Information processing method and device

Abstract

The embodiment of the invention provides an information processing method and device, and the method comprises the steps: collecting basic information of a resource scheduling system corresponding to a plurality of information dimensions, carrying out the preprocessing of the basic information of the plurality of information dimensions, and obtaining the standard information of the plurality of information dimensions; in response to an exception detection request submitted for the standard information of the multiple information dimensions, screening exception information from the standard information of the multiple information dimensions; querying a knowledge base associated with the resource scheduling system through the exception information, and determining an exception repair strategy; and calling a decision execution sub-module to execute an operation and maintenance instruction corresponding to the exception repair strategy, wherein the operation and maintenance instruction is used for repairing a system fault of the resource scheduling system associated with the exception information.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of information processing, and in particular, to an information processing method and device. BACKGROUND

[0002] With the development of the Internet and computer technology, digital factory construction has become a trend. By using an AGVS (Automated Guided Vehicle System) system to realize scheduling control of an AGV (Automated Guided Vehicle) trolley, the AGV trolley can automatically perform a work task, greatly improving production efficiency and saving personnel costs. As a very important production component of a factory, the AGVS system will cause a production line to be unable to supply materials in time if a system fault occurs, thereby affecting the production progress of the factory. Therefore, the operation and maintenance of the AGVS system requires a very high level. In the prior art, in order to ensure that the AGVS system can operate normally, a monitoring tool is usually used to collect various indicators and operating states of the system to monitor the system operating state, and an operation and maintenance personnel is used to quickly remove the fault by maintenance. However, this process requires a high level of professionalism of the operation and maintenance personnel, and the fault repair efficiency is low, so an effective solution is urgently needed to solve the above problems. SUMMARY

[0003] Therefore, an information processing method is provided in the embodiments of the present specification. One or more embodiments of the present specification also relate to an information processing device, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects in the prior art.

[0004] According to a first aspect of an embodiment of the present specification, an information processing method is provided, including:

[0005] Collecting basic information of a plurality of information dimensions corresponding to a resource scheduling system, and pre-processing the basic information of the plurality of information dimensions to obtain standard information of the plurality of information dimensions;

[0006] In response to an exception detection request submitted for the standard information of the plurality of information dimensions, screening abnormal information in the standard information of the plurality of information dimensions;

[0007] Querying a knowledge base associated with the resource scheduling system through the abnormal information to determine an exception repair strategy;

[0008] Calling a decision execution submodule to execute an operation and maintenance instruction corresponding to the exception repair strategy, for repairing a system fault associated with the abnormal information of the resource scheduling system.

[0009] Optionally, the collection resource scheduling system corresponds to a plurality of information dimensions of basic information, including:

[0010] In the message queue system log corresponding to the resource scheduling system, the first basic information corresponding to the first information dimension is obtained, the second basic information corresponding to the second information dimension of the message queue system is obtained in the message queue system log, the third basic information corresponding to the third information dimension is obtained in the resource scheduling system log corresponding to the resource scheduling system, the fourth basic information corresponding to the fourth information dimension is obtained in the database corresponding to the resource scheduling system, and the fifth basic information corresponding to the fifth information dimension is obtained in the system server corresponding to the resource scheduling system.

[0011] The first basic information of the first information dimension, the second basic information of the second information dimension, the third basic information of the third information dimension, the fourth basic information of the fourth information dimension and the fifth basic information of the fifth information dimension are used as the basic information of a plurality of information dimensions.

[0012] Optionally, the basic information of the plurality of information dimensions is preprocessed to obtain standard information of a plurality of information dimensions, including:

[0013] The basic information of the plurality of information dimensions is preprocessed according to a preset information processing rule;

[0014] According to the preprocessing result, the standard information of a plurality of information dimensions is generated, wherein the information format of the standard information corresponding to each information dimension is the same.

[0015] Optionally, before the step of screening abnormal information in the standard information of the plurality of information dimensions in response to the abnormal detection request submitted for the standard information of the plurality of information dimensions, it further includes:

[0016] The standard information of the plurality of information dimensions is stored in a system database.

[0017] Wherein, the step of screening abnormal information in the standard information of the plurality of information dimensions in response to the abnormal detection request submitted for the standard information of the plurality of information dimensions, including:

[0018] In response to the abnormal detection request submitted for the system database, the system database is queried according to the query result, and the standard message corresponding to the abnormal type is determined as the abnormal message.

[0019] Optionally, the knowledge base associated with the resource scheduling system is determined by querying the abnormal information to determine the abnormal repair strategy, including:

[0020] query a knowledge base associated with the resource scheduling system based on the abnormal information, obtain an initial abnormal repair strategy according to a query result, and determine a strategy score corresponding to the initial abnormal repair strategy;

[0021] in a case where the strategy score is greater than a score threshold, taking the initial abnormal repair strategy as an abnormal repair strategy;

[0022] in a case where the strategy score is less than or equal to the score threshold, inputting the abnormal information into a repair strategy generation model for processing to obtain a predicted abnormal repair strategy; and in response to a confirmation request submitted for the predicted abnormal repair strategy, taking the predicted abnormal repair strategy as an abnormal repair strategy.

[0023] Optionally, the query of the knowledge base associated with the resource scheduling system based on the abnormal information and the obtaining of the initial abnormal repair strategy according to a query result include:

[0024] determining a knowledge base associated with the resource scheduling system, and determining an information sub-base and a strategy sub-base in the knowledge base;

[0025] calculating an information similarity between the abnormal information and information stored in the information sub-base, and determining target information matched with the abnormal information according to the information similarity;

[0026] querying the strategy sub-base based on an information identifier corresponding to the target information, and obtaining an initial abnormal repair strategy matched with the target information according to a query result.

[0027] Optionally, the inputting of the abnormal information into the repair strategy generation model for processing to obtain the predicted abnormal repair strategy includes:

[0028] obtaining scenario prompt information associated with the resource scheduling system, and updating the abnormal information based on the scenario prompt information;

[0029] inputting the updated abnormal information into the repair strategy generation model for processing to obtain the predicted abnormal repair strategy.

[0030] Optionally, the calling of the decision execution sub-module to execute the operation and maintenance instruction corresponding to the abnormal repair strategy for repairing a system fault associated with the abnormal information in the resource scheduling system further includes:

[0031] in a case where the system fault repair of the resource scheduling system is completed, establishing an information matching relationship between the abnormal repair strategy and the abnormal information;

[0032] storing the abnormal repair strategy and the abnormal information into the knowledge base according to the information matching relationship.

[0033] According to a second aspect of the embodiments of this specification, an information processing apparatus is provided, comprising:

[0034] The data acquisition module is configured to collect basic information corresponding to multiple information dimensions of the resource scheduling system, and to preprocess the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions.

[0035] The filtering module is configured to filter out abnormal information from the standard information in the multiple information dimensions in response to an anomaly detection request submitted for standard information in the multiple information dimensions.

[0036] The determination module is configured to query the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy.

[0037] The repair module is configured to call the decision execution submodule to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, in order to repair system faults associated with the anomaly information in the resource scheduling system.

[0038] According to a third aspect of the embodiments of this specification, a computing device is provided, comprising:

[0039] Memory and processor;

[0040] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the above-described information processing method.

[0041] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the information processing method described above.

[0042] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program or instructions that, when executed by a processor, implement the steps of the information processing method described above.

[0043] The information processing method provided in this embodiment, in order to quickly locate problems in the resource scheduling system and automatically repair system faults, can first collect basic information corresponding to multiple information dimensions of the resource scheduling system. At this point, preprocessing can be performed on the basic information of multiple information dimensions to obtain standard information for each dimension. Then, in response to anomaly detection requests submitted for the standard information of multiple information dimensions, anomaly information can be filtered from the standard information of multiple information dimensions. To improve the efficiency of system fault repair, anomaly information can be queried against the knowledge base of the associated resource scheduling system to determine anomaly repair strategies. After identifying anomaly information, the knowledge base can be used to match the repair plan for the corresponding system fault. This allows the decision execution submodule to be invoked to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, thereby completing the repair of system faults associated with the anomaly information in the resource scheduling system. When detecting the resource scheduling system, the method can combine basic information of multiple information dimensions to locate system faults, match corresponding repair plans through information processing, and automatically execute operation and maintenance instructions by invoking the decision execution submodule. This allows for rapid and efficient system fault repair, saving significant manpower while ensuring the resource scheduling system can provide stable service. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of an information processing method provided in one embodiment of this specification;

[0045] Figure 2 This is a flowchart illustrating an information processing method provided in one embodiment of this specification;

[0046] Figure 3 This is a schematic diagram of the structure of an information processing device provided in one embodiment of this specification;

[0047] Figure 4 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0048] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0049] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a,” “described,” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0050] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0051] Furthermore, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0052] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0053] AGVS (Automated Guided Vehicle System) is an automated logistics solution integrating multiple advanced technologies. This system uses battery-powered, driverless transport vehicles to automate the handling, loading, unloading, and transportation of goods, significantly improving the efficiency and flexibility of material handling.

[0054] AGV (Automated Guided Vehicle) is an intelligent transportation tool widely used in modern industry.

[0055] MQTT (Message Queuing Telemetry Transport) is an instant messaging protocol. MQTT was designed for communication between a large number of remote sensors and control devices operating on low-bandwidth, unreliable, or high-latency networks with limited computing power.

[0056] This specification provides an information processing method, and also relates to an information processing apparatus, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail in the following embodiments.

[0057] In practical applications, the AGVS system architecture is quite complex, involving both software and hardware components, and relying on numerous system components, including AGV vehicles, MQTT, the AGVS system itself, databases, and network devices. A problem in any one of these components can render the entire system unusable. Currently, system maintenance primarily relies on monitoring tools to track various system metrics and operational statuses, such as server health, network health, AGVS system performance indicators, and database status. When system problems arise, maintenance personnel can quickly locate and identify the issue using these tools, then analyze and resolve it based on their experience. However, this approach is limited by the individual capabilities of the maintenance personnel. While highly skilled personnel can quickly resolve issues, those with limited expertise may be unable to address problems promptly, impacting production line operations. Therefore, an effective solution is urgently needed to address these issues.

[0058] See Figure 1The schematic diagram illustrates the information processing method provided in this embodiment. To quickly locate problems in the resource scheduling system and automatically repair system faults, it first collects basic information corresponding to multiple information dimensions of the resource scheduling system. This basic information is then preprocessed to obtain standard information for each dimension. Subsequently, in response to anomaly detection requests submitted for the standard information across multiple dimensions, anomalies are filtered from the standard information. To improve system fault repair efficiency, anomaly repair strategies are determined by querying the knowledge base associated with the resource scheduling system using the anomaly information. After identifying the anomaly information, a repair plan for the corresponding system fault is matched using the knowledge base. This allows the decision execution submodule to be invoked to execute the corresponding maintenance instructions for the anomaly repair strategy, thus repairing the system fault associated with the anomaly information in the resource scheduling system. By combining basic information from multiple information dimensions to locate system faults during resource scheduling system detection, matching corresponding repair plans through information processing, and automatically executing maintenance instructions by invoking the decision execution submodule, system fault repair can be completed quickly and efficiently, saving significant manpower while ensuring the resource scheduling system provides stable service.

[0059] See Figure 2 , Figure 2 A flowchart of an information processing method according to an embodiment of this specification is shown, which specifically includes the following steps.

[0060] Step S202: Collect basic information corresponding to multiple information dimensions of the resource scheduling system, and preprocess the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions.

[0061] The information processing method provided in this embodiment is applied to the operation and maintenance scenario of an AGVS system for scheduling AGV vehicles within a factory. Specifically, the resource scheduling system is the AGVS system; correspondingly, the basic information of multiple information dimensions refers to the system information monitored by the resource scheduling system in different information dimensions, including but not limited to AGV information, MQTT information, AGVS system information, database information, and basic equipment information, etc., which are not limited in this embodiment. Correspondingly, preprocessing specifically refers to the process of standardizing the basic information of each information dimension to obtain standard information with the same information format for each information dimension, wherein the standard information is the information structure obtained after standardizing the basic information.

[0062] Based on this, in order to quickly locate problems in the resource scheduling system and automatically repair system faults, basic information corresponding to multiple information dimensions of the resource scheduling system can be collected first. At this time, the basic information of multiple information dimensions can be preprocessed to obtain standard information for multiple information dimensions. Then, in response to the anomaly detection request submitted for the standard information of multiple information dimensions, anomaly information can be filtered from the standard information of multiple information dimensions. In order to improve the efficiency of system fault repair, the knowledge base associated with the resource scheduling system can be queried through the anomaly information to determine the anomaly repair strategy. After the anomaly information is determined, the repair plan corresponding to the system fault can be matched with the anomaly information in the knowledge base. This allows the decision execution submodule to be called to execute the operation and maintenance instructions corresponding to the anomaly repair strategy to complete the repair of the system fault associated with the anomaly information of the resource scheduling system.

[0063] In one optional embodiment of this specification, the resource collection and scheduling system corresponds to basic information across multiple information dimensions, including:

[0064] Obtain the first basic information corresponding to the first information dimension from the message queue system log corresponding to the resource scheduling system; obtain the second basic information corresponding to the second information dimension from the message queue system log; obtain the third basic information corresponding to the third information dimension from the resource scheduling system log corresponding to the resource scheduling system; obtain the fourth basic information corresponding to the fourth information dimension from the database corresponding to the resource scheduling system; and obtain the fifth basic information corresponding to the fifth information dimension from the system server corresponding to the resource scheduling system. Use the first basic information of the first information dimension, the second basic information of the second information dimension, the third basic information of the third information dimension, the fourth basic information of the fourth information dimension, and the fifth basic information of the fifth information dimension as the basic information of multiple information dimensions.

[0065] Specifically, the message queue system log refers to the system log corresponding to the message queue system of the associated resource management system, i.e., the MQTT system log; the first information dimension is the dimension of AGV information in the associated MQTT system log, and the first basic information specifically refers to AGV information; correspondingly, the second information dimension refers to the dimension associated with MQTT, and the second basic information specifically refers to MQTT information; correspondingly, the third information dimension refers to the dimension associated with the AGVS system, and the third basic information specifically refers to AGVS information; the fourth information dimension refers to the dimension associated with the database, and the fourth basic information specifically refers to database information; the fifth information dimension refers to the dimension associated with infrastructure information, and the fifth basic information specifically refers to infrastructure information.

[0066] Based on this, considering that the resource scheduling system includes both hardware and software components, and the causes of system failures are potentially more diverse, to ensure accurate fault location before subsequent automated system fault repair, anomaly information can be filtered by collecting multi-dimensional information. Specifically, information collection involves retrieving the first basic information corresponding to the first information dimension from the message queue system logs of the resource scheduling system; the second basic information corresponding to the second information dimension from the message queue system logs; the third basic information corresponding to the third information dimension from the resource scheduling system logs; the fourth basic information corresponding to the fourth information dimension from the database of the resource scheduling system; and the fifth basic information corresponding to the fifth information dimension from the system server of the resource scheduling system. This allows the first basic information of the first information dimension, the second basic information of the second information dimension, the third basic information of the third information dimension, the fourth basic information of the fourth information dimension, and the fifth basic information of the fifth information dimension to serve as the basic information for multiple information dimensions, for subsequent use.

[0067] In practical applications, when collecting information from an AGVS system, information such as AGV information, MQTT information, AGVS information, database information, and infrastructure information can be collected.

[0068] AGV information can be collected by monitoring the MQTT system logs to obtain connection monitoring status information between the AGV and MQTT, as well as abnormal information reported by the AGV. MQTT, as a message middleware, is used for communication and interaction between the AGV and AGVS. Therefore, AGV information is first reported to the MQTT middleware and then pushed to the AGVS. Thus, the MQTT middleware records all AGV information and the connection monitoring status between the AGV and MQTT.

[0069] MQTT information can be collected by collecting MQTT system logs, which can be used to obtain MQTT health status, message reception time, message push time, message logs, etc.

[0070] AGVS information can be collected by collecting AGVS system logs, which can reveal AGVS interface call information, business exception information, and so on.

[0071] Database information can be collected by executing SQL query commands to obtain information such as database health status, tablespace size, whether there are deadlocks, and SQL execution time.

[0072] Infrastructure information can be collected through Prometheus, including CPU usage, memory usage, disk usage, network throughput, network packet loss rate, and TCP / IP three-way handshake status.

[0073] In summary, by collecting basic information from multiple dimensions for subsequent system testing, we can more accurately locate the fault in the event of a system failure, thereby enabling rapid system repair and ensuring the system can operate normally and provide stable system services.

[0074] In one optional embodiment of this specification, the preprocessing of the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions includes:

[0075] The basic information of the multiple information dimensions is preprocessed according to the preset information processing rules; standard information of multiple information dimensions is generated based on the preprocessing results, wherein the information format of the standard information corresponding to each information dimension is the same.

[0076] Specifically, information processing rules refer to the rules for preprocessing the basic information corresponding to multiple information dimensions collected, used to process the basic information corresponding to multiple information dimensions into standard information with the same information format. Based on this, after obtaining the basic information corresponding to multiple information dimensions, the basic information of multiple information dimensions can be preprocessed according to the preset information processing rules; thus, standard information of multiple information dimensions can be generated based on the preprocessing results, and the information format of the standard information corresponding to each information dimension is the same.

[0077] In practical applications, when preprocessing the collected AGV information, MQTT information, AGVS information, database information, and infrastructure information, the information can be converted into a unified standard information format. This unified format can use JSON data, as follows:

[0078] {

[0079] "topic":"",

[0080] "type":"",

[0081] "starttime":"",

[0082] "msg",""

[0083] }

[0084] Here, `topic` represents the type of information, represented by an `int`. For example, `[1, 10]` represents AGV information, where 1 represents the AGV's connection status with MQTT, and 2 represents AGV reported exceptions. `[11, 20]` represents MQTT information, where 11 represents MQTT health status, and 12 represents MQTT timeout. `[21, 100]` represents AGVS information, where 21 represents SAP interface information, and 22 represents MQTT interface exceptions. `[101, 130]` represents database information, where 101 represents SQL execution timeout, and 102 represents deadlock. `[131, 160]` represents infrastructure information, such as 131 representing CPU utilization and 132 representing memory utilization. `type` represents the type of information exception, including `info`, `warning`, and `error`, where `info` represents normal, `warning` represents an alarm, and `error` represents a fault. `starttime` represents the time the information occurred. `msg` represents the information content.

[0085] Furthermore, the information processing rules make logical judgments based on the type of collected information and convert the information into the aforementioned standard information format. When setting information processing rules, the following rules can be included based on the information type:

[0086] 1. AGV information processing rules: (1) Parse the health status information of the AGV and MQTT connection, and obtain the connection disconnection information. When the connection disconnection time is >5s, the exception type is error; when 5s ≥ connection disconnection time > 0s, the exception type is warning; when the connection disconnection time = 0s, the exception type is info. (2) Parse the exception information reported by the AGV. The exception type is error.

[0087] 2. MQTT message processing rules: (1) Parse the MQTT message receiving time t1 and the MQTT push hour time t2. If t2-t1>5s, the exception type is error; if 5s≥t2-t1>2s, the exception type is warning; otherwise, the exception type is info. (2) Parse the MQTT health status. If the status is healthy, the exception type is info; if the status is abnormal, the exception type is error.

[0088] 3. AGVS Information Processing Rules: (1) Parse the interface information. If the interface call fails, the exception type is error. If the call succeeds, the exception type is info. (2) Parse the business logs and obtain the business exception status. If the status is abnormal, the exception type is error. If the status is normal, the exception type is info.

[0089] 4. Database information processing rules: (1) Parse deadlock information. If the deadlock time is >60s, the exception type is error. If 60s ≥ deadlock time > 10s, the exception type is warning. Otherwise, the exception type is info. (2) Parse SQL execution information to obtain SQL execution time and SQL execution result. If the SQL execution time is >30s, the exception type is error. If 30s ≥ t2-t1 > 10s, the exception type is warning. Otherwise, the exception type is info.

[0090] 5. Infrastructure information processing rules: (1) Parse CPU utilization information. If CPU utilization > 90%, the exception type is error; if 90% ≥ CPU utilization > 70%, the exception type is warning; otherwise, the exception type is info. (2) Parse memory utilization information. If memory utilization > 95%, the exception type is error; if 95% ≥ CPU utilization > 80%, the exception type is warning; otherwise, the exception type is info.

[0091] In practice, the information processing rules can be adjusted according to actual needs, and this embodiment does not impose any limitations.

[0092] In summary, by pre-setting information processing rules and pre-processing basic information according to the information processing rules corresponding to different dimensions of information, standard information with the same format can be obtained. This allows for subsequent screening of abnormal information based on the standard information, thereby matching the corresponding repair solutions and quickly completing system fault repair.

[0093] Step S204: In response to the anomaly detection request submitted for the standard information of the multiple information dimensions, filter out the abnormal information from the standard information of the multiple information dimensions.

[0094] Specifically, after obtaining standard information from multiple information dimensions, if an anomaly detection request is received for the standard information from multiple information dimensions, the anomaly information can be filtered from the multiple standard information based on the anomaly detection request. This allows for subsequent matching strategies through information processing, thereby completing system fault repair and reducing the consumption of human resources.

[0095] Specifically, an anomaly detection request refers to a request submitted when performing anomaly detection on the resource scheduling system. This request can be triggered at a preset time or submitted by operations and maintenance personnel. Correspondingly, anomaly information refers to standard information that filters out anomaly types from standard information corresponding to multiple information dimensions. This information can characterize the current system failure.

[0096] In an optional embodiment of this specification, before the step of filtering out abnormal information from the standard information of the multiple information dimensions in response to an anomaly detection request submitted for the standard information of the multiple information dimensions is performed, the method further includes:

[0097] The standard information of the multiple information dimensions is stored in the system database; wherein, in response to the anomaly detection request submitted for the standard information of the multiple information dimensions, the anomaly information is filtered from the standard information of the multiple information dimensions, including: in response to the anomaly detection request submitted for the system database, querying the system database, and determining the standard message of the corresponding anomaly type as the anomaly message based on the query result.

[0098] Specifically, the system database refers to a database that stores standard information, which is used to persist standardized information before fault detection in the resource scheduling system. Based on this, after obtaining standard information corresponding to multiple information dimensions, the standard information for multiple information dimensions can be stored in the system database. This allows the system database to be queried in response to anomaly detection requests submitted to it, and the standard message corresponding to the anomaly type can be determined as the anomaly message based on the query results, so as to facilitate subsequent fault location and repair.

[0099] In practical applications, the system database can be a relational database, and the database table structure can include id, primary key, topic, message type, starttime, message occurrence time, msg, message content, etc. This embodiment does not impose any limitations.

[0100] In summary, by storing information in a database, it is more convenient to complete system fault repair when a detection request is triggered at any time, thereby improving the flexibility of system operation and maintenance.

[0101] Step S206: Query the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy.

[0102] Specifically, after identifying the abnormal information, in order to improve the efficiency of system fault repair, a knowledge base can be built in advance for the resource scheduling system, and the abnormal repair strategies matching different abnormal information can be stored in the knowledge base. This allows the abnormal repair strategy matching the abnormal information to be directly determined by querying the knowledge base, thereby completing the system fault repair corresponding to the abnormal information of the resource scheduling system.

[0103] The anomaly repair strategy specifically refers to the strategy for repairing system faults corresponding to abnormal information in the resource scheduling system. Examples include restarting the AGVS system, expanding server resources, resending AGVS interface data, and providing warranty service for AGV hardware. This embodiment does not impose any limitations on this.

[0104] In one optional embodiment of this specification, the step of querying the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy includes:

[0105] Based on the anomaly information, the knowledge base associated with the resource scheduling system is queried. An initial anomaly repair strategy is obtained based on the query results, and a strategy score corresponding to the initial anomaly repair strategy is determined. If the strategy score is greater than a score threshold, the initial anomaly repair strategy is adopted as the anomaly repair strategy. If the strategy score is less than or equal to the score threshold, the anomaly information is input into the repair strategy generation model for processing to obtain a predicted anomaly repair strategy. In response to a confirmation request submitted for the predicted anomaly repair strategy, the predicted anomaly repair strategy is adopted as the anomaly repair strategy.

[0106] Specifically, the initial anomaly repair strategy refers to the anomaly repair strategy retrieved from the knowledge base that matches the anomaly information. Correspondingly, the strategy score refers to the matching score between the anomaly information and the initial anomaly repair strategy. Correspondingly, the score threshold is a set value used to compare strategy scores and determine whether to apply the initial anomaly repair strategy; it can be set according to actual needs, and this embodiment does not impose any limitations. Correspondingly, the repair strategy generation model refers to a large AI model capable of predicting anomaly repair strategies for the resource scheduling system based on the input anomaly information. Correspondingly, the predicted anomaly repair strategy refers to the anomaly repair strategy output by the repair strategy generation model.

[0107] Based on this, after obtaining anomaly information, in order to improve system repair efficiency and reduce the professional requirements of operation and maintenance personnel, the knowledge base of the associated resource scheduling system can be queried based on the anomaly information to obtain an initial anomaly repair strategy based on the query results, and at the same time, the strategy score corresponding to the initial anomaly repair strategy can be determined; then the strategy score can be compared with the score threshold.

[0108] If the strategy score is greater than the score threshold, it means that the initial anomaly repair strategy that matches the anomaly information can complete the repair of the system fault corresponding to the anomaly information. Therefore, the initial anomaly repair strategy can be used as the anomaly repair strategy for subsequent use.

[0109] If the strategy score is less than or equal to the score threshold, it means that the initial anomaly repair strategy matched with the anomaly information cannot repair the system fault corresponding to the anomaly information. In order to repair the system fault corresponding to the anomaly information, a repair strategy corresponding to the system fault needs to be generated. Therefore, the anomaly information can be input into the repair strategy generation model for processing, and a predicted anomaly repair strategy can be obtained based on the model's processing results. This strategy can then be fed back to the operations and maintenance personnel for confirmation, thus responding to the confirmation request submitted for the predicted anomaly repair strategy and using the predicted anomaly repair strategy as the actual anomaly repair strategy for subsequent use.

[0110] In practical applications, after storing standard information in the database, exception information with warning and error types can be retrieved by querying the database. Then, the AGVS knowledge base can be searched based on this exception information to obtain matching solutions (initial exception repair strategy) and search result scores (strategy score). When the search result score is >90, the solution is considered capable of fixing the system fault, and the solution retrieved from the AGVS knowledge base can be transmitted to the decision execution submodule, which automatically performs maintenance and repair based on the solution. When the search result score is ≤90, the solution is considered incapable of fixing the system fault, and the exception information can be input into the AI ​​big data model. The big data model analyzes the information and generates a corresponding solution, which is then transmitted to the decision execution submodule. After obtaining the solution generated by the AI ​​big data model, the decision execution submodule allows maintenance personnel to confirm it and then execute the corresponding maintenance actions to repair the problem.

[0111] In summary, by combining a knowledge base with a large model to determine anomaly repair strategies, it is possible to quickly and accurately identify repair strategies that match anomaly information, thereby effectively improving the efficiency of system fault repair and avoiding impact on business operations.

[0112] In one optional embodiment of this specification, the step of querying the knowledge base associated with the resource scheduling system based on the anomaly information and obtaining an initial anomaly repair strategy based on the query results includes:

[0113] A knowledge base associated with the resource scheduling system is determined, and an information sub-base and a strategy sub-base are determined within the knowledge base; the information similarity between the abnormal information and the information stored in the information sub-base is calculated, and target information matching the abnormal information is determined based on the information similarity; the strategy sub-base is queried based on the information identifier corresponding to the target information, and an initial abnormality repair strategy matching the target information is obtained based on the query result.

[0114] Specifically, the information sub-database refers to a database storing knowledge about anomalies, while the strategy sub-database refers to a database storing solutions for fixing different system faults. Furthermore, the repair strategies stored in the strategy sub-database correspond to the information stored in the information sub-database. Correspondingly, information similarity refers to the degree of similarity between anomaly information and the information stored in the information sub-database. And correspondingly, target information refers to the information in the information sub-database that has the highest similarity to the anomaly information.

[0115] Therefore, in order to quickly complete strategy selection by combining the knowledge base, the knowledge base of the associated resource scheduling system can be determined first in the strategy determination stage, and information sub-bases and strategy sub-bases can be determined in the knowledge base. By calculating the information similarity between the abnormal information and the information stored in the information sub-base, the target information with the highest matching degree with the abnormal information can be selected according to the information similarity. On this basis, the strategy sub-base can be queried based on the information identifier corresponding to the target information, so as to obtain the initial abnormal repair strategy matching the target information according to the query results for subsequent use.

[0116] In practical applications, the AGVS knowledge base can be implemented using Elasticsearch and MySQL. Elasticsearch stores exception information, while MySQL stores corresponding solutions (remediation strategies), and the two are linked by message IDs. The information stored in Elasticsearch aggregates all exception messages with a warning or error status within 1 second based on the `starttime` field, and then uses an IK tokenizer for word segmentation and storage. In practice, considering that the occurrence of one problem may lead to problems in other areas, it is necessary to integrate all possible problems to improve the accuracy of problem analysis.

[0117] Furthermore, when anomaly information is retrieved, a content search is performed using Elasticsearch, and the search results are scored out of 100. Results scoring 90 or higher obtain the corresponding message ID, and a MySQL query is conducted based on this ID to retrieve the relevant solution. These solutions are then output to the decision execution submodule for system fault repair. If the score is below 90, it indicates that the anomaly was not precisely matched, and the AGVS knowledge base lacks a suitable solution, requiring further analysis using a large AI model.

[0118] In summary, by establishing information sub-bases and strategy sub-bases in the knowledge base, and then querying the sub-bases to determine the target information and its matching strategy after identifying abnormal information, the system repair efficiency can be effectively improved.

[0119] In one optional embodiment of this specification, the step of inputting the anomaly information into the repair strategy generation model for processing to obtain a predicted anomaly repair strategy includes:

[0120] Obtain scenario prompt information associated with the resource scheduling system, and update the anomaly information based on the scenario prompt information; input the updated anomaly information into the repair strategy generation model for processing to obtain a predicted anomaly repair strategy.

[0121] Specifically, scenario-based prompts refer to the prompts associated with the resource scheduling system, and these prompts must match the scenario corresponding to the AGVS system. This allows the model to quickly identify the problem and generate a matching remediation strategy. Therefore, when no remediation strategy matching the anomaly information exists in the knowledge base, the model can generate the strategy. Thus, the scenario-based prompts from the associated resource scheduling system can be obtained first, and the anomaly information can be updated based on these prompts. The updated anomaly information is then input into the remediation strategy generation model for processing, and the predicted anomaly remediation strategy can be obtained based on the model's processing results.

[0122] In practical applications, the repair strategy generation model can use Azure OpenAI Service. After obtaining anomaly information, it adds content description enhancements for the AGVS scenario to the original anomaly information to improve the accuracy of the problem description. The enhanced anomaly information is then transmitted to Azure OpenAI Service via API, where Azure OpenAI Service analyzes it and generates corresponding solutions for the decision execution submodule to repair system faults.

[0123] In summary, by fusing anomaly information with scene prompts before model prediction, a more accurate description of the problem can be achieved, enabling the model to provide more accurate anomaly repair strategies and improve the system fault repair effect.

[0124] Step S208: Invoke the decision execution submodule to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, which are used to repair the system faults associated with the anomaly information in the resource scheduling system.

[0125] Specifically, after obtaining the anomaly repair strategy, the decision execution submodule can be invoked to execute the corresponding operation and maintenance instructions to repair system faults associated with the resource scheduling system's anomaly information. These operation and maintenance instructions include, but are not limited to, restarting the system, expanding server resources, resending interface data, hardware warranty service, and notifying operation and maintenance personnel. This embodiment does not impose any limitations.

[0126] In one optional embodiment of this specification, after the step of calling the decision execution submodule to execute the operation and maintenance instructions corresponding to the anomaly repair strategy to repair the system fault associated with the anomaly information in the resource scheduling system is executed, the method further includes:

[0127] When the system fault repair of the resource scheduling system is completed, an information matching relationship is established between the anomaly repair strategy and the anomaly information; the anomaly repair strategy and the anomaly information are stored in the knowledge base according to the information matching relationship.

[0128] Based on this, in order to enable the knowledge base to cover a wider range of scenarios, after the system fault repair of the resource scheduling system is completed, an information matching relationship between the anomaly repair strategy and the anomaly information can be established; and the anomaly repair strategy and the anomaly information can be stored in the knowledge base according to the information matching relationship for use in subsequent system fault repairs.

[0129] In practical applications, after receiving an anomaly repair strategy, the decision execution submodule can determine its source based on the strategy. If the strategy originates from an AI large model, it can be manually confirmed by operations personnel to verify the anomaly content and corresponding solution suggestions before executing the appropriate operations instructions. If the strategy originates from the AGVS knowledge base, it can automatically execute operations instructions based on the solutions provided by the knowledge base.

[0130] Examples of actions include restarting the program, expanding system resources, resending AGVS interface data, reporting AGV hardware malfunctions, and notifying maintenance personnel. This allows the AGVS system to continue controlling the AGVs within the factory, performing material handling operations, such as moving engine parts from shelf A to production line B for assembly. After the decision execution submodule completes the maintenance instructions, if the system returns to normal, the corresponding anomaly information and maintenance repair instructions are updated in the AGVS knowledge base. If the system still has problems, anomaly information is collected and analyzed again until the problem is resolved.

[0131] In summary, to quickly locate problems in the resource scheduling system and automatically repair system faults, we can first collect basic information from multiple information dimensions corresponding to the resource scheduling system. At this stage, we can preprocess this basic information to obtain standard information for each dimension. Then, in response to anomaly detection requests submitted based on the standard information from these dimensions, we can filter for anomalies. To improve system fault repair efficiency, we can query the knowledge base associated with the resource scheduling system to determine anomaly repair strategies. After identifying anomalies, we can match the corresponding system fault repair solutions to the knowledge base. This allows us to invoke the decision execution submodule to execute the corresponding maintenance instructions for the anomaly repair strategy, thus repairing the system faults associated with the resource scheduling system anomalies. By combining basic information from multiple dimensions to locate system faults during resource scheduling system inspections, matching corresponding repair solutions through information processing, and automatically executing maintenance instructions by invoking the decision execution submodule, we can quickly and efficiently repair system faults, saving significant manpower while ensuring the resource scheduling system provides stable service.

[0132] Corresponding to the above method embodiments, this specification also provides embodiments of an information processing apparatus. Figure 3 A schematic diagram of the structure of an information processing apparatus according to one embodiment of this specification is shown. Figure 3 As shown, the device includes:

[0133] The acquisition module 302 is configured to acquire basic information corresponding to multiple information dimensions of the resource scheduling system, and preprocess the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions.

[0134] The filtering module 304 is configured to filter abnormal information from the standard information in the multiple information dimensions in response to an anomaly detection request submitted for standard information in the multiple information dimensions.

[0135] The determination module 306 is configured to query the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy.

[0136] Repair module 308 is configured to call the decision execution submodule to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, in order to repair system faults associated with the anomaly information in the resource scheduling system.

[0137] In an optional embodiment, the acquisition module 302 is further configured to:

[0138] Obtain the first basic information corresponding to the first information dimension from the message queue system log corresponding to the resource scheduling system; obtain the second basic information corresponding to the second information dimension from the message queue system log; obtain the third basic information corresponding to the third information dimension from the resource scheduling system log corresponding to the resource scheduling system; obtain the fourth basic information corresponding to the fourth information dimension from the database corresponding to the resource scheduling system; and obtain the fifth basic information corresponding to the fifth information dimension from the system server corresponding to the resource scheduling system. Use the first basic information of the first information dimension, the second basic information of the second information dimension, the third basic information of the third information dimension, the fourth basic information of the fourth information dimension, and the fifth basic information of the fifth information dimension as the basic information of multiple information dimensions.

[0139] In an optional embodiment, the acquisition module 302 is further configured to:

[0140] The basic information of the multiple information dimensions is preprocessed according to the preset information processing rules; standard information of multiple information dimensions is generated based on the preprocessing results, wherein the information format of the standard information corresponding to each information dimension is the same.

[0141] In an optional embodiment, the apparatus further includes:

[0142] The information storage module is configured to store standard information of the multiple information dimensions into the system database;

[0143] The filtering module 304 is further configured as follows:

[0144] In response to an anomaly detection request submitted to the system database, the system database is queried, and a standard message corresponding to the anomaly type is determined as the anomaly message based on the query result.

[0145] In an optional embodiment, the determining module 306 is further configured to:

[0146] Based on the anomaly information, the knowledge base associated with the resource scheduling system is queried. An initial anomaly repair strategy is obtained based on the query results, and a strategy score corresponding to the initial anomaly repair strategy is determined. If the strategy score is greater than a score threshold, the initial anomaly repair strategy is adopted as the anomaly repair strategy. If the strategy score is less than or equal to the score threshold, the anomaly information is input into the repair strategy generation model for processing to obtain a predicted anomaly repair strategy. In response to a confirmation request submitted for the predicted anomaly repair strategy, the predicted anomaly repair strategy is adopted as the anomaly repair strategy.

[0147] In an optional embodiment, the determining module 306 is further configured to:

[0148] A knowledge base associated with the resource scheduling system is determined, and an information sub-base and a strategy sub-base are determined within the knowledge base; the information similarity between the abnormal information and the information stored in the information sub-base is calculated, and target information matching the abnormal information is determined based on the information similarity; the strategy sub-base is queried based on the information identifier corresponding to the target information, and an initial abnormality repair strategy matching the target information is obtained based on the query result.

[0149] In an optional embodiment, the determining module 306 is further configured to:

[0150] Obtain scenario prompt information associated with the resource scheduling system, and update the anomaly information based on the scenario prompt information; input the updated anomaly information into the repair strategy generation model for processing to obtain a predicted anomaly repair strategy.

[0151] In an optional embodiment, the apparatus further includes:

[0152] The knowledge storage module is configured to, upon completion of system fault repair in the resource scheduling system, establish an information matching relationship between the anomaly repair strategy and the anomaly information; and store the anomaly repair strategy and the anomaly information in the knowledge base according to the information matching relationship.

[0153] The information processing device provided in this embodiment, in order to quickly locate problems in the resource scheduling system and automatically repair system faults, can first collect basic information corresponding to multiple information dimensions of the resource scheduling system. At this point, preprocessing can be performed on the basic information of multiple information dimensions to obtain standard information for each dimension. Then, in response to anomaly detection requests submitted for the standard information of multiple information dimensions, anomaly information can be filtered from the standard information of multiple information dimensions. To improve the efficiency of system fault repair, anomaly information can be queried against the knowledge base of the associated resource scheduling system to determine anomaly repair strategies. After identifying anomaly information, the knowledge base can be used to match the repair plan for the corresponding system fault. This allows the decision execution submodule to be invoked to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, thereby repairing the system fault associated with the anomaly information in the resource scheduling system. When detecting the resource scheduling system, the device can combine basic information of multiple information dimensions to locate system faults, match corresponding repair plans through information processing, and automatically execute operation and maintenance instructions by invoking the decision execution submodule. This allows for rapid and efficient system fault repair, saving significant manpower while ensuring the resource scheduling system can provide stable service.

[0154] The above is an illustrative scheme of an information processing device according to this embodiment. It should be noted that the technical solution of this information processing device and the technical solution of the information processing method described above belong to the same concept. For details not described in detail in the technical solution of the information processing device, please refer to the description of the technical solution of the information processing method described above.

[0155] Figure 4 A structural block diagram of a computing device 400 according to one embodiment of this specification is shown. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0156] The computing device 400 also includes an access device 440, which enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 440 may include one or more of any type of wired or wireless network interface (e.g., a network interface controller (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0157] In one embodiment of this specification, the aforementioned components of the computing device 400 and Figure 4 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0158] Computing device 400 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). Computing device 400 can also be a mobile or stationary server.

[0159] The processor 420 is configured to execute the following computer-executable instructions, which, when executed by the processor, implement the steps of the above-described information processing method.

[0160] The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the information processing method described above belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the information processing method described above.

[0161] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described information processing method.

[0162] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the information processing method described above belong to the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the information processing method described above.

[0163] An embodiment of this specification also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described information processing method.

[0164] The above is an illustrative scheme of a computer program product according to this embodiment. It should be noted that the technical solution of this computer program product and the technical solution of the information processing method described above belong to the same concept. For details not described in detail in the technical solution of the computer program product, please refer to the description of the technical solution of the information processing method described above.

[0165] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0166] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added or removed according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0167] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0168] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0169] The preferred embodiments disclosed above are merely illustrative of this specification. Optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described in this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification.

Claims

1. An information processing method, characterized in that, include: The system collects basic information corresponding to multiple information dimensions from the resource scheduling system, and preprocesses the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions. In response to anomaly detection requests submitted for standard information across the multiple information dimensions, anomaly information is filtered from the standard information across the multiple information dimensions. The anomaly information is used to query the knowledge base associated with the resource scheduling system to determine the anomaly repair strategy. The decision execution submodule is invoked to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, which are used to repair system faults associated with the anomaly information in the resource scheduling system.

2. The information processing method according to claim 1, characterized in that, The resource collection and scheduling system corresponds to basic information across multiple information dimensions, including: Obtain the first basic information corresponding to the first information dimension from the message queue system log corresponding to the resource scheduling system; obtain the second basic information corresponding to the second information dimension from the message queue system log; obtain the third basic information corresponding to the third information dimension from the resource scheduling system log corresponding to the resource scheduling system; obtain the fourth basic information corresponding to the fourth information dimension from the database corresponding to the resource scheduling system; and obtain the fifth basic information corresponding to the fifth information dimension from the system server corresponding to the resource scheduling system. The first basic information of the first information dimension, the second basic information of the second information dimension, the third basic information of the third information dimension, the fourth basic information of the fourth information dimension, and the fifth basic information of the fifth information dimension are used as the basic information of multiple information dimensions.

3. The information processing method according to claim 1, characterized in that, The preprocessing of the basic information for the multiple information dimensions to obtain standard information for the multiple information dimensions includes: The basic information of the multiple information dimensions is preprocessed according to the preset information processing rules; Based on the preprocessing results, standard information with multiple information dimensions is generated, where the information format of the standard information corresponding to each information dimension is the same.

4. The information processing method according to claim 1, characterized in that, Before the step of filtering out abnormal information from the standard information across the multiple information dimensions in response to the anomaly detection request submitted for the standard information across the multiple information dimensions, the method further includes: Store the standard information of the multiple information dimensions into the system database; The step of responding to anomaly detection requests submitted for standard information across the multiple information dimensions, and filtering out anomaly information from the standard information across the multiple information dimensions, includes: In response to an anomaly detection request submitted to the system database, the system database is queried, and a standard message corresponding to the anomaly type is determined as the anomaly message based on the query result.

5. The information processing method according to claim 1, characterized in that, The step of querying the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy includes: Based on the anomaly information, query the knowledge base associated with the resource scheduling system, obtain an initial anomaly repair strategy based on the query results, and determine the strategy score corresponding to the initial anomaly repair strategy. If the strategy score is greater than the score threshold, the initial anomaly repair strategy will be used as the anomaly repair strategy. If the strategy score is less than or equal to the score threshold, the abnormal information is input into the repair strategy generation model for processing to obtain a predicted abnormality repair strategy; in response to the confirmation request submitted for the predicted abnormality repair strategy, the predicted abnormality repair strategy is adopted as the abnormality repair strategy.

6. The information processing method according to claim 5, characterized in that, The step of querying the knowledge base associated with the resource scheduling system based on the anomaly information and obtaining an initial anomaly repair strategy based on the query results includes: Determine the knowledge base associated with the resource scheduling system, and determine the information sub-base and the strategy sub-base in the knowledge base; Calculate the information similarity between the abnormal information and the information stored in the information sub-database, and determine the target information that matches the abnormal information based on the information similarity; Based on the information identifier corresponding to the target information, the strategy sub-library is queried, and an initial anomaly repair strategy matching the target information is obtained based on the query results.

7. The information processing method according to claim 5, characterized in that, The step of inputting the abnormal information into the repair strategy generation model for processing to obtain a predicted abnormality repair strategy includes: Obtain scenario prompt information associated with the resource scheduling system, and update the anomaly information based on the scenario prompt information; The updated anomaly information is input into the repair strategy generation model for processing to obtain the predicted anomaly repair strategy.

8. The information processing method according to any one of claims 1-7, characterized in that, After the step of executing the operation and maintenance instructions corresponding to the anomaly repair strategy by the call decision execution submodule to repair the system fault associated with the anomaly information in the resource scheduling system is executed, the following steps are also included: After the system fault repair of the resource scheduling system is completed, an information matching relationship is established between the anomaly repair strategy and the anomaly information; The anomaly repair strategy and the anomaly information are stored in the knowledge base according to the information matching relationship.

9. An information processing device, characterized in that, include: The data acquisition module is configured to collect basic information corresponding to multiple information dimensions of the resource scheduling system, and to preprocess the basic information of the multiple information dimensions to obtain standard information of the multiple information dimensions. The filtering module is configured to filter out abnormal information from the standard information in the multiple information dimensions in response to an anomaly detection request submitted for standard information in the multiple information dimensions. The determination module is configured to query the knowledge base associated with the resource scheduling system through the anomaly information to determine the anomaly repair strategy. The repair module is configured to call the decision execution submodule to execute the operation and maintenance instructions corresponding to the anomaly repair strategy, in order to repair system faults associated with the anomaly information in the resource scheduling system.

10. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, It stores computer-executable instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that, It includes a computer program or instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.

Images