Intelligent analysis and display method and system for equipment operation and maintenance data

Abstract

The invention discloses an intelligent analysis and display method and system for equipment operation and maintenance data, and the method comprises the steps: obtaining an operation log and an operation time sequence parameter stream of equipment, converting the operation log into structured data, and taking the structured data as an event expression unit of the equipment; according to the event expression unit and the operation time sequence parameter flow, calculating a mutagenesis value of each time node in a time section during operation of the equipment, extracting mutagenesis peak points of all the mutagenesis values in the time section, and forming a mutagenesis peak point set; according to the operation time sequence parameter flow, a state desire tensor time sequence of the equipment is constructed, division is conducted according to multiple time periods, multiple division results are abstracted into a graph structure to serve as a final display result, and mutagenesis peak points in the mutagenesis peak point set serve as anchor points of each time period.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of equipment operation and maintenance, and more particularly relates to an intelligent analysis and display method and system for equipment operation and maintenance data. BACKGROUND

[0002] In the field of traditional equipment operation and maintenance, equipment is mainly maintained by means of regular inspection, table report recording, and post-fault processing. The running state of the equipment is usually preliminarily judged by manually reading logs, checking status lights, or using PLC data to export tables. This mode is heavily dependent on personnel experience, has a long response cycle, and is weak in identifying sudden, gradual, or multi-source coupled faults.

[0003] Therefore, there is an urgent need for a technical solution that can analyze the state of the equipment according to the equipment operation and maintenance data, display it in a way that is different from the understanding of the operation and maintenance personnel, and guide the operation and maintenance operation. SUMMARY

[0004] To solve the above technical problems, the present application provides an intelligent analysis and display method for equipment operation and maintenance data, comprising:

[0005] obtaining the running log and the running time sequence parameter stream of the equipment, converting the running log into structured data as the event expression unit of the equipment;

[0006] According to the event expression unit and the running time sequence parameter stream, the mutagenic value of each time node in the time section of the equipment running is calculated, the mutagenic peak points of all mutagenic values in the time section are extracted, and a mutagenic peak point set is formed.

[0007] According to the running time sequence parameter stream, a state desire tensor time sequence of the equipment is constructed, and is divided into multiple time periods, and the multiple division results are abstracted into a graph structure as the final display result, wherein the mutagenic peak points in the mutagenic peak point set are used as anchor points for each time period.

[0008] Further, the event expression unit of the equipment includes: the event expression unit is a structured binary tuple, which includes event encoding and event occurrence time.

[0009] Further, calculating the mutagenic value of each time node in the time section of the equipment running includes: constructing a mutagenic degree function, and calculating the mutagenic value of each time node in the time section according to the event expression unit and the running time sequence parameter stream.

[0010] Further, extracting the mutagenic peak points of all mutagenic values in the time section to form a mutagenic peak point set includes: dividing the time section into multiple sub-time sections, and the point with the maximum mutagenic value in each sub-time section is used as the mutagenic peak point of the current sub-time section.

[0011] Furthermore, the temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device;

[0012] Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

[0013] Furthermore, the division by multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a certain fixed window and step size, and each step size includes the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

[0014] Furthermore, before abstracting multiple partitioning results into a graph structure, the process includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

[0015] Furthermore, the multiple partitioning results are abstracted into a graph structure, which serves as the final display result. This includes: forming transition pairs by arranging adjacent intent labels corresponding to each sub-trajectory in chronological order, connecting all transition pairs in sequence, and generating a directed graph structure, which serves as the final display result.

[0016] This invention also proposes an intelligent analysis and display method and system for equipment operation and maintenance data, including:

[0017] The data processing module is used to acquire the device's operation logs and runtime sequence parameter streams, and convert the operation logs into structured data as event expression units for the device.

[0018] The mutation value acquisition module is used to calculate the mutation value of each time node in the time segment during device operation based on the event expression unit and the runtime sequence parameter stream, extract the mutation peak points of all mutation values ​​in the time segment, and form a mutation peak point set.

[0019] The graph structure generation module is used to construct the state desire tensor time series sequence of the device according to the runtime sequence parameter stream, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. In this graph, the mutation peak points in the mutation peak point set are used as anchor points for each time period.

[0020] Furthermore, the event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes an event code and an event occurrence time.

[0021] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:

[0022] Through the above technical solutions, this invention can proactively discover potential clues to equipment anomalies without relying on manual log review or waiting for equipment alarms; it can extract behavioral intentions from rigid data changes, enabling maintenance personnel to clearly understand the status of the equipment. Attached Figure Description

[0023] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention;

[0024] Figure 2 This is a system structure diagram of Embodiment 2 of the present invention;

[0025] Figure 3 This is a schematic diagram of the mutagenic values ​​in Embodiment 1 of the present invention;

[0026] Figure 4 This is a schematic diagram of the structure of Embodiment 1 of the present invention. Detailed Implementation

[0027] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0028] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0029] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0030] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0031] The display screen is used to show the user interface of each application.

[0032] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0033] Example 1

[0034] like Figure 1 As shown in the figure, this embodiment proposes an intelligent analysis and display method for equipment operation and maintenance data, including:

[0035] Step 101: Obtain the device's operation log and runtime sequence parameter stream, and convert the operation log into structured data as the device's event expression unit;

[0036] Preferably, the device's operation log can be in the format of free text, system encoding, nested structure, etc., for example, [2025-01-10 14:32:01] Warning: Fan speed abnormal. Current value: 700rpm, expected value: >1200rpm. The runtime sequence parameter stream can be time-series sensor data (such as temperature, current, speed, vibration, etc.).

[0037] Specifically, the event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

[0038] For example, based on the warning [2025-01-10 14:32:01]: abnormal fan speed. Current value: 700rpm, expected value: >1200rpm, then the event expression unit is:

[0039] Event coding: The i-th event = fan speed too low;

[0040] Time of the incident: 2025-01-10 14:32:01.

[0041] Step 102: Based on the event expression unit and the runtime sequence parameter stream, calculate the induced mutation value of each time node within the time segment during device operation, extract the induced mutation peak points of all induced mutation values ​​within the time segment, and form a set of induced mutation peak points;

[0042] The purpose of calculating the induced value in this embodiment is to discover particularly unstable time points in the device behavior. These time points may hide important operation and maintenance problems. Therefore, in many cases, the data of the device has already started to fluctuate before the problem occurs, but there is no clear error record. This embodiment calculates the induced value through step 102 in order to find the precursors of the device abnormality.

[0043] Specifically, the mutagenic value of each time node within a time segment during the operation of the computing device includes: constructing a mutagenicity function and calculating the mutagenic value of each time node within the time segment based on the event expression unit and the runtime sequence parameter stream.

[0044] Preferably, the mutation degree function set in this embodiment is as follows:

[0045]

[0046] Where D(t) is the induced mutation value at time t, m is the number of sensor data in the runtime sequence parameter stream, and ω j p represents the weight of the j-th sensor data. j (t) represents the data from the j-th sensor at time t, where n is the number of events, and β i Let δ(t-τ) be the weight of the i-th event. i τ is a unit impulse function, representing the instantaneous impact of an event. i Let the i-th event occur at time τ.

[0047] Specifically, extracting the mutation peak points of all induced mutation values ​​within a time interval to form a mutation peak point set includes: dividing the time interval into multiple sub-time intervals, and taking the point with the largest induced mutation value in each sub-time interval as the mutation peak point of the current sub-time interval.

[0048] like Figure 3 As shown, this embodiment provides the following example to describe the mutation peak point:

[0049] Assuming Figure 3 The horizontal axis (time t, which can be seconds or minutes, is not limited in this embodiment) is divided into 5 sub-time segments: 0-20, 20-40, 40-60, 60-80, and 80-100. Then, the highest point of each sub-time segment can be found as the mutation peak point, and a mutation peak point set can be formed.

[0050] Step 103: Based on the runtime sequence parameter stream, construct the state desire tensor time sequence of the device, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. The mutation peak points in the mutation peak point set serve as anchor points for each time period.

[0051] Specifically, the temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device;

[0052] Preferably, this embodiment sets corresponding functions to calculate the first tendency index, the second tendency index, and the third tendency index of the current time device, as shown below:

[0053] The function for calculating the first tendency index of the current time device is:

[0054]

[0055] Where, d s (t) is the first tendency index of the device at time t, and Z is the normalization factor.

[0056] The function for calculating the second tendency index of the current time device is:

[0057]

[0058] Where, d e (t) is the second tendency index of the device at time t, ω′ k R represents the weight of the k-th anomaly detection response metric. k (t) represents the response index for the k-th anomaly detection.

[0059] In order to make R k (t) To make it clearer, this embodiment illustrates R through the following example. k (t) is explained as follows:

[0060]

[0061]

[0062] The parameters in the table are explained as follows: T is the equipment temperature at time t, θ T Let I be the temperature threshold, I be the device current at time t, and θ be the current at time t. I Let be the current threshold, and a(t) be the acceleration of the equipment vibration at time t. Let θ be the historical mean of the equipment's vibration acceleration. R′ R is the equipment rotation speed threshold, and R′ is the equipment rotation speed at time t.

[0063] The function for calculating the third tendency index of the current time device is:

[0064]

[0065] Where, d q (t) represents the third tendency index of the equipment at time t, η j For the j-th sensor data p at time t j The weights of the expected value of (t), For the j-th sensor data p at time tj The expected value of (t), Δ j for With p j (t) Maximum allowable deviation.

[0066] Preferably, in order to unify the parameters, this embodiment performs a normalization operation on the first tendency index, the second tendency index, and the third tendency index of the current time device, and uniformly normalizes the three tendency indices to the range of 0-1.

[0067] Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

[0068] Specifically, dividing the time into multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a fixed window and step size, and each step size includes the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

[0069] Specifically, before abstracting multiple partitioning results into a graph structure, the process also includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

[0070] To clarify the meanings of the intent labels—namely, the intent labels for maintaining the current state, the intent labels for escaping the current mutation, and the intent labels for moving towards a target state—this embodiment provides the following examples:

[0071] Intent label regarding the device maintaining its current state:

[0072] The equipment is operating stably in its current state, with all indicators within the normal range and no obvious trend requiring "change" or "adjustment". For example, the equipment's fan speed is 1500 rpm, the system's expected value is also 1500 rpm, and the temperature and current fluctuations are very small; the equipment is operating within the standard load range, has not reached the load threshold, and has no overload trend, etc.

[0073] Regarding the device's intent to evade current mutation:

[0074] When the equipment senses that external or internal disturbances (such as temperature rise, sudden current change, or abnormal vibration) exceed the threshold, the system attempts to escape this adverse state by adjusting the operating parameters. For example, if the equipment temperature rises rapidly (e.g., from 60℃ to 75℃), the equipment itself will increase the fan speed; if the motor current suddenly increases, the equipment will activate the current limiting protection; if the equipment detects a sudden change in vibration frequency, it will reduce the speed to avoid structural resonance.

[0075] Intent labels related to the device's tendency to move towards a certain target state:

[0076] During operation, equipment has an inherent tendency to actively approach the target state. Even if the current state is acceptable, if the target is better, with lower energy consumption or greater safety, for example, if the current temperature of the equipment is 42°C and the target is to cool it down to 38°C, the fan will continue to run at an accelerated speed; if the equipment is under low load, it will actively enter the "energy-saving mode".

[0077] Since every change in equipment data has a motivation, such as a sudden drop in current possibly indicating a desire to reduce load, we verbalize the equipment's behavior to make it easier for maintenance personnel to understand. Therefore, the purpose of step 103 in this embodiment is to translate the equipment's behavior into an expression of what it wants to do, such as "want to cool down," "want to perform a self-test," or "want to enter hibernation," which corresponds to intent labels. In this way, we can extract the equipment's behavioral intent from rigid data changes, allowing the equipment to be analyzed like an object with behavioral logic.

[0078] Specifically, the multiple segmentation results are abstracted into a graph structure, which, as the final display result, includes: forming transition pairs from adjacent intent labels corresponding to each sub-trajectory in chronological order, connecting all transition pairs in sequence, and generating a directed graph structure (e.g., Figure 4 As shown in the image, this is the final result.

[0079] For example, subtrajectories are assigned to corresponding intent labels, forming an intent label sequence [S0,S0,S1,S2,S2,S1,S3]. Adjacent intent labels corresponding to each subtrajectory are then paired in sequence, as shown below:

[0080] S0→S0;S0→S1;S1→S2;S2→S2;S2→S1;S1→S3;

[0081] Wherein, S0 is the intention label for the device to maintain its current state, S1 is the intention label for the device to evade the current mutation, and S3 is the intention label for the device to move toward a certain target state.

[0082] Example 2

[0083] like Figure 2 As shown, this embodiment proposes an intelligent analysis and display system for equipment operation and maintenance data, including:

[0084] The data processing module is used to acquire the device's operation logs and runtime sequence parameter streams, and convert the operation logs into structured data as event expression units for the device.

[0085] Specifically, the event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

[0086] The mutation value acquisition module is used to calculate the mutation value of each time node in the time segment during device operation based on the event expression unit and the runtime sequence parameter stream, extract the mutation peak points of all mutation values ​​in the time segment, and form a mutation peak point set.

[0087] Specifically, the mutagenic value of each time node within a time segment during the operation of the computing device includes: constructing a mutagenicity function and calculating the mutagenic value of each time node within the time segment based on the event expression unit and the runtime sequence parameter stream.

[0088] Specifically, extracting the mutation peak points of all induced mutation values ​​within a time interval to form a mutation peak point set includes: dividing the time interval into multiple sub-time intervals, and taking the point with the largest induced mutation value in each sub-time interval as the mutation peak point of the current sub-time interval.

[0089] The graph structure generation module is used to construct the state desire tensor time series sequence of the device according to the runtime sequence parameter stream, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. In this graph, the mutation peak points in the mutation peak point set are used as anchor points for each time period.

[0090] Specifically, the temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device;

[0091] Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

[0092] Specifically, dividing the time into multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a fixed window and step size, and each step size includes the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

[0093] Specifically, before abstracting multiple partitioning results into a graph structure, the process also includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

[0094] Specifically, the multiple partitioning results are abstracted into a graph structure, which serves as the final display result. This includes forming transition pairs by arranging adjacent intent labels corresponding to each sub-trajectory in chronological order, connecting all transition pairs in sequence, and generating a directed graph structure, which serves as the final display result.

[0095] Example 3

[0096] This invention also proposes a storage medium storing multiple instructions, which are used to implement the intelligent analysis and display method for equipment operation and maintenance data.

[0097] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0098] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: Step 101, obtain the device's operation log and runtime sequence parameter stream, and convert the operation log into structured data as the device's event expression unit;

[0099] Specifically, the event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

[0100] Step 102: Based on the event expression unit and the runtime sequence parameter stream, calculate the induced mutation value of each time node within the time segment during device operation, extract the induced mutation peak points of all induced mutation values ​​within the time segment, and form a set of induced mutation peak points;

[0101] Specifically, the mutagenic value of each time node within a time segment during the operation of the computing device includes: constructing a mutagenicity function and calculating the mutagenic value of each time node within the time segment based on the event expression unit and the runtime sequence parameter stream.

[0102] Specifically, extracting the mutation peak points of all induced mutation values ​​within a time interval to form a mutation peak point set includes: dividing the time interval into multiple sub-time intervals, and taking the point with the largest induced mutation value in each sub-time interval as the mutation peak point of the current sub-time interval.

[0103] Step 103: Based on the runtime sequence parameter stream, construct the state desire tensor time sequence of the device, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. The mutation peak points in the mutation peak point set serve as anchor points for each time period.

[0104] Specifically, the temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device;

[0105] Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

[0106] Specifically, dividing the time into multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a fixed window and step size, and each step size includes the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

[0107] Specifically, before abstracting multiple partitioning results into a graph structure, the process also includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

[0108] Specifically, the multiple partitioning results are abstracted into a graph structure, which serves as the final display result. This includes forming transition pairs by arranging adjacent intent labels corresponding to each sub-trajectory in chronological order, connecting all transition pairs in sequence, and generating a directed graph structure, which serves as the final display result.

[0109] Example 4

[0110] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the intelligent analysis and display method for equipment operation and maintenance data.

[0111] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0112] The storage medium can be used to store software programs and modules, such as the intelligent analysis and display method for equipment operation and maintenance data in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned intelligent analysis and display method for equipment operation and maintenance data. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0113] The processor can call the information and application stored in the storage medium through the transmission system to execute the following method steps: Step 101, obtain the device's operation log and runtime sequence parameter stream, and convert the operation log into structured data as the device's event expression unit;

[0114] Specifically, the event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

[0115] Step 102: Based on the event expression unit and the runtime sequence parameter stream, calculate the induced mutation value of each time node within the time segment during device operation, extract the induced mutation peak points of all induced mutation values ​​within the time segment, and form a set of induced mutation peak points;

[0116] Specifically, the mutagenic value of each time node within a time segment during the operation of the computing device includes: constructing a mutagenicity function and calculating the mutagenic value of each time node within the time segment based on the event expression unit and the runtime sequence parameter stream.

[0117] Specifically, extracting the mutation peak points of all induced mutation values ​​within a time interval to form a mutation peak point set includes: dividing the time interval into multiple sub-time intervals, and taking the point with the largest induced mutation value in each sub-time interval as the mutation peak point of the current sub-time interval.

[0118] Step 103: Based on the runtime sequence parameter stream, construct the state desire tensor time sequence of the device, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. The mutation peak points in the mutation peak point set serve as anchor points for each time period.

[0119] Specifically, the temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device;

[0120] Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

[0121] Specifically, dividing the time into multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a fixed window and step size, and each step size includes the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

[0122] Specifically, before abstracting multiple partitioning results into a graph structure, the process also includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

[0123] Specifically, the multiple partitioning results are abstracted into a graph structure, which serves as the final display result. This includes forming transition pairs by arranging adjacent intent labels corresponding to each sub-trajectory in chronological order, connecting all transition pairs in sequence, and generating a directed graph structure, which serves as the final display result.

[0124] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0125] In the above embodiments of the present invention, 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.

[0126] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0127] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0128] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0129] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0130] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for intelligent analysis and display of equipment operation and maintenance data, characterized in that, include: Obtain the device's operation logs and runtime sequence parameter streams, and convert the operation logs into structured data as event expression units for the device; Based on the event expression unit and the runtime sequence parameter stream, calculate the induced mutation value of each time node within the time segment during device operation, extract the induced mutation peak points of all induced mutation values ​​within the time segment, and form a set of induced mutation peak points; Based on the runtime sequence parameter stream, a state desire tensor time sequence of the device is constructed and divided into multiple time periods. The multiple division results are abstracted into a graph structure as the final display result, wherein the mutation peak points in the mutation peak point set serve as anchor points for each time period.

2. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 1, characterized in that, The event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

3. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 1, characterized in that, The mutagenic value of each time node within a time segment during the operation of the computing device includes: constructing a mutagenicity function and calculating the mutagenic value of each time node within the time segment based on the event expression unit and the runtime sequence parameter stream.

4. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 3, characterized in that, Extracting the peak mutation points of all induced mutation values ​​within a time interval to form a set of induced mutation peak points involves dividing the time interval into multiple sub-time intervals, with the point of maximum induced mutation value in each sub-time interval serving as the induced mutation peak point of that sub-time interval.

5. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 1, characterized in that, The temporal sequence of the state desire tensor includes: the first tendency index of the current time device, the second tendency index of the current time device, and the third tendency index of the current time device; Among them, the higher the first tendency index, the more stable the current time device is; the higher the second tendency index, the more the current time device wants to escape the current mutation; and the higher the third tendency index, the more the current time device tends to a certain target state.

6. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 1, characterized in that, Dividing the data into multiple time periods includes: performing a sliding operation on the temporal sequence of the state desire tensor according to a fixed window and step size, where each step size contains the mutation peak points in the set of mutation peak points, and finally generating multiple sub-trajectories as the division result.

7. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 6, characterized in that, Before abstracting multiple partitioning results into a graph structure, the process also includes: initializing multiple intent labels and initial trajectories corresponding to the intent labels, clustering the sub-trajectories according to the initial trajectories, and thus assigning the sub-trajectories to the corresponding intent labels. The intent labels are intent labels for the device to maintain its current state, intent labels for the device to escape the current mutation, and intent labels for the device to tend towards a certain target state.

8. The intelligent analysis and display method for equipment operation and maintenance data as described in claim 7, characterized in that, The multiple partitioning results are abstracted into a graph structure, which is the final display result. This includes forming transition pairs by arranging the adjacent intent labels corresponding to each sub-trajectory in sequence, connecting all transition pairs in sequence, and generating a directed graph structure, which is the final display result.

9. A method and system for intelligent analysis and display of equipment operation and maintenance data, characterized in that, include: The data processing module is used to acquire the device's operation logs and runtime sequence parameter streams, and convert the operation logs into structured data as event expression units for the device. The mutation value acquisition module is used to calculate the mutation value of each time node in the time segment during device operation based on the event expression unit and the runtime sequence parameter stream, extract the mutation peak points of all mutation values ​​in the time segment, and form a mutation peak point set. The graph structure generation module is used to construct the state desire tensor time series sequence of the device according to the runtime sequence parameter stream, divide it into multiple time periods, and abstract the multiple division results into a graph structure as the final display result. In this graph, the mutation peak points in the mutation peak point set are used as anchor points for each time period.

10. The intelligent analysis and display system for equipment operation and maintenance data as described in claim 9, characterized in that, The event expression unit of the device includes: the event expression unit is a structured binary tuple, which includes the event code and the event occurrence time.

Images