A display terminal full life cycle fault intelligent diagnosis system

Abstract

This invention belongs to the field of display terminal fault diagnosis technology, specifically a smart fault diagnosis system for the entire lifecycle of display terminals. It receives a description of a fault phenomenon from the display terminal, retrieves a set of signal input control objects associated with the fault phenomenon, performs targeted detection on each control object within the set, generates an original detection dataset, removes instantaneous anomalies, obtains an effective fault feature set carrying potential fault identifiers, fuses it with historical fault contribution weights, obtains the fault cause confidence level for each control object, determines the correlation strength between the fault mode of each control object and environmental factors through preset environmental association rules, generates environmental sensitivity assessment labels and binds them to the fault cause confidence level, reveals the coupling mechanism between the root cause of the fault and environmental triggers, and outputs a fault location diagnosis report. This avoids insufficient granularity in fault location caused by generalized detection of the entire machine, providing a more comprehensive basis for fault handling.

Description

Technical Field

[0001] This invention belongs to the field of display terminal fault diagnosis technology, specifically a smart fault diagnosis system for the entire life cycle of a display terminal. Background Technology

[0002] In modern information society, display terminals are widely used in key scenarios such as production control, information display, and human-computer interaction. Their operational reliability is directly related to production efficiency, information transmission quality, and user experience.

[0003] However, display terminals have complex structures and numerous components, making them susceptible to environmental factors and aging throughout their lifecycle. This can lead to various faults such as screen flickering, black screens, and bright / dark lines. Traditional fault diagnosis relies on manual experience, resulting in low efficiency, high misdiagnosis rates, and often only reactive repairs after a fault occurs, severely impacting production continuity and service availability. Therefore, developing an intelligent fault diagnosis system covering the entire lifecycle of display terminals is crucial for achieving rapid fault diagnosis and accurate location.

[0004] In the existing technology, there are also some solutions related to display terminal fault diagnosis. For example, the remote operation and maintenance method, system, terminal and storage medium of LED display screen with Chinese patent publication number CN117993884A obtains the operating data of the LED display screen to be maintained to determine whether there is a fault. If a fault is found, the operating data is preprocessed to obtain the fault data model of the LED display screen to be maintained. The model is then input into a fault model library containing historical fault data models and their corresponding fault solutions for comparison. The fault type and solution are determined and then executed, thereby greatly improving the efficiency and quality of remote operation and maintenance of LED display screens.

[0005] Another Chinese patent publication, CN116703367A, discloses a method and system for repairing an LED LCD screen. This method acquires first repair data and repair time, conducts in-depth inspection of the first repair data to obtain second repair data, estimates second damage characteristics based on the first data, displays repair solutions using AI, statistically analyzes fault time frequency, and reports faults below a preset lifespan threshold or above a preset frequency to the factory, thereby improving the efficiency of fault detection and repair and reducing repair time and costs.

[0006] While the above solutions propose some methods for diagnosing display terminal faults, existing technologies still have the following limitations:

[0007] 1. Existing technologies generally rely on static matching of historical fault cases or generalized detection of overall performance parameters, neglecting the status monitoring and targeted diagnosis of the signal input end as a key hub of the display terminal. This results in the diagnostic process requiring traversal of the entire hardware topology, which is inefficient and cannot accurately locate the fault source at the signal link or interface level.

[0008] 2. Existing technologies lack a mechanism for verifying the temporal continuity of detection data, which can easily lead to misjudging anomalies caused by transient interference as persistent faults and triggering redundant maintenance.

[0009] 3. Existing diagnostic logic does not incorporate the accelerating effect of environmental stress on hardware failure and ignores the quantitative correlation between temperature and humidity conditions and failure modes, which can easily lead to environmentally induced failures being incorrectly attributed to defects in the device itself. Summary of the Invention

[0010] To overcome the shortcomings in the background art, embodiments of the present invention provide a smart fault diagnosis system for the entire life cycle of a display terminal, which can effectively solve the problems involved in the background art.

[0011] The objective of this invention can be achieved through the following technical solution: a smart fault diagnosis system for the entire life cycle of a display terminal, comprising: a fault information receiving module, a targeted detection execution module, an instantaneous fault filtering module, a cause confidence output module, an environmental coupling analysis module, and a diagnostic report generation module.

[0012] The fault information receiving module is connected to the targeted detection execution module, the targeted detection execution module is connected to the instantaneous fault filtering module, the instantaneous fault filtering module is connected to the cause confidence output module, the cause confidence output module is connected to the environmental coupling analysis module, and the environmental coupling analysis module is connected to the diagnostic report generation module.

[0013] The fault information receiving module receives a description of the fault phenomenon from the display terminal and retrieves a set of signal input terminal control objects associated with the fault phenomenon.

[0014] The targeted detection execution module performs targeted detection on each control object in the set and generates an original detection dataset.

[0015] The instantaneous fault filtering module removes instantaneous outliers from the original detection dataset based on density clustering and time-series fluctuation analysis, thereby obtaining an effective fault feature set carrying potential fault identifiers.

[0016] The cause confidence output module integrates the effective fault feature set and the historical fault contribution weights to output the fault cause confidence of each controlled object.

[0017] The environmental coupling analysis module extracts environmental temperature and humidity data during the period when the fault occurs, determines the correlation strength between the fault mode of each controlled object and environmental factors through preset environmental association rules, and generates environmental sensitivity assessment labels.

[0018] The diagnostic report generation module integrates the environmental sensitivity assessment labels with the fault cause confidence ranking results and outputs a fault location diagnostic report.

[0019] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention retrieves the set of signal input terminal control objects associated with the fault phenomenon of the display terminal, performs targeted detection on each control object in the set, and completes the initial screening of the status with the three domain parameters of power supply, clock signal to data bus, avoiding the insufficient granularity of fault location caused by the generalized detection of the whole machine, and focuses on the core hub of the video link of the display terminal.

[0020] (2) Based on density clustering and time series fluctuation analysis, this invention removes instantaneous outliers from the original detection dataset, actively filters transient noise and occasional event interference, ensures the reliability of the data source, significantly reduces the false alarm rate, and thus improves the accuracy of fault judgment and the credibility of diagnostic reports.

[0021] (3) By integrating the effective fault feature set and the historical fault contribution weight with dynamic decay, this invention scientifically outputs the confidence of fault causes of each controlled object, realizes self-optimization of diagnostic logic, and thus improves the adaptability and accuracy of complex fault attribution.

[0022] (4) This invention determines the correlation strength between the fault mode of each controlled object and environmental factors by setting pre-set environmental association rules, generates environmental sensitivity assessment labels and binds them to the confidence of fault cause, reveals the coupling mechanism between the root cause of the fault and the environmental cause, and outputs a fault location diagnosis report to provide a more comprehensive basis for fault handling. Attached Figure Description

[0023] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the module connection of the present invention.

[0025] Figure 2 This is a flowchart illustrating the logic of removing outliers from the original detection dataset in the instantaneous fault filtering module of this invention.

[0026] Figure 3 This is a flowchart illustrating the logic of generating environmental sensitivity assessment labels in the environmental coupling analysis module of this invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Reference Figure 1 As shown, the present invention provides a smart fault diagnosis system for the entire life cycle of a display terminal, including: a fault information receiving module, a targeted detection execution module, an instantaneous fault filtering module, a cause confidence output module, an environmental coupling analysis module, and a diagnostic report generation module.

[0029] The fault information receiving module is connected to the targeted detection execution module, the targeted detection execution module is connected to the instantaneous fault filtering module, the instantaneous fault filtering module is connected to the cause confidence output module, the cause confidence output module is connected to the environmental coupling analysis module, and the environmental coupling analysis module is connected to the diagnostic report generation module.

[0030] The fault information receiving module receives a description of the fault phenomenon from the display terminal and retrieves a set of signal input terminal control objects associated with the fault phenomenon.

[0031] It should be noted that the aforementioned signal input terminal control object refers to the detectable hardware unit in the signal input link of the display terminal, including but not limited to IC chips, resistor-capacitor groups, interface modules, etc.

[0032] In a preferred embodiment of the present invention, retrieving a set of signal input terminal control objects associated with the fault phenomenon includes: performing semantic parsing on the fault phenomenon description and decomposing it into fault behavior feature words and controlled unit identifiers.

[0033] It should be noted that the above semantic parsing process is as follows: preload the fault behavior lexicon and the controlled unit lexicon, perform part-of-speech tagging on the fault phenomenon description text, extract verb phrases and object noun phrases, match and verify the tagged verb phrases with the fault behavior lexicon, output standardized fault behavior feature words, map and verify the tagged object noun phrases with the controlled unit lexicon, and output standardized controlled unit identifiers.

[0034] Based on the grammatical dependency structure of the description content, the logical association between fault behavior feature words and controlled unit identifiers is verified, and only pairings that meet the following conditions are retained: the fault behavior feature word directly modifies the controlled unit identifier in the grammatical structure, or the controlled unit identifier is the direct object of the fault behavior feature word.

[0035] The fault behavior lexicon specifically includes terminal-specific fault verbs, which can be generated by parsing historical maintenance manuals and work order statistics. The controlled unit lexicon stores standardized names for hardware objects, derived from the equipment BOM and circuit diagram annotations.

[0036] Based on a preset fault code library, standard fault codes that match the combination of fault behavior feature words and controlled unit identifiers are retrieved.

[0037] Access the dynamically updated mapping table, extract the candidate signal input control objects of the standard fault code mapping corresponding to the fault phenomenon, and generate a set.

[0038] The mapping table is constructed based on the full life cycle fault case library of the display terminal, and records the correspondence between standard fault codes and their associated signal input terminal control objects.

[0039] It should be noted that the aforementioned display terminal full lifecycle failure case database is model-specific, containing failure cases of a specific model of display terminal from its introduction to its eventual scrapping. When a new failure case is added, the mapping relationship table is updated according to the following rules:

[0040] Based on the signal flow tracing analysis of the newly added cases, the signal input terminal control object where the root cause of the fault is located is extracted. If the object does not exist in the original fault code mapping set, it is added to the list of associated objects of the corresponding fault code.

[0041] For existing controlled objects, adjust their fault contribution weights based on the verification results of new cases.

[0042] The targeted detection execution module performs targeted detection on each control object in the set to generate an original detection dataset.

[0043] In a preferred embodiment of the present invention, the targeted detection execution process includes: performing multiple rounds of hierarchical detection on each control object in the set, with each round proceeding from power supply, clock signal to data bus according to hardware level.

[0044] In each round, the power supply response parameters, timing reference parameters, and data integrity parameters of the controlled object are collected synchronously.

[0045] Generate the original detection dataset containing object identifiers, detection rounds, and hierarchical parameters.

[0046] It should be noted that the basis for the above-mentioned single-round, hardware-level progressive detection from power supply, clock signal to data bus is as follows: since all controlled objects at the signal input end rely on power supply to complete signal level resolution and rely on clock signal to achieve timing synchronization, these two constitute the common operating environment of electronic circuits, and power supply or clock abnormalities will appear before data errors, so they are designed as the priority detection layer.

[0047] Data bus detection is based on the principle of physical layer signal integrity. It uses protocol-independent indicators such as eye diagram and bit error rate to adapt to control objects with different interface standards, thus forming differentiated fault location capabilities.

[0048] The power supply response parameters include, but are not limited to, the input pin voltage ripple coefficient and the current transient response settling time.

[0049] The timing reference parameters include, but are not limited to, reference clock cycle jitter and clock-data skew.

[0050] The data integrity parameters include, but are not limited to, bus eye diagram opening, bit error rate, and protocol packet CRC check failure count.

[0051] This invention retrieves a set of signal input control objects associated with display terminal fault phenomena, performs targeted detection on each control object in the set, and completes initial status screening using parameters from power supply, clock signal to data bus, avoiding insufficient granularity of fault location caused by generalized detection of the whole machine, and focusing on the core hub of the display terminal's video link.

[0052] The instantaneous fault filtering module removes instantaneous outliers from the original detection dataset based on density clustering and time-series fluctuation analysis, thereby obtaining an effective fault feature set carrying potential fault identifiers.

[0053] Reference Figure 2 As shown in a preferred embodiment of the present invention, the instantaneous outlier removal of the original detection dataset includes: generating a parameter-specific time sequence according to the detection round for the same type of parameters of the same control object.

[0054] The time series is divided into sliding analysis windows along the detection round direction. The fluctuation dispersion index of the parameter detection values ​​within the sliding analysis window is quantified. If the fluctuation dispersion index of a certain sliding analysis window exceeds the historical steady state preset allowable threshold, all parameter detection values ​​covered by the sliding analysis window are marked as candidate anomalies.

[0055] It should be noted that the fluctuation dispersion index of the parameter detection values ​​within the aforementioned sliding analysis window specifically refers to the standard deviation. The historical steady-state preset permission threshold is mainly constructed based on the parameter fluctuation characteristics of the same model display terminal under historical healthy conditions. The standard deviation of the parameters under historical healthy conditions can be calculated, and the sum of this and the preset permission error is used as the historical steady-state preset permission threshold.

[0056] Density clustering algorithm is used to identify clusters of candidate outliers that are continuously distributed along the time axis, and isolated candidate outliers are eliminated.

[0057] It should be noted that the specific implementation process of the density clustering algorithm described above is as follows: each candidate outlier point is mapped to the time axis coordinates to construct a one-dimensional spatial point set. The coordinate spacing between each spatial point on the time axis is calculated, and the median is taken as the clustering radius. The number of spatial points contained in the neighborhood constructed by the clustering radius of each spatial point is retrieved. Spatial points whose neighborhood contains more than a preset number of spatial points are taken as core points. Starting from any core point, all points in its neighborhood are included in the current cluster. If a newly added point is a core point, its neighborhood points are merged into the cluster. When it is impossible to continue expanding, the generated continuous cluster is the outlier cluster. Points not included in any cluster are determined to be isolated candidate outliers.

[0058] Traverse the dedicated timing sequences of parameters of each type for the same control object, perform multi-domain collaborative verification on the retained abnormal clusters, and assign a potential fault identifier to the control object when the control object has abnormal cluster conditions in at least two of the three dimensions of power supply response, timing reference and data integrity.

[0059] Output a valid fault feature set after verification, including the control object carrying the potential fault identifier, the abnormal cluster data corresponding to each abnormal detection parameter that triggers the identifier, and the start and end detection rounds.

[0060] This invention uses density clustering and time-series fluctuation analysis to remove instantaneous outliers from the original detection dataset, actively filtering transient noise and occasional event interference. This ensures the reliability of the data source, significantly reduces the false alarm rate, and thus improves the accuracy of fault determination and the credibility of diagnostic reports.

[0061] The cause confidence output module integrates the effective fault feature set and the historical fault contribution weights to output the fault cause confidence of each controlled object.

[0062] In a preferred embodiment of the present invention, the process of obtaining the confidence level of the fault cause of each controlled object includes: setting the confidence level of the fault cause of the controlled object that does not carry a potential fault identifier as a baseline lower limit value.

[0063] Designate the control object carrying a potential fault identifier as the target object, and perform the following steps:

[0064] (a) Based on the abnormal cluster data corresponding to each abnormal detection parameter, quantify the overall intensity characteristics of the target object, including the intensity of time persistence, the intensity of spatial correlation and the intensity of fluctuation deviation, and generate an abnormal fault index by fusing the three intensity characteristics.

[0065] It should be noted that the above-mentioned duration intensity is based on the average value of the ratio of the start and end detection rounds of the anomaly cluster data corresponding to each anomaly detection parameter to the total detection rounds.

[0066] Spatial correlation strength is quantified based on the number of detection parameters that trigger anomalies and the dimensional categories involved. For example, the ratio of the number of detection parameters that trigger anomalies to the total number of detection parameters, and the ratio of the number of dimensional categories involved to the total number of dimensional categories can be obtained. The product of the two ratios is taken as the spatial correlation strength.

[0067] The volatility deviation intensity is obtained by selecting the maximum value from the volatility dispersion index of the anomaly cluster data corresponding to each anomaly detection parameter.

[0068] It should also be noted that the above-mentioned method of generating abnormal fault indicators by fusing the three intensity features can be exemplarily obtained by accumulating the three intensity features.

[0069] (b) Based on the hardware topology of the signal input terminal, if the direct upstream control object of the target object carries a potential fault identifier, the target object is assigned a cascade fault factor; otherwise, a local fault factor is assigned. The confidence level represented by the local fault factor is higher than that of the cascade fault factor.

[0070] (c) By applying the fault factor to the abnormal fault index, the basic fault source confidence of the target object is obtained.

[0071] It should be noted that the basic fault source confidence of the above-mentioned target object can be obtained by multiplying the fault factor and the abnormal fault index, wherein the cascaded fault factor has a value of less than 1, the local fault factor has a value of greater than 1, and the over-amplitude of both is limited to within 0.3.

[0072] (d) Determine the historical fault contribution weight of the target object and add it to the basic fault source confidence to obtain the fault cause confidence of the target object.

[0073] In a preferred embodiment of the present invention, the process of determining the historical fault contribution weight of the target object includes: tracing the historical fault records of the target object in the fault case library of the entire life cycle of the display terminal, which contain the fault behavior feature words and the controlled unit identifier, and calculating the proportion of the case frequency as the fundamental fault source.

[0074] Based on the interval of the most recent historical failure, a time decay factor is introduced to correct the frequency proportion of the case, so as to generate the historical failure contribution weight of the target object.

[0075] This invention integrates effective fault feature sets with dynamically decaying historical fault contribution weights to scientifically output the confidence level of fault causes for each controlled object, thereby achieving self-optimization of diagnostic logic and improving the adaptability and accuracy of complex fault attribution.

[0076] The environmental coupling analysis module extracts environmental temperature and humidity data during the period when the fault occurs, determines the correlation strength between the fault mode of each controlled object and environmental factors through preset environmental association rules, and generates environmental sensitivity assessment labels.

[0077] In a preferred embodiment of the present invention, the preset environment association rules include the following: the vulnerable temperature and humidity ranges of each controlled object at the display terminal signal input terminal and the set of directional abnormal parameters triggered within the range.

[0078] Reference Figure 3 As shown, in a preferred embodiment of the present invention, determining the correlation strength between the failure mode of each controlled object and environmental factors, and generating corresponding environmental sensitivity assessment labels, includes: marking controlled objects that do not carry potential failure identifiers with a label indicating no environmental correlation.

[0079] For control objects carrying potential fault indicators, perform environmental matching analysis: i. Compare whether the environmental temperature and humidity data during the time when the fault occurred fall within the vulnerable temperature and humidity range of the target object.

[0080] ii. If not found, mark the target object's failure mode and environmental factors as having no environmental relevance.

[0081] iii. If it falls into the category, compare whether each anomaly detection parameter of the target object belongs to its directional anomaly parameter set, and quantify the directional anomaly compliance degree and continuous compliance rounds of the target object;

[0082] It should be noted that the above-mentioned target object orientation anomaly conformity specifically refers to the proportion of the target object anomaly detection parameters in the orientation anomaly parameter set, and the continuous conformity round specifically refers to the minimum round in which the orientation anomaly changes continuously conform to the anomaly cluster data corresponding to the anomaly detection parameters.

[0083] Both the directional anomaly compliance degree being greater than a preset compliance degree threshold and the number of consecutive compliance rounds being greater than a preset round threshold are used as conditions. If both conditions are met, the target object's fault mode and environmental factors are labeled as high environmental sensitivity. If only one condition is met, it is labeled as medium environmental sensitivity. If neither condition is met, it is labeled as low environmental sensitivity.

[0084] It should be noted that the above-mentioned preset compliance threshold and preset round threshold are determined based on the statistical distribution characteristics of the display terminal's full lifecycle failure case library, through the following technical path:

[0085] Extract all cases confirmed as environmentally induced failures from the case library, statistically analyze the distribution of orientation anomalies in these cases, and select inflection points as preset compliance thresholds.

[0086] The ratio of the minimum effective duration of all cases identified as environmentally induced failures in the case library to the preset fixed duration of a single round is used as the preset round threshold.

[0087] In a preferred embodiment of the present invention, the step of comparing whether each anomaly detection parameter of the target object belongs to its directional anomaly parameter set includes: performing parameter attribution verification on the anomaly detection parameters to confirm whether they belong to the physical quantity type defined in the directional anomaly parameter set.

[0088] Based on anomaly cluster data with anomaly detection parameters, calculate the actual direction of change of the anomaly detection parameters relative to the historical steady-state arithmetic mean.

[0089] It should be noted that the above-mentioned historical steady-state arithmetic mean is based on the collection of corresponding parameter monitoring data of the same model of display terminals under historical health conditions. The arithmetic mean of all parameter monitoring values ​​in the collection is taken. The actual change direction of the abnormal detection parameter relative to the historical steady-state arithmetic mean depends on the comparison between the abnormal detection parameter and the historical steady-state arithmetic mean. If the abnormal detection parameter is greater than the historical steady-state arithmetic mean, it indicates that the actual change direction is positive. If it is less than the historical steady-state arithmetic mean, it indicates that the change direction is negative. If it is equal to the historical steady-state arithmetic mean, it indicates that there is no change.

[0090] Extract the expected change direction of each directional abnormal parameter of the target object within the vulnerable temperature and humidity range. When the actual change direction is consistent with the expected change direction, the abnormal detection parameter is determined to have passed the directional consistency verification.

[0091] An anomaly detection parameter is determined to belong to the set of directional anomaly parameters only if it simultaneously satisfies both attribution verification and direction matching verification.

[0092] The diagnostic report generation module integrates the environmental sensitivity assessment labels with the fault cause confidence ranking results and outputs a fault location diagnostic report.

[0093] In a preferred embodiment of the present invention, the integration process of the environmental sensitivity assessment labels and the failure cause confidence ranking results includes: converting the environmental sensitivity assessment labels into level values ​​and establishing a Cartesian coordinate system with failure cause confidence as the horizontal axis and environmental sensitivity assessment labels as the vertical axis.

[0094] It should be noted that the above conversion of environmental sensitivity assessment labels into numerical levels specifically refers to converting labels with no environmental relevance, low environmental sensitivity, medium environmental sensitivity, and high environmental sensitivity into 0, 1, 2, and 3 respectively.

[0095] Define coordinate system partitioning rules to standardize the high confidence-high sensitivity region and the medium confidence-medium sensitivity region in the coordinate system.

[0096] It should also be noted that the above coordinate system partitioning rules include the following: the area where the confidence level of the cause of the fault is greater than the first preset confidence level and the environmental sensitivity assessment label level value is 3 is designated as the high confidence-high sensitivity area.

[0097] The region where the confidence level of the cause of the failure is within the closed interval between the second and first preset confidence levels and the environmental sensitivity assessment label level is 2 is defined as the medium confidence-medium sensitivity region.

[0098] For controlled objects located in the high confidence-high sensitivity zone, mark the primary fault source and generate corresponding core fault location entries in the report.

[0099] For control objects located in the medium confidence to medium sensitivity zone, label them with secondary fault sources and generate corresponding auxiliary fault analysis entries in the report.

[0100] Mark the remaining controlled objects as fault sources to be verified, and generate a list of detection parameters to recommend incremental detection rounds.

[0101] This invention determines the correlation strength between the fault mode of each controlled object and environmental factors by setting pre-defined environmental association rules, generates environmental sensitivity assessment labels and binds them to the confidence level of the fault cause, reveals the coupling mechanism between the root cause of the fault and the environmental trigger, and outputs a fault location diagnosis report to provide a more comprehensive basis for fault handling.

[0102] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A smart fault diagnosis system for the entire lifecycle of a display terminal, characterized in that, include: The fault information receiving module receives a description of the fault phenomenon from the display terminal and retrieves a set of signal input terminal control objects associated with the fault phenomenon. The targeted detection execution module performs targeted detection on each control object in the set and generates an original detection dataset. The targeted detection execution process includes: performing multiple rounds of hierarchical detection on each control object in the set, with each round progressing from power supply and clock signal to data bus according to hardware level; synchronously collecting power supply response parameters, timing reference parameters and data integrity parameters of the control object in each round; and generating an original detection dataset containing object identifier, detection round, and hierarchical parameters. The process of instantaneous outlier removal from the original detection dataset includes: generating parameter-specific time-series sequences for the same type of parameters of the same controlled object according to the detection rounds; dividing the time-series sequences into sliding analysis windows along the detection rounds, quantifying the fluctuation dispersion index of parameter detection values ​​within the sliding analysis window, and marking all parameter detection values ​​covered by the sliding analysis window as candidate outliers if the fluctuation dispersion index of a certain sliding analysis window exceeds the historical steady-state preset allowable threshold; using a density clustering algorithm to identify continuously distributed candidate outlier clusters on the time axis and removing isolated candidate outliers; traversing the parameter-specific time-series sequences of the same controlled object for each type of parameter, performing multi-domain collaborative verification on the retained outlier clusters, and assigning a potential fault identifier to the controlled object when the controlled object has an outlier cluster condition in at least two of the three dimensions of power supply response, timing reference, and data integrity; and outputting a verified effective fault feature set, including the controlled object carrying the potential fault identifier, the outlier cluster data corresponding to each outlier detection parameter that triggered the identifier, and their start and end detection rounds. The instantaneous fault filtering module removes instantaneous outliers from the original detection dataset based on density clustering and time-series fluctuation analysis, and obtains an effective fault feature set carrying potential fault identifiers. The cause confidence output module integrates the effective fault feature set and historical fault contribution weights to output the fault cause confidence of each controlled object. The environmental coupling analysis module extracts environmental temperature and humidity data during the period when the fault phenomenon occurs, determines the correlation strength between the fault mode of each control object and environmental factors through preset environmental association rules, and generates environmental sensitivity assessment labels. The diagnostic report generation module integrates the environmental sensitivity assessment labels with the fault cause confidence ranking results and outputs a fault location diagnostic report.

2. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 1, characterized in that: Retrieve the set of signal input control objects associated with the fault phenomenon, including: Semantic parsing is performed on the description of the fault phenomenon, which is decomposed into fault behavior feature words and controlled unit identifiers; Based on a preset fault code library, retrieve standard fault codes that match the combination of fault behavior feature words and controlled unit identifiers; Access the dynamically updated mapping table, extract the candidate signal input control objects of the standard fault code mapping corresponding to the fault phenomenon, and generate a set; The mapping table is constructed based on the display terminal's full lifecycle fault case library, recording the correspondence between standard fault codes and their associated signal input terminal control objects.

3. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 1, characterized in that: The process of obtaining the confidence level of the fault cause for each controlled object includes: Set the confidence level of the cause of failure for the controlled object that does not carry a potential fault identifier as the lower limit of the baseline; Designate the control object carrying a potential fault identifier as the target object, and perform the following steps: (a) Based on the anomaly cluster data corresponding to each anomaly detection parameter, quantify the overall intensity characteristics of the target object, including the intensity of time persistence, the intensity of spatial correlation and the intensity of fluctuation deviation, and generate anomaly fault indicators by fusing the three intensity characteristics. (b) Based on the hardware topology of the signal input terminal, if the direct upstream control object of the target object carries a potential fault identifier, the target object is assigned a cascade fault factor; otherwise, a local fault factor is assigned. The confidence level represented by the local fault factor is higher than that of the cascade fault factor. (c) By applying the fault factor to the abnormal fault index, the basic fault source confidence of the target object is obtained; (d) Determine the historical fault contribution weight of the target object and add it to the basic fault source confidence to obtain the fault cause confidence of the target object.

4. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 3, characterized in that: The process for determining the historical fault contribution weight of the target object includes: Trace the historical fault records of the target object in the fault case library of the entire life cycle of the display terminal, which contain fault behavior feature words and controlled unit identifiers, and calculate the proportion of cases that are the root cause of the fault. Based on the interval of the most recent historical failure, a time decay factor is introduced to correct the frequency proportion of the case, so as to generate the historical failure contribution weight of the target object.

5. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 1, characterized in that: The preset environment association rules include the following: The display terminal shows the vulnerable temperature and humidity ranges of each controlled object and the set of directional abnormal parameters caused by the range.

6. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 5, characterized in that: The determination of the correlation strength between the failure modes of each controlled object and environmental factors, and the generation of corresponding environmental sensitivity assessment labels, includes: Label controlled objects that do not carry potential fault indicators with non-environmentally relevant tags; For control objects carrying potential fault indicators, perform environmental matching analysis: i. Compare whether the environmental temperature and humidity data during the time when the fault occurred fall within the vulnerable temperature and humidity range of the target object; ii. If not included, mark the target object's failure mode and environmental factors as having no environmental relevance. iii. If it falls within the range, compare whether each anomaly detection parameter of the target object belongs to its directional anomaly parameter set, quantify the directional anomaly compliance degree and the number of consecutive compliance rounds of the target object; Both the directional anomaly compliance degree being greater than a preset compliance degree threshold and the number of consecutive compliance rounds being greater than a preset round threshold are used as conditions. If both conditions are met, the target object's fault mode and environmental factors are labeled as high environmental sensitivity. If only one condition is met, it is labeled as medium environmental sensitivity. If neither condition is met, it is labeled as low environmental sensitivity.

7. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 6, characterized in that: The comparison of whether each anomaly detection parameter of the target object belongs to its directional anomaly parameter set includes: Perform parameter attribution verification on the anomaly detection parameters to confirm whether they belong to the physical quantity type defined in the directional anomaly parameter set; Based on anomaly cluster data with anomaly detection parameters, calculate the actual direction of change of the anomaly detection parameters relative to the historical steady-state arithmetic mean; Extract the expected change direction of each directional abnormal parameter of the target object within the vulnerable temperature and humidity range. When the actual change direction is consistent with the expected change direction, the abnormal detection parameter is determined to have passed the directional consistency verification. An anomaly detection parameter is determined to belong to the set of directional anomaly parameters only if it simultaneously satisfies both attribution verification and direction matching verification.

8. The intelligent fault diagnosis system for the entire life cycle of a display terminal according to claim 6, characterized in that: The process of integrating the environmental sensitivity assessment labels with the failure cause confidence ranking results includes: Convert environmental sensitivity assessment labels into numerical levels and establish a Cartesian coordinate system with the confidence level of the cause of failure as the horizontal axis and the environmental sensitivity assessment labels as the vertical axis. Define coordinate system partitioning rules to standardize the high-confidence-high-sensitivity region and the medium-confidence-medium-sensitivity region in the coordinate system; For control objects located in the high confidence-high sensitivity zone, mark the primary fault source and generate corresponding core fault location entries in the report; For control objects located in the medium confidence to medium sensitivity zone, label the secondary fault sources and generate corresponding auxiliary fault analysis entries in the report; Mark the remaining controlled objects as fault sources to be verified, and generate a list of detection parameters to recommend incremental detection rounds.

Images