Printing equipment fault tracing and maintenance decision-making system and method based on knowledge graph

Abstract

The invention discloses a printing equipment fault tracing and maintenance decision-making system and method based on a knowledge graph, and belongs to the technical field of printing equipment. The method comprises the following steps: acquiring operation data and historical fault data of the printing equipment and fault condition information at the current moment; according to the operation data and the historical fault data, updating a confidence coefficient of a relationship in a fault tracing knowledge graph; and determining a fault reason according to the fault condition information and the fault tracing knowledge graph. The technical effect of improving the accuracy of the fault tracing result of the printing equipment is achieved.

Description

Technical Field

[0001] The present invention relates to the field of printing equipment, and in particular, to a printing equipment fault tracing and maintenance decision-making system and method based on a knowledge graph. Background Art

[0002] The electrical control system and mechanical components of printing equipment are generally complex. The realization of a single function often requires accurate electrical control based on high-precision mechanical components to achieve precise printing. At present, in the process of using a general knowledge graph for fault identification, due to subtle differences in functions among some similar models of printing equipment, the hardware is not completely the same. On this basis, when using the knowledge graph, it cannot fully correspond to the printing equipment, resulting in inaccurate results of fault problem tracing.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main object of the present invention is to provide a printing equipment fault tracing and maintenance decision-making system and method based on a knowledge graph, aiming to improve the accuracy of the printing equipment fault tracing results.

[0005] To achieve the above object, the present invention provides a printing equipment fault tracing and maintenance decision-making method based on a knowledge graph. The printing equipment fault tracing and maintenance decision-making method based on a knowledge graph includes the following steps:

[0006] Obtain the operation data, historical fault data, and fault situation information at the current moment of the printing equipment;

[0007] Update the confidence level of the relationship in the fault tracing knowledge graph according to the operation data and the historical fault data;

[0008] Determine the fault cause according to the fault situation information and the fault tracing knowledge graph.

[0009] Optionally, the step of determining the fault cause according to the fault situation information and the fault tracing knowledge graph includes:

[0010] Determine the initial node in the fault tracing knowledge graph according to the fault situation information, and search for the relationship chain according to the initial node to obtain multiple relationship chains;

[0011] Determine the target relationship chain according to the multiple relationship chains and the confidence level of each relationship, and determine the fault cause according to the target relationship chain.

[0012] Optionally, before the step of updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data, the following steps are further included:

[0013] Obtain the maintenance data of the printing equipment, and extract a plurality of triple data according to the maintenance data. The structure of the triple data is: first object, relationship, second object;

[0014] Construct a fault traceability knowledge graph according to the plurality of triple data.

[0015] Optionally, the historical fault data includes: a historical fault relationship chain, which is a fault relationship chain obtained in the fault traceability knowledge graph based on a fault prompt determined before the current moment. The step of updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data includes:

[0016] Determine an operation relationship chain according to the operation data;

[0017] Determine a first type of relationship and a second type of relationship in the fault traceability knowledge graph according to the historical fault relationship chain and the operation relationship chain. The first type of relationship is a relationship belonging to the historical fault relationship chain or a relationship belonging to the operation relationship chain, and the second type of relationship is a relationship other than the first type of relationship in the fault traceability knowledge graph;

[0018] Determine the weight value corresponding to each of the first type of relationships according to the historical fault relationship chain and the operation relationship chain, and set the weight value of the second type of relationship to a preset value;

[0019] Determine the confidence of each relationship according to all the relationships and the corresponding weight values.

[0020] Optionally, the step of determining the confidence of each relationship according to all the relationships and the corresponding weight values includes:

[0021] Determine at least one target triple data associated with each target object according to the fault traceability knowledge graph. The target triple data is triple data with the target object as the first object;

[0022] Calculate the target confidence of each target relationship on the target object according to the target relationships and the corresponding target weight data of all the target triple data;

[0023] Take the target confidence as the confidence.

[0024] Optionally, the operation data includes: the functions being run and the corresponding related components, and the running time. The step of determining the operation relationship chain according to the operation data includes:

[0025] Determine multiple related objects in the fault tracing knowledge graph according to the related components;

[0026] Determine the operation relationship chain according to the fault tracing knowledge graph and the multiple related objects.

[0027] Optionally, the step of determining the operation relationship chain according to the fault tracing knowledge graph and the multiple related objects includes:

[0028] Calculate the first shortest path between any two of the related objects according to the fault tracing knowledge graph and the multiple related objects, and obtain multiple first shortest paths;

[0029] Determine the operation relationship chain according to the multiple first shortest paths and the Held-Karp algorithm.

[0030] Optionally, the step of determining the target relationship chain according to the multiple relationship chains and the confidence level of each relationship includes:

[0031] Determine the relationship chain probability corresponding to each relationship chain according to a pre-designed calculation formula, the confidence level of each relationship, and each relationship chain;

[0032] Determine the target relationship chain according to the relationship probability of each relationship chain.

[0033] Optionally, after the step of determining the fault cause according to the fault situation information and the fault tracing knowledge graph, it further includes:

[0034] Generate a corresponding maintenance decision according to the fault cause.

[0035] In addition, to achieve the above object, the present invention also provides a printing equipment fault tracing and maintenance decision system based on a knowledge graph. The printing equipment fault tracing and maintenance decision system based on a knowledge graph includes:

[0036] An acquisition module, configured to acquire the operation data, historical fault data, and fault situation information at the current moment of the printing equipment;

[0037] An update module, configured to update the confidence level of the relationship in the fault tracing knowledge graph according to the operation data and the historical fault data;

[0038] An identification module, configured to determine the fault cause according to the fault situation information and the fault tracing knowledge graph.

[0039] The present invention provides a method for fault tracing and maintenance decision-making of printing equipment based on a knowledge graph. The method obtains the operation data, historical fault data, and fault situation information at the current moment of the printing equipment, and updates the confidence of the relationships in the fault tracing knowledge graph according to the operation data and the historical fault data, so as to adjust the knowledge graph according to the actual working state of each printing equipment, thereby obtaining a knowledge graph directly associated with the actual situation of the printing equipment, improving the accuracy of the knowledge graph reasoning process, and further improving the accuracy of fault identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a schematic structural diagram of a printing equipment in the hardware operating environment related to the embodiment solution of the present invention;

[0041] Figure 2 is a schematic flowchart of the first embodiment of the method for fault tracing and maintenance decision-making of printing equipment based on a knowledge graph according to the present invention;

[0042] Figure 3 is a schematic flowchart of the second embodiment of the method for fault tracing and maintenance decision-making of printing equipment based on a knowledge graph according to the present invention;

[0043] Figure 4 is a schematic flowchart of the third embodiment of the method for fault tracing and maintenance decision-making of printing equipment based on a knowledge graph according to the present invention;

[0044] The realization, functional features, and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] Referring to Figure 1 , Figure 1 is a schematic structural diagram of a printing equipment in the hardware operating environment related to the embodiment solution of the present invention.

[0047] As Figure 1As shown in the figure, the printing device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, an interaction device 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The interaction device 1003 may include a display screen and an input unit such as a keyboard. Optionally, the interaction device 1003 may also be connected to the communication bus through a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (WI-FI) interface). The memory 1005 may be a high-speed Random Access Memory (RAM) or a stable Non-Volatile Memory (NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1 the structure shown in the figure does not constitute a limitation on the printing device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0049] As Figure 1 shown, the memory 1005, as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a printing device fault tracing and repair decision-making program based on a knowledge graph.

[0050] In Figure 1 the printing device shown, the network interface 1004 is mainly used for data communication with other devices; the interaction device 1003 is mainly used for data interaction with users; the processor 1001 and the memory 1005 in the printing device of the present invention may be arranged in the printing device. The printing device calls the printing device fault tracing and repair decision-making program based on the knowledge graph stored in the memory 1005 through the processor 1001, and executes the printing device fault tracing and repair decision-making method provided by the embodiments of the present invention.

[0051] The embodiments of the present invention provide a printing device fault tracing and repair decision-making method based on a knowledge graph. Referring to Figure 2 , Figure 2 it is a schematic flowchart of the first embodiment of a printing device fault tracing and repair decision-making method based on a knowledge graph of the present invention.

[0052] In this embodiment, the method for fault traceability and maintenance decision-making of printing equipment based on a knowledge graph includes:

[0053] Step S1, obtaining the operation data of the printing equipment, historical fault data, and the fault situation information at the current moment;

[0054] The fault situation information here can be the prompt information output by the machine, or it can also be the actual problem information determined by the management personnel of the printing equipment after discovering the fault. By recording the operation log of the printing equipment during operation and extracting the data related to the printer's work based on the operation log as the operation data, the operation data here does not include the personal privacy data of users. Optionally, after a fault occurs, the maintenance personnel record the maintenance log, and determine the historical fault data according to the maintenance log. In addition, the historical fault data can also be based on the fault data or abnormal data recorded by the equipment.

[0055] Step S2, updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data;

[0056] It should be clear that updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data does not add data to the fault traceability knowledge graph, that is, it does not add triple data to the basis of the fault traceability knowledge graph, that is, it does not add objects and relationships in the fault traceability knowledge graph. Each relationship in the fault traceability knowledge graph is set with a confidence, which reflects the reliability of this relationship for the two connected objects. In addition, in this field, the data in the triple data can also be called the head entity, relation, and tail entity. However, in this embodiment, the first object and the second object can be hardware entities or concepts other than entities. For example: printing process, ink state, paper parameters, fault type, etc. The relationship here is the edge connecting two points in the knowledge graph. Updating the confidence of the relationship in the fault traceability knowledge graph through the operation data and the historical fault data is actually dynamically adjusting the knowledge graph based on the current printing equipment. For example: when the printing equipment is in a single working mode for a long time, the confidence of the relevant relationships in the fault traceability knowledge graph can be adjusted to improve the accuracy of subsequent fault detection using the knowledge graph.

[0057] Step S3, determining the fault cause according to the fault situation information and the fault traceability knowledge graph.

[0058] In this embodiment, optionally, an initial node in the fault traceability knowledge graph is determined according to the fault situation information, and a relationship chain is searched based on the initial node to obtain multiple relationship chains; a target relationship chain is determined according to the multiple relationship chains and the confidence level of each relationship, and the fault cause is determined according to the target relationship chain. At the same time, the algorithm for determining the fault cause in the fault traceability knowledge graph based on the fault situation information is not limited. For example, the Dijkstra algorithm or the A* algorithm can be used to determine the target relationship chain, and the cause of the fault is identified according to the target relationship chain.

[0059] In this embodiment, by obtaining the operation data, historical fault data, and fault situation information at the current moment of the printing device, and updating the confidence level of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data, the knowledge graph can be adjusted for the actual working state of each printing device, so as to obtain a knowledge graph directly associated with the actual situation of the printing device, thereby improving the accuracy of the knowledge graph reasoning process and further improving the accuracy of fault identification.

[0060] Further, based on the first embodiment, a second embodiment of the printing device fault traceability and maintenance decision-making method based on the knowledge graph according to the present invention is proposed. In this embodiment, referring to Figure 3 , before the step of updating the confidence level of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data, it further includes:

[0061] Step S201, obtain the maintenance data of the printing device, and extract multiple triple data according to the maintenance data. The structure of the triple data is: first object, relationship, second object;

[0062] Specifically, obtain relevant data such as the instruction manual and maintenance manual of the printing device, extract triple data according to the instruction manual and maintenance manual, extract the text information of the instruction manual and maintenance manual, clean the noise information such as page numbers in the text, and identify entity objects after cleaning. After obtaining the entity objects, extract relationships according to preset rules, and regular expressions can be used for extraction, so as to obtain triple data of the first object, relationship, and second object.

[0063] Step S202, construct a fault traceability knowledge graph according to the multiple triple data.

[0064] Standardize the objects in each triple, that is, align different objects with the same meaning, record based on the string similarity algorithm, calculate the similarity between objects, and unify two objects with a similarity within a certain range into one object. Similarly, the relationships need to be standardized. For example: unify error codes, fault codes, and alarm codes; unify print settings, print options, and print parameters.

[0065] In this embodiment, a fault tracing knowledge graph is constructed from the maintenance data of the printing device, so that a complete knowledge graph for fault tracing can be obtained.

[0066] Furthermore, based on the first embodiment or the second embodiment, a third embodiment of the printing device fault tracing and maintenance decision-making method based on the knowledge graph of the present invention is proposed. In this embodiment, with reference to Figure 4 , the historical fault data includes: a historical fault relationship chain, which is a fault relationship chain obtained in the fault tracing knowledge graph based on a fault prompt before the current moment. The step of updating the confidence level of the relationship in the fault tracing knowledge graph according to the operation data and the historical fault data includes:

[0067] Step S21, determining an operation relationship chain according to the operation data;

[0068] The operation data here can involve the hardware or virtual concepts of one or more printing devices, and the objects whose states change are determined according to the operation data. For example: changes in ink content, changes in the position of the print head, changes in print settings, changes in the temperature of the drum unit, changes in the temperature of the power supply. The number of operation relationship chains here can be multiple, and there is no limitation on whether the operation relationship chains need to be connected.

[0069] Step S22, determining a first type of relationship and a second type of relationship in the fault tracing knowledge graph according to the historical fault relationship chain and the operation relationship chain. The first type of relationship is a relationship belonging to the historical fault relationship chain or a relationship belonging to the operation relationship chain, and the second type of relationship is a relationship other than the first type of relationship in the fault tracing knowledge graph;

[0070] The historical fault relationship chain here is a relationship chain generated based on the fault cause determined in the fault tracing knowledge graph at the current moment, and may only include the fault tracing of the current device, or may include: the historical fault relationship chain of the same model of printing device. After distinguishing the first type of relationship and the second type of relationship, their weight values can be updated in different ways.

[0071] Step S23, determining the weight value corresponding to each of the first type of relationships according to the historical fault relationship chain and the operation relationship chain, and setting the weight value of the second type of relationship to a preset value;

[0072] Count the number of times each of the first type of relationships appears in the historical fault relationship chain and the operation relationship chain respectively, and determine the corresponding weight value according to the statistical result;

[0073] Optionally, the calculation formula for the weight value is:

[0074] w i = αN(r i ) + βM(r i )

[0075] w i is the weight value of the first - type relationship for the i - th one, r i is the first - type relationship for the i - th one, N(r i ) is the number of times the first - type relationship for the i - th one appears in the historical fault relationship chain, M(r i ) is the number of times the first - type relationship for the i - th one appears in the operation relationship chain, and α and β are the coefficients corresponding to the historical fault relationship chain and the operation relationship chain respectively. The weight value of the second - type relationship here is set to a preset value. Preferably, this preset value is less than any of the weight values of the first - type relationships.

[0076] Optionally, α and β can be determined by historical faults and operating conditions. Specifically, when the frequency of the same fault occurring on the same type of printing equipment increases, the corresponding α coefficient can increase accordingly. Additionally, in special cases, the α coefficient can be negative. For example: when the equipment, due to a fault, has some components removed during the repair process, the α coefficient corresponding to this historical fault relationship chain is negative. For printing equipment, some models have minor improvements and actually do not have a separate corresponding instruction manual, which results in the fact that in the fault - tracing knowledge graph, not all relationships can be corresponding to the current printing equipment. For example: some hardware optimizations, driver updates, changes in the position of the cooling fan, etc. The weight formula of this embodiment, since it is determined based on operation data, can effectively reduce the error in fault determination caused by incorrect relationships in the fault - tracing knowledge graph due to the above - mentioned problems.

[0077] Furthermore, in some embodiments, different historical fault relationship chains correspond to different coefficients, that is, α j is the coefficient corresponding to the j - th historical fault relationship chain.

[0078] Determine the confidence level of each relationship according to all relationships and their corresponding weight values.

[0079] After obtaining the weight values, the weight data is not directly used as the confidence level of each relationship in the fault - tracing knowledge graph, but also needs to be adjusted according to the number of relationships related to the object in the fault - tracing knowledge graph.

[0080] In this embodiment, the weight value corresponding to each of the first type of relationships is determined through the historical fault relationship chain and the operation relationship chain, and the weight value of the second type of relationship is set to a preset value, so that the relationship changes caused by operation or faults can be effectively determined, and further the accuracy of determining the fault cause based on the fault traceability knowledge graph can be improved in the subsequent process.

[0081] Further, the step of determining the confidence level of each relationship according to all the relationships and the corresponding weight values includes:

[0082] Determine at least one target triple data associated with each target object according to the fault traceability knowledge graph, where the target triple data is triple data with the target object as the first object;

[0083] Here, the target object is an object in the fault traceability knowledge graph that can be used as the first object, that is, the head entity. An object that can only be used as the second object at the end cannot be a target object.

[0084] Calculate the target confidence level of each target relationship on the target object according to the target relationships of all the target triple data and the corresponding target weight data;

[0085] Take the target confidence level as the confidence level.

[0086] In this embodiment, each target object often corresponds to more than one relationship. Therefore, it is necessary to determine the confidence levels among the various relationships of the target object as a whole according to all the target triple data. The formula for calculating the confidence level is as follows:

[0087]

[0088] Specifically, P t is the target confidence level of the target relationship of the target triple data, w t is the target weight data, and T is the number of target triple data.

[0089] In this embodiment, at least one target triple data associated with each target object is determined through the fault traceability knowledge graph, the target confidence level of each target relationship on the target object is calculated according to the target relationships of all the target triple data and the corresponding target weight data; and the target confidence level is taken as the confidence level. Thus, the update of the fault traceability knowledge graph can be realized through the historical fault relationship chain and the operation relationship chain, ensuring that targeted corrections can be made for each or every type of printing equipment, and thus the corresponding faults of the anomalies can be determined more accurately.

[0090] Further, based on the third embodiment, a fourth embodiment of the method for fault tracing and maintenance decision-making of a printing device based on a knowledge graph according to the present invention is proposed. The operation data includes: the functions being run and the corresponding related components, and the running time. The step of determining the operation relationship chain according to the operation data includes:

[0091] Determine a plurality of related objects in the fault tracing knowledge graph according to the related components;

[0092] Determine the operation relationship chain according to the fault tracing knowledge graph and the plurality of related objects.

[0093] Specifically, each related component is respectively matched with the objects in the fault tracing knowledge graph, and the most similar object is matched as the related object. Optionally, the related objects are grouped according to the functions being run, and one operation relationship chain is determined for the related objects in each group, so that multiple operation relationship chains can be obtained. In other embodiments, for each related component, when the running time of the related component is greater than or equal to the preset running time, the related component is matched with the objects in the fault tracing knowledge graph, and the most similar object is matched as the related object. When the running time of the related component is less than the preset running time, the corresponding related relationship does not need to be determined.

[0094] For components with different running times, the components with long-term use are screened out according to the length of the running time, and the components running overloaded can be effectively identified. Using these components to determine the operation relationship chain can more accurately update the knowledge graph and improve the accuracy of subsequent determination of different faults.

[0095] Further, the step of determining the operation relationship chain according to the fault tracing knowledge graph and the plurality of related objects includes:

[0096] Calculate the first shortest path between any two of the related objects according to the fault tracing knowledge graph and the plurality of related objects, and obtain a plurality of the first shortest paths;

[0097] Determine the operation relationship chain according to the plurality of the first shortest paths and the Held-Karp algorithm.

[0098] In other embodiments, it is also possible to select the Neo4j graph database to construct the knowledge graph and use the built-in algorithm of Neo4j to determine the operation relationship chain.

[0099] In this embodiment, a plurality of related objects in the fault tracing knowledge graph are determined through the related components, and the operation relationship chain is determined according to the fault tracing knowledge graph and the plurality of related objects, so that the operation relationship chain can be accurately obtained.

[0100] Further, based on any of the embodiments, a fifth embodiment of the method for fault tracing and maintenance decision-making of a printing device based on a knowledge graph according to the present invention is proposed. The step of determining the target relationship chain according to the multiple relationship chains and the confidence level of each relationship includes:

[0101] Determine the relationship chain probability corresponding to each relationship chain according to a pre-designed calculation formula, the confidence level of each relationship, and each relationship chain;

[0102] Determine the target relationship chain according to the relationship probability of each relationship chain.

[0103] Sort all the relationship chains according to the relationship probability. The higher the relationship probability, the higher the ranking of the corresponding relationship chain. The relationship chain ranked first is used as the target relationship chain.

[0104] Further, after the step of determining the fault cause according to the target relationship chain, the following is further included:

[0105] Generate a corresponding maintenance decision according to the fault cause.

[0106] In this embodiment, the maintenance decision is determined by maintenance personnel or a preset maintenance plan according to different fault causes.

[0107] In addition, an embodiment of the present invention further proposes a system for fault tracing and maintenance decision-making of a printing device based on a knowledge graph. The system for fault tracing and maintenance decision-making of a printing device based on a knowledge graph includes:

[0108] An acquisition module, configured to acquire the operation data, historical fault data, and fault situation information at the current moment of the printing device;

[0109] An update module, configured to update the confidence level of the relationships in the fault tracing knowledge graph according to the operation data and the historical fault data;

[0110] An identification module, configured to determine the fault cause according to the fault situation information and the fault tracing knowledge graph.

[0111] It should be noted that in this article, the terms "include", "comprise" or any other variation thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0112] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0113] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0114] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for fault tracing and maintenance decision-making of printing equipment based on a knowledge graph, characterized in that, The method for fault traceability and maintenance decision-making of printing equipment based on a knowledge graph includes the following steps: Obtain the operation data of the printing equipment, historical fault data, and the fault situation information at the current moment; Update the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data; Determine the fault cause according to the fault situation information and the fault traceability knowledge graph.

2. The method for tracing and repairing decision-making of printing equipment faults based on a knowledge graph according to claim 1, wherein, The step of determining the fault cause according to the fault situation information and the fault traceability knowledge graph includes: Determine the initial nodes in the fault traceability knowledge graph according to the fault situation information, and search for relationship chains based on the initial nodes to obtain multiple relationship chains; Determine the target relationship chain according to the multiple relationship chains and the confidence of each relationship, and determine the fault cause according to the target relationship chain.

3. The method for tracing and repairing decision-making of printing equipment faults based on a knowledge graph according to claim 1, wherein, Before the step of updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data, it also includes: Obtain the maintenance materials of the printing equipment, and extract multiple triple data from the maintenance materials. The structure of the triple data is: the first object, the relationship, and the second object; Construct a fault traceability knowledge graph according to the multiple triple data.

4. The method for tracing and maintaining decision-making of printing equipment faults based on a knowledge graph according to claim 1, wherein, The historical fault data includes: historical fault relationship chains, which are the fault relationship chains obtained in the fault traceability knowledge graph based on fault prompts determined before the current moment. The step of updating the confidence of the relationships in the fault traceability knowledge graph according to the operation data and the historical fault data includes: Determine the operation relationship chain according to the operation data; Determine the first type of relationships and the second type of relationships in the fault traceability knowledge graph according to the historical fault relationship chains and the operation relationship chain. The first type of relationships are the relationships belonging to the historical fault relationship chains or the relationships belonging to the operation relationship chains, and the second type of relationships are the relationships other than the first type of relationships in the fault traceability knowledge graph; Determine the weight value corresponding to each of the first type of relationships according to the historical fault relationship chains and the operation relationship chain, and set the weight value of the second type of relationships to a preset value; Determine the confidence of each relationship according to all the relationships and the corresponding weight values.

5. The method for fault tracing and maintenance decision-making of a printing device based on a knowledge graph according to claim 1, wherein The step of determining the confidence of each relationship according to all the relationships and the corresponding weight values includes: Determine at least one target triple data associated with each target object according to the fault traceability knowledge graph. The target triple data is the triple data with the target object as the first object; Calculate the target confidence of each target relationship on the target object according to the target relationships and the corresponding target weight data of all the target triple data; Take the target confidence as the confidence.

6. The method for tracing and repairing decision-making of printing equipment faults based on a knowledge graph according to claim 4, characterized in that, The operation data includes: the functions being run and the corresponding related components, and the operation time. The step of determining the operation relationship chain according to the operation data includes: Determine multiple related objects in the fault traceability knowledge graph according to the related components; Determine the operation relationship chain according to the fault traceability knowledge graph and the multiple related objects.

7. The method for tracing and repairing decision-making of printing equipment faults based on a knowledge graph according to claim 6, wherein The step of determining the operation relationship chain according to the fault traceability knowledge graph and the multiple related objects includes: Calculate the first shortest path between any two of the relevant objects according to the fault traceability knowledge graph and the multiple relevant objects, and obtain a plurality of the first shortest paths; Determine the operation relationship chain according to the plurality of the first shortest paths and the Held-Karp algorithm.

8. The method for tracing and maintaining decision-making of printing equipment faults based on a knowledge graph according to claim 2, wherein The step of determining the target relationship chain according to the plurality of relationship chains and the confidence level of each relationship includes: Determine the relationship chain probability corresponding to each relationship chain according to a pre-designed calculation formula, the confidence level of each relationship, and each relationship chain; Determine the target relationship chain according to the relationship probability of each relationship chain.

9. The method for fault tracing and maintenance decision-making of a printing device based on a knowledge graph according to any one of claims 1 to 8, characterized in that After the step of determining the fault cause according to the fault situation information and the fault traceability knowledge graph, it further includes: Generate a corresponding maintenance decision according to the fault cause.

10. A printing equipment fault tracing and maintenance decision-making system based on a knowledge graph, characterized in that, The printing equipment fault traceability and maintenance decision-making system based on the knowledge graph includes: An acquisition module, configured to acquire the operation data, historical fault data of the printing equipment, and the fault situation information at the current moment; An update module, configured to update the confidence level of the relationship in the fault traceability knowledge graph according to the operation data and the historical fault data; An identification module, configured to determine the fault cause according to the fault situation information and the fault traceability knowledge graph.

Images