearing files, from highest to lowest, is: temporary files, session records, logs, knowledge bases that are automatically extracted, and knowledge bases that are reviewed by experts.
[0009] Specifically, it also includes S5, where the multidimensional tag also includes the project ID and equipment model of the wind turbine, monitors the operating status of the wind turbine in real time, identifies and stores the wind turbine cache data related to the fault separately when the wind turbine is detected to have a fault, and specifies the temporary retention strategy and temporary clearing priority sorting of the wind turbine cache data related to the fault according to the severity level of the fault of the wind turbine.
[0010] Specifically, specifying the temporary retention strategy and temporary clearing priority ranking of the fault-related wind turbine cache data based on the fault severity level of the wind turbine includes: obtaining the fault severity level of the wind turbine; determining the fault weight base number based on the fault severity level; for different types of fault-related wind turbine cache data, adopting the corresponding comprehensive retention weight calculation method based on the fault weight base number; specifying the corresponding temporary retention strategy for the fault-related wind turbine cache data according to the numerical range of the comprehensive retention weight of each fault-related wind turbine cache data; and sorting the fault-related wind turbine cache data in descending order according to the value of the comprehensive retention weight to generate the temporary clearing priority ranking.
[0011] Specifically, obtaining fault-related wind turbine cache data includes: matching and filtering according to the fault type of the wind turbine to obtain knowledge base type wind turbine cache data corresponding to the fault type; filtering log type wind turbine cache data or session record type wind turbine cache data based on time range; and obtaining temporary file type wind turbine cache data generated based on fault detection.
[0012] Specifically, the method of calculating the comprehensive retention weight based on the fault weight base for different types of fault-related wind turbine cache data includes: For the knowledge base type wind turbine cache data, calculate the type matching degree coefficient of the knowledge base type wind turbine cache data according to the fault type, calculate the time decay coefficient according to the time difference between the creation time of the knowledge base type wind turbine cache data and the current time, and calculate the comprehensive retention weight of the knowledge base type wind turbine cache data based on the type matching degree coefficient, the fault weight base and the time decay coefficient. For the log-type wind turbine cache data or the session record-type wind turbine cache data, a time distance coefficient is calculated based on the time difference between the time the data was generated and the time the fault occurred. An access popularity coefficient is calculated based on the number of times the data was accessed within a unit of time before the fault occurred. Based on the time distance coefficient, the fault weight base, and the access popularity coefficient, the comprehensive retention weight of the log-type wind turbine cache data or the session record-type wind turbine cache data is calculated. A preset retention weight is assigned to the temporary file type wind turbine cache data generated based on fault detection, and the comprehensive retention weight of the temporary file type wind turbine cache data is calculated based on the preset retention weight and the fault weight base.
[0013] According to one aspect of the present invention, a multi-granularity cache automatic clearing system for wind turbine AI assistants is proposed, comprising the following modules according to any one of the first aspects: The strategy specification and sorting module is configured to store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priorities are specified according to the different sources and types of cache data. The clearing process startup module is configured to clear the wind turbine cache data when the local storage usage exceeds a certain threshold or when a daily scheduled clearing task is triggered. The time difference calculation module is configured to traverse the wind turbine cache data according to the clearing priority and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data. The clearing process completion module is configured to perform physical deletion if the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, update the storage utilization rate after deletion, and terminate the wind turbine cache data clearing process in advance if it drops below a certain threshold.
[0014] According to one aspect of the present invention, a computer program product is provided having a computer program stored thereon, which, when executed by a processor, performs the method as described in the first aspect.
[0015] The advantages of this invention are: Enables fine-grained cache management by project, device, data type, and other dimensions; Ensure the long-term retention of high-value fault knowledge and prevent the accidental deletion of critical data; Effectively frees up storage resources occupied by invalid data, extending the lifespan of the terminal; The cleanup is completed seamlessly for users, improving system stability and user experience consistency. Attached Figure Description
[0016] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments and, together with the description, serve to explain the principles of the invention. Other embodiments and many anticipated advantages of the embodiments will be readily recognized as they become better understood through reference to the following detailed description. Elements in the drawings are not necessarily to scale. The same reference numerals refer to corresponding similar parts.
[0017] Figure 1 A flowchart illustrating an automatic clearing method for multi-granularity caches in a wind turbine AI assistant according to the present invention is shown. Figure 2 A schematic diagram of a multi-granularity cache automatic clearing system for a wind turbine AI assistant according to the present invention is shown. Figure 3 A schematic diagram of a computer system architecture suitable for implementing the embodiments of this application is shown. Detailed Implementation
[0018] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.
[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0020] Figure 1 A multi-granularity cache automatic clearing method for wind turbine AI assistants is shown, including the following steps: S1, store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priority are specified according to the different sources and types of cache data. S2, when the local storage usage exceeds a certain threshold or triggers the daily scheduled clearing task, the wind turbine cache data clearing process is carried out; S3, traverse the wind turbine cache data according to the clearing priority, and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data; S4. If the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, physical deletion is performed. After deletion, the storage utilization rate is updated. If it drops below a certain threshold, the wind turbine cache data clearing process is terminated in advance.
[0021] This invention provides a multi-granularity cache automatic clearing method, including: tagging cached data with multi-dimensional tags, including project ID, device model, data type (knowledge base / session record / temporary file), creation time, and access frequency; pre-setting retention policies for each granularity level (e.g., "fault cases of project A are permanently retained, and session records are retained for 30 days"); when the storage space is below a threshold or when a timed trigger occurs, scanning is performed level by level from low to high priority, and selective clearing is performed according to the tag matching strategy.
[0022] In a specific implementation, each piece of cached data is appended with the following multidimensional tags when it is entered into the database: data_type: The type, which is an enumeration value; create_time: Creation timestamp; last_access: last access time; retain_policy: Retain policy ID (inherits the default value of data_type).
[0023] In a specific embodiment, the data type of the wind turbine cache data includes knowledge case, chat session, temp file, and log; the sources of the wind turbine cache data include expert review and automatic extraction.
[0024] In specific embodiments, the following types of strategy templates are pre-defined: P1 (Permanent Retention): data_type = “knowledge_case” and source = “expert review”; P2 (retained for 365 days): data_type = “knowledge_case” and source = “auto-extracted”; P3 (retained for 30 days): data_type = “chat_session”; P4 (Deleted upon session end): data_type = “temp_file”; P5 (retain for 90 days): data_type = "log".
[0025] Specifically, the priority order for clearing files, from highest to lowest, is: temporary files, session records, logs, knowledge bases that are automatically extracted, and knowledge bases that are reviewed by experts.
[0026] In one embodiment, the multidimensional tag also includes S5, wherein the multidimensional tag further includes the project ID and device model of the wind turbine, namely, project_id represents the unique code of the wind farm project to which it belongs, and device_model represents the associated wind turbine model (such as GW155-4.5).
[0027] The system monitors the operating status of the corresponding wind turbines in real time. When a fault is detected, the system identifies and stores the relevant wind turbine cache data. Specifically, a "fault isolation" flag field is added to the cache index table for the fault-related data. The fault-related data is then migrated from the main cache area to an independent fault isolation cache area. This area uses an independent storage path, and a mapping table is established to record the relationship between the original path and the isolation path. After migration, the space in the original location can be released or overwritten, but the index table points to the new location, ensuring that the fault-related data is stored in the isolation path. This data is specifically used for fault analysis, troubleshooting, and case alerts, and does not participate in the regular clearing process in S4. A temporary retention strategy and temporary clearing priority order for the fault-related wind turbine cache data are specified based on the severity level of the wind turbine's fault.
[0028] Specifically, specifying the temporary retention strategy and temporary clearing priority ranking of the fault-related wind turbine cache data based on the fault severity level of the wind turbine includes: obtaining the fault severity level of the wind turbine; determining the fault weight base number based on the fault severity level; for different types of fault-related wind turbine cache data, adopting the corresponding comprehensive retention weight calculation method based on the fault weight base number; specifying the corresponding temporary retention strategy for the fault-related wind turbine cache data according to the numerical range of the comprehensive retention weight of each fault-related wind turbine cache data; and sorting the fault-related wind turbine cache data in descending order according to the value of the comprehensive retention weight to generate the temporary clearing priority ranking.
[0029] It is understood that, in specific embodiments, the data range within which the corresponding temporary retention strategy for the fault-related wind turbine cache data is specified based on the numerical range of the comprehensive retention weight of each fault-related wind turbine cache data can be adjusted according to actual needs.
[0030] Specifically, obtaining fault-related wind turbine cache data includes: matching and filtering according to the fault type of the wind turbine to obtain knowledge base type wind turbine cache data corresponding to the fault type; filtering log type wind turbine cache data or session record type wind turbine cache data based on time range; and obtaining temporary file type wind turbine cache data generated based on fault detection.
[0031] Specifically, the system performs matching and filtering based on the fault type of the wind turbine. A fault data knowledge base-tag mapping table is pre-built, associating each fault type with a set of knowledge tags. For example, when the wind turbine experiences excessive vibration, possible associated knowledge tags include blade imbalance, tower resonance, bearing wear, loose bolts, etc. The knowledge base type data pre-stores the corresponding field tags, and performs fuzzy matching with the corresponding fault type. The type matching degree coefficient can be calculated using the Jaccard similarity coefficient. When the matching degree is greater than a certain threshold, the wind turbine cache data corresponding to the knowledge base type of the fault type is selected.
[0032] Define a pre-fault tracing window and a post-fault persistence window. The window length is dynamically set according to the fault type to filter the wind turbine cache data of log type or session record type generated during the fault occurrence and troubleshooting.
[0033] In a specific embodiment, the step of calculating the corresponding comprehensive retention weight based on the fault weight base for different types of fault-related wind turbine cache data specifically includes: For the knowledge base type wind turbine cache data: A type matching coefficient is calculated based on the fault type, and a comprehensive retention weight is calculated based on the type matching coefficient, the fault weight base, and the time-related decay coefficient. The time-related decay coefficient is calculated based on the time difference between the creation time of the knowledge base type wind turbine cache data and the current time; the larger the time difference, the smaller the time-related decay coefficient.
[0034] For the log-type wind turbine cache data or session record-type wind turbine cache data: calculate the time distance coefficient based on the time difference between the data generation time and the fault occurrence time, and calculate the comprehensive retention weight of the log-type wind turbine cache data or session record-type wind turbine cache data based on the time distance coefficient, the fault weight base and the access heat coefficient. The access heat coefficient is calculated based on the number of times the data was accessed within a unit of time before the fault occurred. The more times it is accessed, the larger the access heat coefficient is.
[0035] A preset retention weight is assigned to the temporary file type wind turbine cache data generated based on fault detection, and the comprehensive retention weight of the temporary file type wind turbine cache data is calculated based on the preset retention weight and the fault weight base.
[0036] It is understood that, in specific embodiments, the specific formulas or values for fault weight base, time decay coefficient, time distance coefficient, access popularity coefficient, and preset retention weight can be set according to actual needs.
[0037] According to one aspect of the present invention, a multi-granularity cache automatic clearing system for wind turbine AI assistants is proposed, comprising the following modules according to any one of the first aspects: The strategy specification and sorting module 201 is configured to store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priorities are specified according to the different sources and types of cache data. The clearing process initiation module 202 is configured to perform a wind turbine cache data clearing process when the local storage usage exceeds a certain threshold or a daily scheduled clearing task is triggered. The time difference calculation module 203 is configured to traverse the wind turbine cache data according to the clearing priority and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data; The clearing process completion module 204 is configured to perform physical deletion if the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, update the storage utilization rate after deletion, and terminate the wind turbine cache data clearing process in advance if it drops below a certain threshold.
[0038] The following is for reference. Figure 3 It shows a schematic diagram of the structure of a computer system 300 suitable for implementing electronic devices according to embodiments of the present application. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0039] like Figure 3As shown, the computer system 300 includes a central processing unit (CPU) 301, which performs various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 309 into random access memory (RAM) 304. The RAM 304 also stores various programs and data required for the operation of the system 300. The CPU 301, ROM 302, ROM 303, and RAM 304 are interconnected via a bus 305. An input / output (I / O) interface 306 is also connected to the bus 305.
[0040] The following components are connected to I / O interface 306: an input section 307 including a keyboard, mouse, etc.; an output section 308 including a liquid crystal display (LCD) and speakers, etc.; a storage section 309 including a hard disk, etc.; and a communication section 310 including a network interface card such as a LAN card and a modem, etc. The communication section 310 performs communication processing via a network such as the Internet. A drive 311 is also connected to I / O interface 306 as needed. A removable medium 312, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 311 as needed so that computer programs read from it can be installed into storage section 309 as needed.
[0041] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts are implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program is downloaded and installed from a network via communication section 310, and / or installed from removable medium 312. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the methods of this application.
[0042] It should be noted that the computer-readable storage medium of this application is a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium is, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium is any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium includes a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium or any computer-readable storage medium other than a computer-readable storage medium may transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wireless, wireline, optical fiber, RF, etc., or any suitable combination thereof.
[0043] Computer program code for performing the operations of this application is written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code executes entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer is connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or connected to an external computer (e.g., via the Internet using an Internet service provider).
[0044] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram represents a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually execute substantially in parallel, and they may sometimes execute in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, is implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0045] The modules described in the embodiments of this application are implemented in software or hardware.
[0046] In another aspect, this application also provides a computer-readable storage medium included in the electronic device described in the above embodiments; it also exists independently and is not assembled into the electronic device. The computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: S1, store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags, the multi-dimensional tags including at least the type, source, creation timestamp, and last access time of the wind turbine cache data, specifying different retention strategies and clearing priority sorting according to different sources and types of cache data; S2, when the local storage utilization rate exceeds a certain threshold or a daily scheduled clearing task is triggered, perform a wind turbine cache data clearing process; S3, traverse the wind turbine cache data according to the clearing priority sorting, and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data; S4, if the time difference exceeds the specified time limit of the retention strategy corresponding to the wind turbine cache data, perform physical deletion, update the storage utilization rate after deletion, and if it drops below a certain threshold, terminate the wind turbine cache data clearing process early.
[0047] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. A method for automatic clearing of multi-granularity cache for wind turbine AI assistants, characterized in that, Includes the following steps: S1, store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priority are specified according to the different sources and types of cache data. S2, when the local storage usage exceeds a certain threshold or triggers the daily scheduled clearing task, the wind turbine cache data clearing process is carried out; S3, traverse the wind turbine cache data according to the clearing priority, and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data; S4. If the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, physical deletion is performed. After deletion, the storage utilization rate is updated. If it drops below a certain threshold, the wind turbine cache data clearing process is terminated in advance.
2. The multi-granularity cache automatic clearing method for a wind turbine AI assistant according to claim 1, characterized in that, The types of wind turbine cached data include knowledge bases, session records, temporary files, and logs; the sources of the wind turbine cached data include expert review and automatic extraction.
3. The multi-granularity cache automatic clearing method for a wind turbine AI assistant according to claim 2, characterized in that, When the type of the wind turbine cache data is a knowledge base and the source is expert review, the wind turbine cache data is subject to a permanent retention strategy. When the type of the wind turbine cache data is a knowledge base and the source is automatic extraction, the wind turbine cache data is subject to a 365-day retention policy. When the type of the wind turbine cache data is session record, the wind turbine cache data is subject to a 30-day retention policy; When the type of the wind turbine cache data is a temporary file, the wind turbine cache data is subject to a session-end deletion retention policy; When the type of the wind turbine cache data is log, the wind turbine cache data is subject to a 90-day retention policy.
4. The multi-granularity cache automatic clearing method for a wind turbine AI assistant according to claim 2, characterized in that, The priority order for clearing files, from highest to lowest, is: temporary files, session records, logs, knowledge bases that are automatically extracted, and knowledge bases that are reviewed by experts.
5. The method for automatic clearing of multi-granularity cache for wind turbine AI assistants according to claim 1, characterized in that, It also includes S5, where the multidimensional tag also includes the project ID and equipment model of the wind turbine, monitors the operating status of the wind turbine in real time, identifies and stores the wind turbine cache data related to the fault separately when the wind turbine is detected to have a fault, and specifies the temporary retention strategy and temporary clearing priority sorting of the wind turbine cache data related to the fault according to the fault severity level of the wind turbine.
6. The multi-granularity cache automatic clearing method for a wind turbine AI assistant according to claim 5, characterized in that, Specifying a temporary retention strategy and temporary clearing priority ranking for the fault-related wind turbine cache data based on the fault severity level of the wind turbine specifically includes: obtaining the fault severity level of the wind turbine; determining a fault weight base number based on the fault severity level; for different types of fault-related wind turbine cache data, using a corresponding comprehensive retention weight calculation method based on the fault weight base number; specifying a corresponding temporary retention strategy for the fault-related wind turbine cache data according to the numerical range of the comprehensive retention weight of each fault-related wind turbine cache data; and sorting the fault-related wind turbine cache data in descending order according to the numerical value of the comprehensive retention weight to generate the temporary clearing priority ranking.
7. The method for automatic clearing of multi-granularity cache for wind turbine AI assistants according to claim 6, characterized in that, The specific steps for obtaining fault-related wind turbine cache data include: matching and filtering according to the fault type of the wind turbine to obtain knowledge base type wind turbine cache data corresponding to the fault type; filtering log type wind turbine cache data or session record type wind turbine cache data based on the time range; and obtaining temporary file type wind turbine cache data generated based on fault detection.
8. The method for automatic clearing of multi-granularity cache for wind turbine AI assistants according to claim 7, characterized in that, The specific method for calculating the comprehensive retention weight based on the fault weight base for different types of fault-related wind turbine cache data includes: For the knowledge base type wind turbine cache data, calculate the type matching degree coefficient of the knowledge base type wind turbine cache data according to the fault type, calculate the time decay coefficient according to the time difference between the creation time of the knowledge base type wind turbine cache data and the current time, and calculate the comprehensive retention weight of the knowledge base type wind turbine cache data based on the type matching degree coefficient, the fault weight base and the time decay coefficient. For the log-type wind turbine cache data or the session record-type wind turbine cache data, a time distance coefficient is calculated based on the time difference between the time the data was generated and the time the fault occurred. An access popularity coefficient is calculated based on the number of times the data was accessed within a unit of time before the fault occurred. Based on the time distance coefficient, the fault weight base, and the access popularity coefficient, the comprehensive retention weight of the log-type wind turbine cache data or the session record-type wind turbine cache data is calculated. A preset retention weight is assigned to the temporary file type wind turbine cache data generated based on fault detection, and the comprehensive retention weight of the temporary file type wind turbine cache data is calculated based on the preset retention weight and the fault weight base.
9. A multi-granularity cache automatic clearing system for wind turbine AI assistants, characterized in that, The method according to any one of claims 1 to 8 comprises the following modules: The strategy specification and sorting module is configured to store wind turbine cache data and label the wind turbine cache data with multi-dimensional tags. The multi-dimensional tags include at least the type, source, creation timestamp and last access time of the wind turbine cache data. Different retention strategies and clearing priorities are specified according to the different sources and types of cache data. The clearing process startup module is configured to clear the wind turbine cache data when the local storage usage exceeds a certain threshold or when a daily scheduled clearing task is triggered. The time difference calculation module is configured to traverse the wind turbine cache data according to the clearing priority and calculate the time difference between the current time and the creation timestamp or last access time of the wind turbine cache data. The clearing process completion module is configured to perform physical deletion if the time difference exceeds the specified time limit of the retention policy corresponding to the wind turbine cache data, update the storage utilization rate after deletion, and terminate the wind turbine cache data clearing process in advance if it drops below a certain threshold.
10. A computer program product, characterized in that, It stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-8.